Cell and Landline Phone Usage Patterns among Young Adults and the Potential for Nonresponse Error in RDD Surveys. Draft (do not cite)

Size: px
Start display at page:

Download "Cell and Landline Phone Usage Patterns among Young Adults and the Potential for Nonresponse Error in RDD Surveys. Draft (do not cite)"

Transcription

1 Cell and Landline Phone Usage Patterns among Young Adults and the Potential f Nonresponse Err in RDD Surveys Draft (do not cite) Douglas Currivan, Joel Hampton, Niki Mayo and Burton Levine RTI International May 10, 2010 This paper was prepared f presentation at the American Association f Public Opinion Research annual meetings in Chicago on May 16, The auths thank the Flida Department of Health f suppting this research. All conclusions and opinions expressed in this paper are solely those of the auths.

2 Abstract A current challenge in conducting telephone surveys of adults is obtaining satisfacty representation among young adults. Surveys using traditional random digit dial (RDD) sample frames of landline numbers exclude the 38 percent of adults age 18 to 24 who live in households without landline phone service. In addition to this well documented coverage issue, a further problem is the potential difficulty in contacting and interviewing an additional set of about 19 percent of young adults who live in households with a landline phone, but primarily use a cell phone. RDD telephone surveys may further underrepresent the full population of young adults by excluding those who primarily rely on cell phones and are difficult to reach by landline phones. Young adults who primarily use cell phones may have imptant similarities to those who only have wireless phone service in terms of key survey measures. To understand the role of phone usage patterns in the potential f nonresponse err among young adults, this paper investigates the implications of patterns of cell phone and landline phone use among young adults f key survey outcomes. We use data from a statewide RDDbased survey on health behavis that targeted young adults age 18 to 24 and included both landline and cell phone numbers. Based on respondents answers to questions about their use of cell phones versus landline phones, we coded respondents into one of two categies: only/mostly cell phone users only/mostly landline phone users. We then examined patterns in both demographic characteristics and health indicats across these two categies. This analysis provided data on how young adults phone usage could potentially contribute to nonresponse err, beyond coverage err. We discuss the implications of these findings f the representation of young adults in RDD surveys measuring health behavis. Introduction A current challenge in conducting telephone surveys of adults is obtaining satisfacty representation among young adults. Surveys using traditional random digit dial (RDD) sample frames of landline numbers exclude the increasing number of adults age 18 to 24 who live in households without landline phone service. Using National Health Interview Survey (NHIS) data, Blumberg and Luke (2009) indicate 38 percent of adults in this age group do not live in households with a landline phone. In addition to this well documented coverage issue, a further problem in RDD surveys is the potential difficulty in contacting and interviewing young adults who live in households with a landline phone, but primarily ( only) respond to calls on their wireless phones. One potential source of nonresponse bias in surveys of young adults is that those who primarily use cell phones (1) may be me difficult to contact and interview and (2) may have significantly different data to rept on key survey measures, compared to young adults who primarily use landline phones. As Tucker, et al (2007) noted, nonresponse bias could be observed in dual 1

3 frame landline and cell phone surveys if certain types of people with both landline and cell phones primarily use their cell phones. Young adults phone usage patterns may therefe contribute significant nonresponse err to telephone surveys, even when households with all combinations of landline and cell phone service are covered by the sample frame. This paper investigates the implications of patterns of landline and cell phone use among young adults f key survey outcomes. The data we use are drawn from a statewide RDD based survey on tobacco use and other health behavis that targeted young adults age 18 to 24 and included both landline and cell phone samples. Based on respondents answers to questions on the presence, number, and sharing of cell phones in their household, we coded respondents into one of two categies: only/mostly cell phone users only/mostly landline phone users. We then examined patterns in both demographic characteristics and health indicats across these two categies. This analysis provided data on how young adults phone usage could potentially contribute to nonresponse err, beyond coverage err, in surveys measuring health behavis. Patterns of Phone Usage among Young Adults A starting assumption of this research is that young adults increasingly rely mostly on cell phones and other wireless devices f communication and, therefe, increasingly limit their use of landline phones in their households. Available evidence suppts this assumption. First, the percentage of adults age 18 to 24 who live in households with only wireless phone service increased from 10 percent in the first half of 2004 to about 33 percent in the first half of 2009 (Blumberg and Luke, 2007; Blumberg and Luke, 2009). Even greater reliance on wireless phones is observed among adults with characteristics typically associated with those in the 18 to 24 age range. F example, about 69 percent of all adults who live with unrelated roommates live in households with only wireless phone service (Blumberg and Luke, 2009). Although the NHIS data clearly indicate increasing reliance on cell phones over landline phone among 18 to 24 year olds, few studies have examined the phone usage patterns of young adults who currently live in households with landline phone service. Logically, young adults with both wireless and landline phone service should follow one of three phone usage patterns: (1) use wireless phone service significantly me than landline phone service, (2) use wireless phone service about the same as landline phone service, (3) use landline phone service significantly me than wireless phone service. We would expect almost all young adults to fall under either the first the third pattern, as it seems likely they would use one me than they would use the other. The increasing prevalence of cell phones among both youth and young adults would suggest most adults age 2

4 18 to 24 who have access to both types of phone service would generally fav cell phone usage over landline service and therefe fall into the first categy. Young adults who do not have wireless phone service have limited access to a cell phone would most likely fall under the third categy. We cannot rule out the possibility that a non trivial ption of adults age 18 to 24 confm to the second phone usage pattern, but we expect this proption of young adults to be relatively small and, therefe, have little if any impact on nonresponse bias in surveys of young adults. As a result, this research focuses on the differences between young adults who are primarily wireless phone users versus those who are primarily landline phone users. The Potential Impact of Phone Usage Patterns on Survey Estimates The primary objective of this paper is to assess how phone usage patterns among young adults could potentially contribute to nonresponse bias. If young adults who primarily use cell phones were significantly less likely to respond to survey calls than those who primarily use landline phones, we would expect a significant potential f bias in at least some survey measures. Even when other adults such as parents roommates identify a young adult in the household who is then selected to participate in the survey, those who rarely use the landline phone would likely be me difficult to interview than those who regularly do so. This research assesses how phone usage patterns among young adults might be related to survey estimates on tobacco use and other health indicats. Blumberg and Luke (2009) demonstrate the potential impact of non coverage of young adults due to wireless substitution on health indicats using NHIS data from the first half of These data indicate that, compared to adults with landline phone service, adults living in households with only wireless service had a number of negative health indicats, including: me likely to engage in binge drinking, me likely to be current smokers, me likely to experience serious psychological distress, less likely to be without health insurance coverage, and me likely to encounter financial barriers to obtaining needed health care. Adults living in households with only cell phone service also differed from adults with landline phone service on two indicats that reflected me positive health outcomes, including: me likely to rept their health status as excellent very good and less likely to have ever been diagnosed with diabetes. These observed differences in behavial health indicats appear to be driven primarily by the fact that younger adult are me likely to live in cell phone only households than older adults. 3

5 This fact also appears to explain some key demographic differences between wireless only households and those with landline phones. F example, the NHIS finding that 69 percent of all adults living with unrelated roommates lived in households with only wireless telephones is likely attributable to young adults who only have cell phones and live in college dmities apartments with roommates (Blumberg and Luke, 2009). This was the highest prevalence rate of cell phone only adults among all of the population subgroups they examined using NHIS data. Similarly, Blumberg and Luke (2009) found adults renting their homes (40.9%) were over three times me likely than adults who own their homes (12.8 %) to be living in households with only wireless phone service. Both of these findings appear to be influenced by the phone service status among younger adults. Furtherme, even within the young adult population, there may be differences in behavis between those with cell phones only and those with landline service. Delnevo, Gunderson, and Hagman (2007) conclude that observed declines in cigarette smoking and alcohol use among young adults in the Behavial Risk Facts Surveillance System (BRFSS) from 2003 to 2005 are artifacts of under coverage of young adults without landline service. These auths note that we have not observed similar declines in surveys based on area probability samples, such as the NHIS and the National Survey of Drug Use and Health (NSDUH). In a survey including only a landline phone sample, Currivan, Roe, and Stockdale (2008) found significant differences on a number of self repted health indicats between young adults who mostly relied on cell phones and those who mostly relied on landline phones. These auths found young adults who mostly used cell phones were less likely to have health insurance coverage, me likely to have recently experienced mental health problems, me like to be current smokers, and me likely to have recently engaged in binge drinking. These findings were remarkably similar to the differences Blumberg and Luke (2007, 2009) have observed between all adults who only have cell phones mostly use cell phones versus those who mostly use landline phone do not have cell phones. The findings of Currivan, et al (2008) suggest that young adults who only/mostly use cell phones may to differ from those who only/mostly use landline phones on key health indicats. About 60 percent of adults age 18 to 24 currently have landline phone service and could therefe be included in landline based surveys (Blumberg and Luke, 2009). In telephone surveys, errs of omission may affect survey estimates from both noncoverage and nonresponse. F example, young adults may use a landline phone service to receive voice mail messages, but not regularly receive place calls on a landline phone. Further limits to the responsiveness of young adults to landline phone calls may occur when landline phone service is shared with parents roommates. F example, young adults who live with parents may not associate themselves with this phone service and therefe be difficult to reach f a survey. We exple young adults phone usage patterns f both cell and landline phone to see whether 4

6 their behavi indicates any potential f nonresponse err in a survey using both cell and landline numbers. If young adults who only/mostly use cell phones are me difficult to reach f a survey and than those who only/mostly use landline phones, and these two groups differ significantly on key survey estimates, the potential f nonresponse bias exists. Research Questions To understand young adults phone usage patterns and the potential impact of these patterns on survey estimates, this research seeks answer to two questions: 1. How do facts like having landline phone service, multiple cell phones in the household, and shared cell phone influence young adults cell phone usage behavi? 2. How are cell and landline phone usage patterns related to demographic characteristics and health indicats among young adults? Methods The data we use to address our two research questions come from the Flida Young Adult Tobacco Survey (FL YATS). The Flida Department of Health sponsed the FL YATS. RTI designed the FL YATS to understand how Flida Department of Health programs may have been influencing smoking rates among young adults and to provide insight into optimal ways to curb smoking by young adults. F this reason, the study included measures of smoking, other related health behavis, and additional facts that could influence these behavis among adults age 18 to 24. Households were sampled via two frames: (1) List assisted landline RDD, supplemented by directy listed numbers to increase sample efficiency in reaching households with at least one eligible adult age 18 to 24 (2) Cell phone RDD from a frame of all cell phone numbers with Flida area codes. Therefe, all young adults living in Flida households with either landline wireless phone service ( both) were in they covered via this dual sample frame. The sample frame only excluded young adults who did not have either type of phone service. F both frames, we randomly selected phone numbers to generate the expected amount of numbers needed to reach the interviewing goals f each stratum. The iginal goal f the landline sample was 1,850 completed interviews and 350 f the cell phone sample. When identified, one adult age 18 to 24 was selected in each household. If me than one person in the household was in the eligible age range, the survey protocol included a procedure where the interviewer enumerated all eligible adults and their gender, and then the CATI program randomly selected one of the eligible adults. In general, participants were contacted and interviewed via the type of phone line from which they were sampled (landline cell 5

7 phone line). If upon contact with a member of a household it was determined that the sample type did not match the current phone service f a given number, interviewers coded the case as ineligible and did not complete a household screening interview. About 0.3 percent of landline phone numbers were determined to be associated only with cell phone numbers and only about 0.02 percent of cell phone numbers were found to be associated only with landline numbers. Overall, 2,044 adults age 18 to 24 completed the FL YATS. Of these, 1,658 respondents came from the landline phone sample and 386 from the cell phone sample. In addition, 2,012 of the interviews were completed in English (98.4 percent) and 32 (1.6 percent) in Spanish. Although few respondents completed the interview in Spanish overall, the proption of Spanish interviews (40.6 percent) completed by cell phone was much higher than the proption of English interviews (18.5 percent) completed by cell phone. F the landline phone sample, the estimated eligibility rate f all sample cases was 16.4 percent. F the cell phone sample, the estimated eligibility rate f all cases was 17.1 percent. Facting these estimated eligibility rates f all cases with an unknown status into the AAPOR RR 4 calculation, the overall response rate was 28.1 percent f the landline sample and 8.3 percent f the cell phone sample. 1 Among eligible young adults contacted and identified, the AAPOR COOP 1 cooperation rate was 81.0 percent f the landline sample and 39.1 percent f the cell phone sample. Consistent with these two outcome rates, the AAPOR REF 2 refusal rate f the cell phone sample (12.9 percent) was about double the refusal rate f the landline sample (6.6 percent). F both landline and cell phone respondents, the average interview length was about 29 minutes, with an average of 26 minutes f non smokers and 32 minutes f current smokers. In addition to items on smoking behavi and related health indicats, the FL YATS interview included a number of basic demographic items, such as age, gender, Hispanic/Latino igin, race, employment status, housing type, and marital status. The FL YATS survey items concerning usage of landline and wireless phone service were modeled after Current Population Survey (CPS) questions repted by Tucker, Brick, and Meekins (2007). A key feature of the cell phone service item was clearly indicating that this question referred to phones intended f personal use, as opposed to business use (Brick, et al, 2007). Three of the four items on phone usage patterns were adapted from CPS questions repted by Tucker, et al (2007). The fourth usage item, referring to the likelihood of answering cell versus landline phone calls, was devised by the lead auth. 1 Data collection f the cell phone sample was terminated once the target number of interviews was reached, which reduced the final response rate obtained. 6

8 Analysis The analysis was conducted in three phases: 1. Examining cell phone usage by whether (1) landline phone service was available in the household, (2) only one me than one cell phone was in the household, and (3) there were any shared cell phones in the household. 2. Using the cell phone and landline phone service and usage questions to classify respondents into one of two categies: only/mostly cell phone users only/mostly landline phone users. 3. Examining patterns of how demographic items and health indicats are similar different across the two phone usage types (only/mostly cell phone users only/mostly landline phone users). We use these analyses to address our two research questions on potential barriers to young adults participation in telephone surveys associated with their phone usage patterns, and the consequences of these barriers f survey outcomes. Results Research Question 1 Our first question concerned how young adults cell phone usage was related to three potential influences: 1. whether landline phone service was available in the household, 2. whether only one, me than, one cell phone was in the household, 3. whether there were any shared cell phones in the household. This analysis was based on a survey item asking respondents How many calls to your cell phone other wireless device do you answer when you don t recognize the caller s phone number? This question was adapted from Tucker, et al (2007) and was intended to gauge how likely respondents were to answer unsolicited calls on their cell phone, such as survey calls. Table 1 shows about 44 percent of FL YATS participants who had both landline and cell phone service would answer either all almost all me than half of calls they received on their cell phone when they did not recognize the caller s phone number. F respondents who only had cell phone service, about 48 percent indicated they would answer either all almost all me than half of calls they received on their cell phone when they did not recognize the caller. This difference was not statistically significant. This finding indicates young adults did not differ meaningfully in how likely they were to answer calls from unknown callers on their cell phone, based on the phone service in their homes. 7

9 Table 1. Likelihood of Answering Cell Phone by Phone Service in Household How many calls to your cell phone other wireless device do you answer when you do not recognize the caller s phone number? Both Landline and Cell Service (n = 1,464 unweighted) Cell Phone Service Only (n = 238 unweighted) All almost all 33.8% 34.1% Me than half 10.8% 13.7% Less than half 14.1% 10.1% Very few none 41.4% 42.1% Table 2 indicates about 45 percent of respondents who had the only cell phone in their household would answer either all almost all me than half of calls they received on their cell phone when they did not recognize the caller s phone number. Among those who had me then one cell phone in their home, a similar 46 percent indicated they would answer either all almost all me than half of calls they received on their cell phone when they did not recognize the caller. This difference was also not statistically significant. This result suggests young adults did not differ meaningfully in how likely they were to answer calls from unknown callers on their cell phone, regardless of whether they had only one me than one cell phone in their homes. A further point to note on this comparison is that an overwhelming majity of respondents indicated having me than one cell phone in their household. Table 3 shows about 48 percent of respondents who had no shared cell phones in their household would answer either all almost all me than half of calls they received on their cell phone when they did not recognize the caller s phone number. Looking at those who had at least one shared cell phone in their home, a similar 46 percent indicated they would answer either all almost all me than half of calls they received on their cell phone when they did not recognize the caller. As with the pri two facts, the difference between these two types of respondents was not statistically significant. This finding indicates young adults did not differ meaningfully in how likely they were to answer calls from unknown callers on their cell phone, regardless of whether they had a shared cell phone in their homes. A further point to note on this comparison is that a substantial ption of respondents (about 35 percent) indicated they had at least one shared cell phone in their home. 8

10 Table 2. Likelihood of Answering Cell Phone by Number of Cell Phones in Household How many calls to your cell phone other wireless device do you answer when you do not recognize the caller s phone number? Only One Cell Phone in Household (n = 145, unweighted) Me than One Cell Phone (n = 1,545, unweighted) All almost all 35.6% 33.5% Me than half 9.5% 12.4% Less than half 14.9% 11.9% Very few none 40.0% 42.1% Research Question 2: Phone Usage Patterns Our second research question required two steps, (1) using self repted phone use behavis to classify respondents into two distinct phone usage patterns and (2) examining how demographic characters and health indicats differed across these two phone usage types. To complete the first step, we developed an algithm to code respondents as either only/mostly cell phone users only/mostly landline users. We based this algithm on the response patterns of young adults to the following series of questions: {Ask K7 if cell sample; else if landline sample go to K9} K7. Not including cell phones, other wireless devices, phone numbers that are only used by a computer fax machine f business, do you have one me regular telephone numbers in your household that are residential numbers? {Ask K9 if landline sample; else if cell sample, go to K10} K9. Do you currently have a wking cell phone other wireless device f making outgoing calls and receiving incoming calls f your personal use? {Ask K14 if landline sample and K9=1(yes); ask K14 if cell sample and K7 = 1(yes); else go to K15} K14. Compared to answering your regular home phone, how likely are you to answer your cell phone other wireless device when you are at home? Would you say 1 I am me likely to answer my cell phone than I am my home phone 2 I am less likely to answer my cell phone than I am my home phone 3 I am just as likely to answer my cell phone as I am my home phone {Ask K15 if cell sample K9=1(yes); else go to K16} 9

11 Table 3. Likelihood of Answering Cell Phone with Shared Cell Phone in Household How many calls to your regular home phone do you answer when you don t recognize the caller s phone number? No Shared Cell Phones in Household (n = 346, unweighted) At Least One Shared Cell Phone (n = 1,305, unweighted) All almost all 40.9% 32.5% Me than half 7.2% 13.2% Less than half 11.0% 12.8% Very few none 40.9% 41.5% K15. How many calls to your cell phone other wireless device do you answer when you don t recognize the caller s phone number? 1 All almost all calls, 2 Me than half, 3 Less than half, 4 Very few none {Ask K16 if landline sample K7=1(yes)} K16. How many calls to your regular home phone do you answer when you don t recognize the caller s phone number? 1 All almost all calls, 2 Me than half, 3 Less than half, 4 Very few none By categizing respondents using their responses to these survey items, we used both absolute and relative indicats. Questions K7 and K9 were absolute indicats, in that respondents either did did not have each type of phone service in their households. Therefe, f example, we classified all respondents who only had a cell phone into the only/mostly cell phone user categy and those only had a landline phone into the only/mostly landline group. This allowed us to categize the 239 respondents ( 12.2 percent of those that could be coded) who indicated having only wireless service as only/mostly cell phone users and the 113 respondents ( 5.8 percent) who only had landline service as only/mostly landline users. The majity of respondents (1,614, 82.1 percent) had both cell and landline service. Therefe, we could not code most respondents into one of the two phone usage groups based solely on their current phone service. 10

12 Since over 80 percent of FL YATS respondents had both cell phone and landline phone service in their homes, we used questions K14 through K16 to determine whether they were me likely to respond to calls to their cell phones than their landline phones, vice versa. Using these relative items was an imptant part of the coding scheme. As Boyle, Lewis, and Tefft (2009) have pointed out, using infmation about the likelihood of sample members responding to calls on either type of phone is the most accurate way to determine phone usage patterns. Other indicats, such as the proption of calls received on each type of phone, do not actually tell us how likely people are to respond when called f a survey. F respondents who had both cell phone and landline phones and answered K14=1, we coded them as only/mostly cell phone users. F respondents who had both cell phone and landline phones and answered K14=2, we coded them as only/mostly landline phone users. F respondents who had both cell phone and landline phones and answered K14=3 did not provided a valid response to K14, we categized their phone usage based on their responses to questions K15 and K16. F example, among respondents who had both cell phone and landline phones and answered K14=3, we coded them as only/mostly cell phone users if they indicated in K15 that they answered me calls to their cell phones than they indicated f their landline phones in K16. In this way, we facted almost all response patterns to K15 and K16 into the classification of respondents as either only/mostly cell phone users only/mostly landline phone users, including cases where respondents answered only one of these items. The Appendix details the logical criteria used to categize respondents into one of the phone usage types. Table 4 shows the unweighted results of classifying FL YATS respondents into two phone usage types. As expected, a significantly greater proption of young adults were in the categy only/mostly cell phone users (about 54 percent) than the categy only/mostly landline phone users (about 46 percent). Weighting these figures to the population totals indicates that the phone usage split is somewhat greater than observed among the FL YATS respondents. Weighting produces an estimate of 812,000 only/mostly cell phone users (about 57 percent Table 4. Classification of Respondents into Two Phone Usage Types (unweighted) Phone Usage Type* Proption of Respondents Number of Respondents 1. Only/mostly cell phone user has cell phone and either does not have landline phone has landline phone and indicates greater use of cell phone 54.2 % 1, Only/mostly landline user has landline phone and either does not have cell phone has cell phone and indicates greater use of landline phone 45.8 %

13 of the population) and 619,000 only/mostly landline phone users (about 43 percent of the population). These calculations indicate the FL YATS slightly underrepresented young adults who only mostly use cell phones and slightly overrepresented those who only mostly use landline phones. Despite specifying 15 criteria to classify respondents within each of the phone usage types, we were not able to code all respondents using this scheme. The two primary reasons we were not able to categize these respondents as either only/mostly cell phone users only/mostly landline phone users were: 1. item nonresponse on too many of the five survey questions used in the calculation to allow coding, 2. responses to questions K14 through K16 that did not clearly indicate greater use of one type of phone compared to the other. Overall, we could not classify 81 respondents (about 5 percent). We also considered coding respondents into me detailed categies of phone usage. Given that we were able to classify about 96 percent of respondents into two meaningful categies, we limited our analysis to these two categies f simplicity and usefulness of interpretation. Research Question 2: Demographic Characteristics & Health Indicats by Phone Usage Type In addition to improving our basic understanding of current patterns of phone behavi among young adults, our purpose in classifying young adults by phone usage types was to assess whether (and how) survey estimates might differ based on phone usage. Comparison of FL YATS respondent by phone usage types could indicate the potential impact of nonresponse on survey data. F example, respondents who were classified as primarily cell phone users, even if they had landline service in their home, could exhibit behavis similar to young adults who only have cell phone service. Among all adults, research suggest we should expect those who mostly exclusively use cell phones to differ from those who rely mostly exclusively on landline phones both in terms of demographic characteristics such as age and housing situation and health indicats such as smoking and binge drinking (Blumberg and Luke, 2009; Delnevo, Gunderson, and Hagman, 2007). Table 5 presents the results of comparing respondents who were categized as only/mostly cell phone users with those who were only/mostly landline phone users on six demographic characteristics. FL YATS respondents in the two phone usage categies had similar distributions on age, gender, and race/ethnicity. Three demographic differences were observed across the two phone usage groups: 1. Employment/student status. Young adults who were only/mostly cell phone users and those who were only/mostly landline cell phone users differed with respect to their employment and student status. Respondents who were only/mostly cell phone users (43.1 percent) were significantly me likely than those who were 12

14 Table 5. Demographic Characteristics by Phone Usage Type Survey Measure Only/mostly Cell Phone User (n = 1,063) Only/mostly Landline User (n = 900) Age 18 to to 24 Gender Male Female Race/ethnicity Hispanic, any race Non Hispanic Black Non Hispanic White Other race/ethnicity Employment / Student Status Employed, non student * Primarily student # Out of wk * Other # Housing Type Own apartment house # Parents apartment house College dmity * Marital Status Currently married # Living with partner Never/not married 42.9 % 57.1 % 51.4 % 48.6 % 25.6 % 51.4 % 18.7 % 4.3 % 43.1 % 32.0 % 21.8 % 3.1 % 32.1 % 61.4 % 6.5 % 9.1 % 11.3 % 79.6 % 37.8 % 62.2 % 51.1 % 48.9 % 22.4 % 53.4 % 21.4 % 2.8 % 33.2 % 24.7 % 34.3 % 7.8 % 40.3 % 59.3 % 0.4 % 16.6 % 8.7 % 74.7 % * Difference in proptions between the two phone usage types was statistically significant at p <.05. # Difference in proptions between the two phone usage types was not statistically significant at p <.05, but was marginally significant at p <.10. only/mostly landline phone users (33.2 percent) to be employed non students and they were significantly less likely (21.8 percent) than only/mostly landline users (34.3 percent) to be out of wk. A greater proption of respondents who were only/mostly cell phone users (32.0 percent) identified themselves as students than only/mostly landline phone users (24.7 percent), although this test statistic of.070 was above the conventional p <.05 level. A smaller proption of respondents who were only/mostly cell phone users (3.1 percent) ended up in the other categy f employment/student status than only/mostly landline phone users (7.8 percent), although the p value f the test statistic was

15 2. Housing type. Consistent with the data on student status, respondents who were only/mostly cell phone users (6.5 percent) were significantly me likely than only/mostly landline phone users (0.4 percent) to live in a college/university dmity. Those who were only/mostly cell phone users (32.1 percent) also appeared to be less likely than only/mostly landline phone users (40.3 percent) to live in their own apartment house, but this difference was not statistically significant at the conventional p <.05 level. About 60 percent of young adults in each phone usage categy indicated living in parents guardians homes. 3. Marital status. Respondents who were only/mostly cell phone users (9.1 percent) were less likely than only/mostly landline phone users (16.6 percent) to be currently married. This difference was not statistically significant at the conventional p <.05 level, but the p value f this significance test was.054. This finding indicates those young adults who rely me on landline phones are somewhat me likely to be married than those who rely mostly on cell phones. This pattern of findings suggests a few implications f reaching young adults by cell phone landline phone in a survey: Given that respondents who were only/mostly cell phone users were me likely to be employed and me likely to be students than those who were only/mostly landline phone users, the only/mostly cell phone users may be me difficult to reach by either a cell landline phone. The only/mostly landline phone users were much me likely to suggest their current employment status was other, indicating they would likely have fewer schedule demands that could make it difficult f them to respond to survey calls. Given that respondents who were only/mostly cell phone users were less likely to live in their own apartment and me likely to live in college/university housing than those who were only/mostly landline phone users, the only/mostly cell group would be me likely to have roommates. These sample members may therefe be less likely to answer a shared ( partially shared) cell landline phone than young adults who live in their own home. Given that respondents who were only/mostly cell phone users were less likely to be married than those who were only/mostly landline phone users, only/mostly cell sample members could be me difficult to reach via a shared cell landline phone. F example, married couples would be somewhat me likely to know their spouses schedules than roommates perhaps even parents. Therefe, it could be me difficult to reach selected only/mostly cell users who live with roommates parents rather than spouses partners. While some of the demographic differences between only/mostly cell users and only/mostly landline users indicate possible differences in being able to reach young adults in each group, 14

16 the potential f nonresponse bias rests on whether young adults in each group have different substantive data to rept. If young adults who are only/mostly cell phone users are me difficult to reach to complete survey interviews than those who are only/mostly landline users, but the two groups respond similarly to health indicats, we would not observe nonresponse bias by underepresenting only/mostly cell users in these survey data. We would only have a significant potential to observe nonresponse bias due to differential ability to reach young adults if the only/mostly cell users and only/mostly landline users differ significantly with respect to health indicats Table 6 presents FL YATS responses to nine health indicats across the two phone usage groups. F most of these indicats, we observed no significant differences between the only/mostly cell phone users and the only/mostly landline phone users. We did observe differences on the following three health indicats: 1. Health insurance coverage. Young adults who were only/mostly cell phone users (59.4 percent) appeared to be me likely than those who were only/mostly landline phone users (50.5 percent) to indicate having some fm of health insurance coverage. This difference was not statistically significant at the conventional p <.05 level, but the p value was.07, suggesting that there may have been a meaningful difference between the two groups on this indicat. Assuming this difference was meaningful, this finding was inconsistent with repts by Blumberg and Luke (2007, 2009) and Currivan, et al (2008) who found those who relied me on cell phones than landline phone were actually less likely to have health insurance coverage. 2. Physical Health in Past 30 Days. FL YATS respondents who were only/mostly cell phone users (18.9 percent) appeared to be me likely than only/mostly landline phone users (13.6 percent) to indicate their physical health was not good f three me days in the past month. This difference was not statistically significant at the conventional p <.05 level, but the p value was less than.10, suggesting that there was actually a meaningful difference between the two groups on this indicat. 3. Binge drinking. Respondents who were only/mostly cell phone users (30.7 percent) were significantly me likely than only/mostly landline phone users (16.8 percent) to rept binge drinking in the past 30 days. This finding was consistent with repts by Blumberg and Luke (2007, 2009) f all adults, which showed those who live in wireless only households were me likely than those who have landline phones to rept binge drinking in the past 30 days. Overall, we found few examples of differences between only/mostly cell users and only/mostly landline users on common health indicats. The FL YATS data indicate that telephone surveys of young adults could potentially overstate health insurance coverage and recent physical 15

17 Table 6. Health Indicats by Phone Usage Type Survey Measure Health Insurance Status # Any fm of health insurance No health insurance coverage General Health Status Po/Fair/Good Very Good/Excellent Mental Health Status in Past 30 Days Average less than 2.0 days Average 2.0 days greater Physical Health Not Good in Past 30 Days # Less than 3 days 3 days me Moderate Physical Activities in Past 30 Days Less than 3 days 3 days me Seen Health Professional in Past 12 Months Yes No Current Smoking Status 2 Non smoker Smoker Currently Use Chew Tobacco/Snuff/Dip Yes No Binge Drinking in Past 30 Days * 0 times 1 me times Only/mostly Cell Phone User (n = 1,063) 59.4 % 40.6 % 33.3 % 66.7 % 82.7 % 17.3 % 81.1 % 18.9 % 15.1 % 84.9 % 68.0 % 32.0 % 76.0 % 24.0 % 2.6 % 97.4 % 69.3 % 30.7 % Only/mostly Landline User (n = 900) 50.5 % 49.5 % 39.3 % 60.7 % 83.3 % 16.7 % 86.4 % 13.6 % 15.9 % 84.1 % 61.4 % 38.6 % 72.5 % 27.5 % 6.4 % 93.6 % 83.2 % 16.8 % * Difference in proptions between the two phone usage types was statistically significant at p <.05. # Difference in proptions between the two phone usage types was not statistically significant at p <.05, but was marginally significant at p < Respondents who had (1) smoked at least 100 cigarettes in their life and (2) currently smoke cigarettes every day some days were classified as current smokers; otherwise, respondents were coded as non smokers. 16

18 health problems and understate recent binge drinking, if those who rely only/mostly on cell phones are underrepresented due to nonresponse. These findings suggest differential participation rates between only/mostly cell phone users and only/mostly landline phone users would not significantly bias estimates f six other health indicats among young adults. Discussion This research examined phone usage behavi among young adults age 18 to 24 in der to assess the potential f nonresponse err in RDD surveys using landline and cell phone. We first looked at how landline and wireless phone service might influence cell phone usage among young adults. The presence of landline phone service, multiple cell phones in the household, one me shared cell phones did not appear to have a significant association with young adults likelihood of answering calls to their cell phone. This could be viewed as good news f survey researchers interviewing young adults via cell phones. Different configurations of landline and cell phone service in the household did not seem to have a strong influence on the ability to reach young adults via cell phone. Next, we attempted to categize all FL YATS respondents phone usage patterns as being either only/mostly cell phone users versus only/mostly landline phone users, based on a series of questions about phone service and likelihood of answering calls on each type of phone. Our algithm coded 96 percent of respondents into one of the two categies, suggesting most young adults can be categized as using one type of phone me than the other type. We observed a few key differences in demographic characteristics between respondents who were coded as only/mostly cell phone users versus those who were coded as only/mostly landline phone users. Demographic differences in employment/student status, housing type, and marital status between the two phone usage groups suggested young adults who only/primarily use cell phones might be me difficult to reach by either cell landline phones. Among the FL YATS respondents, the only/mostly cell users (mean of 4.40 attempts) did not actually require a significantly greater number of call attempts than only/mostly landline users (mean of 4.24 attempts) to complete the interview. Although we found a few demographic differences between only/mostly cell users and only/mostly landline users that indicated potentially different response propensities, we found limited evidence that these two groups of young adults differed significantly on several key health indicats. Young adults who only/mostly used cell phones were me likely than only/mostly landline users to have some fm of health insurance, to rept recent physical health issues, and to have recently engaged in binge drinking. Only the finding f recent binge drinking was consistent with results from Blumberg and Luke s (2009) comparison of cell phone only individuals with those who had landline service and with Currivan, et al s (2008) comparison of mostly cell users with those who were only/mostly landline users. Research comparing only/mostly cell users and only/mostly landline users has generally shown that 17

19 adults who rely only mostly on cell phones are less likely to have health insurance coverage and current physical health problems. We did not observe any significant differences on six additional health indicats. Many of these indicats have also been shown by Blumberg and Luke (2007, 2009) to differ between adults in cell only households and those with landlines. Overall, our findings f health indicats are mostly inconsistent with recent research making similar comparisons. At least three facts could explain why we did not observe me differences on health indicats between young adults who were only/mostly cell phone users and only/mostly landline phone users. First, the data we examined only included adults age 18 to 24. Blumberg and Luke s (2007, 2009) research includes all adults. The differences they have observed between adults in cell only households and those with landlines appear to be strongly related to age. Differences among the youngest adult age group on common health indicats may simply not be as great as they are among all adults. Second, our sample was further restricted to a single state, Flida. Although we have no evidence indicating young adults health behavi is significantly different in Flida compared to other regions states, we cannot generalize these findings beyond this limited population. The possibility remains that a significant ption of adults 18 to 24 in Flida provided different response patterns to the health indicats than we would have observed in other states across the entire country. Third, the definition and criteria we used f categizing respondents as only/mostly cell phone users versus only/mostly landline users were quite different than used in Blumberg and Luke s research (2007, 2009). F example, Blumberg and Luke (2009) defined respondents as mostly cell phone user based on survey items asking about the proption of calls received on each type of phone, not the actual likelihood of answering calls to each type of phone. Our approach and conclusions were similar to Boyle, et al (2009). The tentative conclusion is that differences between young adults based on their phone service and stated likelihood of responding to phone calls do not identify two vastly different subgroups of survey respondents. This is an imptant methodological point f investigating the potential f nonresponse bias based on phone usage patterns. Measuring actual propensity to respond to survey calls is the most useful approach to identifying subgroups that have different data to rept and, therefe, the potential to introduce nonresponse bias. Overall, this research suggests that young adults who rely only mostly on cell phones may be somewhat me difficult to reach in phone surveys than those who rely only mostly on landline phones. Still, we find little evidence that those who only/mostly use cell phones differ significantly on a number of health indicats from those who only/mostly use landline phones. Therefe, we did not observe much potential f nonresponse bias due to different challenges in reaching and interviewing young adults with different patterns of cell phone and landline usage. 18

20 References Blumberg, Stephen J. and Julian V. Luke. Wireless substitution: Early release of estimates from the National Health Interview Survey, January June National Center f Health Statistics. Available from December Blumberg, Stephen J. and Julian V. Luke. Wireless substitution: Early release of estimates from the National Health Interview Survey, January June National Center f Health Statistics. Available from December Blumberg, Stephen J. and Julian V. Luke Coverage bias in traditional telephone surveys of low income and young adults. Public Opinion Quarterly 71: Boyle, John, Faith Lewis, and Brian Tefft Cell phone mainly households: Coverage and reach of telephone surveys using RDD landline samples. Survey Practice, December: Brick, J. Michael, Pat D. Brick, Sarah Dipko, Stanley Presser, Clyde Tucker, and Yangyang Yuan Cell phone survey feasibility in the U.S.: Sampling and calling cell numbers versus landline numbers. Public Opinion Quarterly 71: Currivan, Douglas B., David J. Roe, and Jason Stockdale. (2008). Landline and cell phone usage patterns among young adults. Presented at the American Association f Public Opinion Research annual conference, New Orleans, LA. Delnevo, Cristine D., Daniel A. Gundersen, and Brett T. Hagman. Declining estimated prevalence of alcohol drinking and smoking among young adults nationally: Artifacts of sample undercoverage? American Journal of Epidemiology Advance Access published October 31, Tucker, Clyde, J. Michael Brick, and Brian Meekins Household telephone service and usage patterns in the United States in 2004: Implications f telephone samples. Public Opinion Quarterly 71:

21 Appendix: Coding Scheme f Determining Phone Usage Type Code as only/mostly cell users if: 1. Cell phone respondent and K7 = 2 2. Cell phone respondent and K7 = 1 and K14 = 1 3. Landline respondent and K9 = 1 and K14 = 1 4. Cell phone respondent and K7=1 and K14 = 3 and K15 < K16 (when both K15 & K16 have valid responses) 5. Landline phone respondent and K9=1 and K14 = 3 and K15 < K16 (when both K15 & K16 have valid responses) 6. Cell phone respondent and K7 = 1 and K14 = 3 and K15 < 2 (when only K15 has a valid response) 7. Landline respondent and K9 = 1 and K14 = 3 and K15 < 2 (when only K15 has a valid response) 8. Cell phone respondent and K7 = 1 and K14 = 3 and K16 > 3 (when only K16 has a valid response) 9. Landline respondent and K9 = 1 and K14 = 3 and K16 > 3 (when only K16 has a valid response) 10. Cell respondent and K7=1 and K14= 1/ 2/missing and K15 < K16 (when both K15 & K16 have valid responses) 11. Landline respondent and K9=1 and K14= 1/ 2/missing and K15 < K16 (when both K15 & K16 have valid responses) 12. Cell respondent and K7 = 1 and K14 = 1/ 2/missing and K15 < 2 (when only K15 has a valid response) 13. Landline respondent and K9=1 and K14= 1/ 2/missing and K15<2 (when only K15 has a valid response) 14. Cell respondent and K7=1 and K14= 1/ 2/missing and K16>3 (when only K16 has a valid response) 15. Landline respondent and K9=1 and K14= 1/ 2/missing and K16>3 (when only K16 has a valid response) 20

Cell and Landline Phone Usage Patterns among Young Adults and the Potential for Nonresponse Error in RDD Surveys

Cell and Landline Phone Usage Patterns among Young Adults and the Potential for Nonresponse Error in RDD Surveys Cell and Landline Phone Usage Patterns among Young Adults and the Potential for Nonresponse Error in RDD Surveys Doug Currivan, Joel Hampton, Niki Mayo, and Burton Levine May 16, 2010 RTI International

More information

Centers for Disease Control and Prevention National Center for Health Statistics

Centers for Disease Control and Prevention National Center for Health Statistics Wireless-Only and Wireless-Mostly Households: A growing challenge for telephone surveys Stephen Blumberg sblumberg@cdc.gov Julian Luke jluke@cdc.gov Centers for Disease Control and Prevention National

More information

Segmented or Overlapping Dual Frame Samples in Telephone Surveys

Segmented or Overlapping Dual Frame Samples in Telephone Surveys Vol. 3, Issue 6, 2010 Segmented or Overlapping Dual Frame Samples in Telephone Surveys John M Boyle *, Faith Lewis, Brian Tefft * Institution: Abt SRBI Institution: Abt SRBI Institution: AAA Foundation

More information

Telephone Survey Response: Effects of Cell Phones in Landline Households

Telephone Survey Response: Effects of Cell Phones in Landline Households Telephone Survey Response: Effects of Cell Phones in Landline Households Dennis Lambries* ¹, Michael Link², Robert Oldendick 1 ¹University of South Carolina, ²Centers for Disease Control and Prevention

More information

Cell phones and Nonsampling Error in the American Time Use Survey

Cell phones and Nonsampling Error in the American Time Use Survey Cell phones and Nonsampling Error in the American Time Use Survey Brian Meekins Stephanie Denton AAPOR 2012 American Time Use Survey (ATUS) A Bureau of Labor Statistics survey, conducted by the U.S. Census

More information

Survey Questions and Methodology

Survey Questions and Methodology Survey Questions and Methodology Spring Tracking Survey 2012 Data for March 15 April 3, 2012 Princeton Survey Research Associates International for the Pew Research Center s Internet & American Life Project

More information

Survey Questions and Methodology

Survey Questions and Methodology Survey Questions and Methodology Winter Tracking Survey 2012 Final Topline 02/22/2012 Data for January 20 February 19, 2012 Princeton Survey Research Associates International for the Pew Research Center

More information

The Growing Gap between Landline and Dual Frame Election Polls

The Growing Gap between Landline and Dual Frame Election Polls MONDAY, NOVEMBER 22, 2010 Republican Share Bigger in -Only Surveys The Growing Gap between and Dual Frame Election Polls FOR FURTHER INFORMATION CONTACT: Scott Keeter Director of Survey Research Michael

More information

The Rise of the Connected Viewer

The Rise of the Connected Viewer JULY 17, 2012 The Rise of the Connected Viewer 52% of adult cell owners use their phones while engaging with televised content; younger audiences are particularly active in these connected viewing experiences

More information

Landline and Cell Phone Usage Patterns in a Large Urban Setting: Results from the 2008 New York City Community Health Survey

Landline and Cell Phone Usage Patterns in a Large Urban Setting: Results from the 2008 New York City Community Health Survey Landline and Cell Phone Usage Patterns in a Large Urban Setting: Results from the 2008 New York City Community Health Survey Stephen Immerwahr 1, Donna Eisenhower 1, Michael Sanderson 1 Michael P. Battaglia

More information

Methods for Incorporating an Undersampled Cell Phone Frame When Weighting a Dual-Frame Telephone Survey

Methods for Incorporating an Undersampled Cell Phone Frame When Weighting a Dual-Frame Telephone Survey Methods for Incorporating an Undersampled Cell Phone Frame When Weighting a Dual-Frame Telephone Survey Elizabeth Ormson 1, Kennon R. Copeland 1, Stephen J. Blumberg 2, Kirk M. Wolter 1, and Kathleen B.

More information

Smartphone Ownership 2013 Update

Smartphone Ownership 2013 Update www.pewresearch.org JUNE 5, 2013 Smartphone Ownership 2013 Update 56% of American adults now own a smartphone of some kind; Android and iphone owners account for half of the cell phone user population.

More information

Sample: n=2,252 national adults, age 18 and older, including 1,127 cell phone interviews Interviewing dates:

Sample: n=2,252 national adults, age 18 and older, including 1,127 cell phone interviews Interviewing dates: Survey Questions Spring 2013 Tracking Survey Final Topline 5/21/2013 Data for April 17-May 19, 2013 Princeton Survey Research Associates International for the Pew Research Center s Internet & American

More information

2017 NEW JERSEY STATEWIDE SURVEY ON OUR HEALTH AND WELL BEING Methodology Report December 1, 2017

2017 NEW JERSEY STATEWIDE SURVEY ON OUR HEALTH AND WELL BEING Methodology Report December 1, 2017 207 NEW JERSEY STATEWIDE SURVEY ON OUR HEALTH AND WELL BEING Methodology Report December, 207 Prepared for: Center for State Health Policy Rutgers University 2 Paterson Street, 5th Floor New Brunswick,

More information

Sample: n=2,252 national adults, age 18 and older, including 1,127 cell phone interviews Interviewing dates:

Sample: n=2,252 national adults, age 18 and older, including 1,127 cell phone interviews Interviewing dates: Survey Questions Spring 2013 Tracking Survey Final Topline 5/21/2013 Data for April 17-May 19, 2013 Princeton Survey Research Associates International for the Pew Research Center s Internet & American

More information

Spring Change Assessment Survey 2010 Final Topline 6/4/10 Data for April 29 May 30, 2010

Spring Change Assessment Survey 2010 Final Topline 6/4/10 Data for April 29 May 30, 2010 Spring Change Assessment Survey 2010 Final Topline 6/4/10 Data for April 29 May 30, 2010 for the Pew Research Center s Internet & American Life Project Sample: n= 2,252 national adults, age 18 and older,

More information

Dual-Frame Sample Sizes (RDD and Cell) for Future Minnesota Health Access Surveys

Dual-Frame Sample Sizes (RDD and Cell) for Future Minnesota Health Access Surveys Dual-Frame Sample Sizes (RDD and Cell) for Future Minnesota Health Access Surveys Steven Pedlow 1, Kanru Xia 1, Michael Davern 1 1 NORC/University of Chicago, 55 E. Monroe Suite 2000, Chicago, IL 60603

More information

Practical Issues in Conducting Cell Phone Polling

Practical Issues in Conducting Cell Phone Polling Practical Issues in Conducting Phone Polling for DC-AAPOR April 16, 2009 Michael Dimock, Leah Christian & Scott Keeter Pew Research Center Frame Surveys at Pew 14 full dual frame surveys in 2008 ~22,000

More information

Geographic Accuracy of Cell Phone RDD Sample Selected by Area Code versus Wire Center

Geographic Accuracy of Cell Phone RDD Sample Selected by Area Code versus Wire Center Geographic Accuracy of Cell Phone RDD Sample Selected by versus Xian Tao 1, Benjamin Skalland 1, David Yankey 2, Jenny Jeyarajah 2, Phil Smith 2, Meena Khare 3 1 NORC at the University of Chicago 2 National

More information

Growing Cell-Phone Population and Noncoverage Bias in Traditional Random Digit Dial Telephone Health Surveys

Growing Cell-Phone Population and Noncoverage Bias in Traditional Random Digit Dial Telephone Health Surveys Health Services Research r Health Research and Educational Trust DOI: 10.1111/j.1475-6773.2010.01120.x METHODS ARTICLE Growing Cell-Phone Population and Noncoverage Bias in Traditional Random Digit Dial

More information

Mobile Access July 7, 2010 Aaron Smith, Research Specialist.

Mobile Access July 7, 2010 Aaron Smith, Research Specialist. Mobile Access 2010 Six in ten Americans go online wirelessly using a laptop or cell phone; African-Americans and 18-29 year olds lead the way in the use of cell phone data applications, but older adults

More information

GALLUP NEWS SERVICE GALLUP POLL SOCIAL SERIES: VALUES AND BELIEFS

GALLUP NEWS SERVICE GALLUP POLL SOCIAL SERIES: VALUES AND BELIEFS GALLUP NEWS SERVICE GALLUP POLL SOCIAL SERIES: VALUES AND BELIEFS -- FINAL TOPLINE -- Timberline: 937008 IS: 727 Princeton Job #: 16-05-006 Jeff Jones, Lydia Saad May 4-8, 2016 Results are based on telephone

More information

Summary of the impact of the inclusion of mobile phone numbers into the NSW Population Health Survey in 2012

Summary of the impact of the inclusion of mobile phone numbers into the NSW Population Health Survey in 2012 University of Wollongong Research Online Faculty of Engineering and Information Sciences - Papers: Part A Faculty of Engineering and Information Sciences 2015 Summary of the impact of the inclusion of

More information

The Demographics of Mobile News Habits

The Demographics of Mobile News Habits December 11, 2012 The Demographics of Mobile News Habits Men, College Grads and the Young are more Engaged FOR FURTHER INFORMATION: Amy Mitchell, Acting Director, Pew Research Center s Project for Excellence

More information

Are Advanced Postcards or Letters Better? An Experiment with Advance Mailing Types

Are Advanced Postcards or Letters Better? An Experiment with Advance Mailing Types Vol. 4, Issue 4, 2011 Are Advanced Postcards or Letters Better? An Experiment with Advance Mailing Types Amanda Richardson Survey Practice 10.29115/SP-2011-0020 Aug 01, 2011 Tags: survey practice Abstract

More information

Better connections: Australian attitudes to mail and . November 2013

Better connections: Australian attitudes to mail and  . November 2013 Better connections: Australian attitudes to mail and email November 0 Contents p Methodology Audience segments Apart from analysing results according to age, gender, location and employment status, the

More information

DATA MEMO. The volume of spam is growing in Americans personal and workplace accounts, but users are less bothered by it.

DATA MEMO. The volume of spam is growing in Americans personal and workplace  accounts, but  users are less bothered by it. DATA MEMO BY: Senior Research Fellow Deborah Fallows DATE: May 2007 The volume of spam is growing in Americans personal and workplace email accounts, but email users are less bothered by it. Spam continues

More information

Dual-Frame Weights (Landline and Cell) for the 2009 Minnesota Health Access Survey

Dual-Frame Weights (Landline and Cell) for the 2009 Minnesota Health Access Survey Dual-Frame Weights (Landline and Cell) for the 2009 Minnesota Health Access Survey Kanru Xia 1, Steven Pedlow 1, Michael Davern 1 1 NORC/University of Chicago, 55 E. Monroe Suite 2000, Chicago, IL 60603

More information

Cell phones and American adults

Cell phones and American adults Cell phones and American adults They make just as many calls, but text less often than teens Amanda Lenhart, Senior Research Specialist 9/2/2010 http://pewinternet.org/reports/2010/cell-phones-and-american-adults.aspx

More information

N.J. drivers continue to roll the dice with safety

N.J. drivers continue to roll the dice with safety For immediate release Mon., Aug. 6, 2012 7 pp. Contacts: Dan Cassino 973.896.7072 Zach Hosseini (NJ DHTS) 609.984.2529 Rich Higginson 908.213.1971 N.J. drivers continue to roll the dice with safety Despite

More information

Mobile-only web survey respondents

Mobile-only web survey respondents Vol. 9, Issue 4, 2016 Mobile-only web survey respondents Peter Lugtig *, Vera Toepoel, Alerk Amin * Institution: Utrecht University Institution: Utrecht University Institution: RAND Corporation Abstract

More information

Cost and Productivity Ratios in Dual-Frame RDD Telephone Surveys

Cost and Productivity Ratios in Dual-Frame RDD Telephone Surveys Vol. 5, Issue 4, 2012 Cost and Productivity Ratios in Dual-Frame RDD Telephone Surveys Matthew Courser *, Paul J. Lavrakas * Institution: Pacific Institute for Research and Evaluation Louisville Center

More information

Solving the Problems Cell Phones Create for Survey Research

Solving the Problems Cell Phones Create for Survey Research Solving the Problems Cell Phones Create for Survey Research Michael Link, Ph.D. Chief Methodologist Technologies & Survey Research Random digit dialing (RDD) has served us well so why change? Validity

More information

HOW DO WE REACH THEM? COMPARING RANDOM SAMPLES FROM MOBILE AND LANDLINE PHONES. Paul Steffens* Marcello Tonelli* Per Davidsson* Paper presented at the

HOW DO WE REACH THEM? COMPARING RANDOM SAMPLES FROM MOBILE AND LANDLINE PHONES. Paul Steffens* Marcello Tonelli* Per Davidsson* Paper presented at the HOW DO WE REACH THEM? COMPARING RANDOM SAMPLES FROM MOBILE AND LANDLINE PHONES Paul Steffens* Marcello Tonelli* Per Davidsson* Paper presented at the AGSE Entrepreneurship Research Exchange 1 4 February,

More information

HOW DO WE REACH THEM? COMPARING RANDOM SAMPLES FROM MOBILE AND LANDLINE PHONES. Paul Steffens* Per Davidsson* Marcello Tonelli* Michael Stuetzer*

HOW DO WE REACH THEM? COMPARING RANDOM SAMPLES FROM MOBILE AND LANDLINE PHONES. Paul Steffens* Per Davidsson* Marcello Tonelli* Michael Stuetzer* HOW DO WE REACH THEM? COMPARING RANDOM SAMPLES FROM MOBILE AND LANDLINE PHONES Paul Steffens* Per Davidsson* Marcello Tonelli* Michael Stuetzer* * Australian Centre for Entrepreneurship Research, QUT Business

More information

Web+Mail as a Mixed-Mode Solution to General Public Survey Challenges in the United States

Web+Mail as a Mixed-Mode Solution to General Public Survey Challenges in the United States Web+Mail as a Mixed-Mode Solution to General Public Survey Challenges in the United States Don A. Dillman and Benjamin Messer* Social & Economic Sciences Research Center Washington State University Pullman,

More information

BY Aaron Smith and Kenneth Olmstead

BY Aaron Smith and Kenneth Olmstead FOR RELEASE APRIL 30, 2018 BY Aaron Smith and Kenneth Olmstead FOR MEDIA OR OTHER INQUIRIES: Aaron Smith, Associate Director, Research Tom Caiazza, Communications Manager 202.419.4372 RECOMMENDED CITATION

More information

Are dual-frame surveys necessary in market research?

Are dual-frame surveys necessary in market research? GfK Verein Are dual-frame surveys necessary in market research? Research report on GfK's methodology test Copyright GfK Verein All rights reserved. No part of this publication may be reproduced, or transmitted

More information

Adobe Security Survey

Adobe Security Survey Adobe Security Survey October 2016 Edelman + Adobe INTRODUCTION Methodology Coinciding with National Cyber Security Awareness Month (NCSAM), Edelman Intelligence, on behalf of Adobe, conducted a nationally

More information

Landline and Cell Phone Response Measures in Behavioral Risk Factor Surveillance System

Landline and Cell Phone Response Measures in Behavioral Risk Factor Surveillance System Vol. 6, Issue 3, 2013 and Cell Phone Response Measures in Behavioral Risk Factor Surveillance System Mohamed Qayad 1, Carol Pierannunzi 2, Pranesh P. Chowdhury 3, Sean Hu 4, Gwynett M. Town 5, Lina Balluz

More information

emarketer US Social Network Usage StatPack

emarketer US Social Network Usage StatPack May 2016 emarketer US Social Network Usage StatPack Presented by Learning from Social Advertising Data Trends Video Views ONCE A USER WATCHES 25% OF A VIDEO, DO THEY Stop Watching Watch 50% Watch 75% Finish

More information

1 PEW RESEARCH CENTER

1 PEW RESEARCH CENTER 1 Survey questions August Tracking 2013 / Facebook Survey Final Topline 9/18/2013 Data for August 7-September 16, 2013 Princeton Survey Research Associates International for the Pew Research Center s Internet

More information

SPRING 2015 PENN STATE POLL

SPRING 2015 PENN STATE POLL SPRING 2015 PENN STATE POLL Report of Methods BLUE POLL Prepared by: Center for Survey Research May 2015 TABLE OF CONTENTS INTRODUCTION...1 METHODOLOGY...2 Instrument Development...2 Sample Design...2

More information

Fall 2012 PENN STATE POLL

Fall 2012 PENN STATE POLL Fall 2012 PENN STATE POLL Report of Methods Prepared by: Center for Survey Research November 2012 TABLE OF CONTENTS INTRODUCTION...1 METHODOLOGY...2 Instrument Development...2 Sample Design...2 RDD Landline

More information

Survey Methods: Insights from the Field

Survey Methods: Insights from the Field 1 of 15 Britta Busse, University of Bremen, Institute Labour and Economy Marek Fuchs, Darmstadt University of Technology 31.01.2013 How to cite this article: Busse, B., & Fuchs, M. (2013). Prevalence of

More information

APPENDIX G: Biennial Exhibition Device Survey Questions

APPENDIX G: Biennial Exhibition Device Survey Questions APPENDIX G: Biennial Exhibition Device Survey Questions STANDARD DEVICE QUESTIONS Did you use Whitney s Audio Guide to access the Museum s audio guide tour during today s visit? If so, please take a few

More information

2018 Canadian consumer tech market. Executive summary

2018 Canadian consumer tech market. Executive summary 2018 Canadian consumer tech market Executive summary Overall technology ownership trends The most popular consumer technology products in Canada continue to be televisions, smartphones, and laptops. Among

More information

Characteristics of Students in the Cisco Networking Academy: Attributes, Abilities, and Aspirations

Characteristics of Students in the Cisco Networking Academy: Attributes, Abilities, and Aspirations Cisco Networking Academy Evaluation Project White Paper WP 05-02 October 2005 Characteristics of Students in the Cisco Networking Academy: Attributes, Abilities, and Aspirations Alan Dennis Semiral Oncu

More information

The Mobile-only Population in Portugal and Its Impact in a Dual Frame Telephone Survey

The Mobile-only Population in Portugal and Its Impact in a Dual Frame Telephone Survey Survey Research Methods (2009) Vol.3, No.2, pp. 105-111 ISSN 1864-3361 http://www.surveymethods.org c European Survey Research Association The Mobile-only Population in Portugal and Its Impact in a Dual

More information

NANOS SURVEY NANOS SURVEY

NANOS SURVEY NANOS SURVEY Canadians are three times more likely to say Canada should ban than allow Huawei from participating in the 5G network in Canada National survey released August, 2018 Project 2018-1260A Summary Fifty-four

More information

TRAFFIC SAFETY FACTS. Young Drivers Report the Highest Level of Phone Involvement in Crash or Near-Crash Incidences. Research Note

TRAFFIC SAFETY FACTS. Young Drivers Report the Highest Level of Phone Involvement in Crash or Near-Crash Incidences. Research Note TRAFFIC SAFETY FACTS Research Note DOT HS 811 611 April 2012 Young Drivers Report the Highest Level of Phone Involvement in Crash or Near-Crash Incidences In the first nationally representative telephone

More information

A Brief History of Cell vs Landline Performance Wisconsin BRFSS

A Brief History of Cell vs Landline Performance Wisconsin BRFSS A Brief History of Cell vs Landline Performance Wisconsin BRFSS 2015 IFD&TC John Stevenson, August Salick, Robert Cradock, Jennifer Dykema May 2015 2014. Materials may not be reproduced without permission

More information

Evaluating the Effectiveness of Using an Additional Mailing Piece in the American Community Survey 1

Evaluating the Effectiveness of Using an Additional Mailing Piece in the American Community Survey 1 Evaluating the Effectiveness of Using an Additional Mailing Piece in the American Community Survey 1 Jennifer Guarino Tancreto and John Chesnut U.S. Census Bureau, Washington, DC 20233 Abstract Decreases

More information

SPRING 2014 PENN STATE POLL

SPRING 2014 PENN STATE POLL SPRING 2014 PENN STATE POLL Report of Methods Prepared by: Center for Survey Research May 2014 TABLE OF CONTENTS INTRODUCTION...1 METHODOLOGY...2 Instrument Development...2 Sample Design...2 RDD Landline

More information

Thaddeus (Thad) Pennas, FHI360

Thaddeus (Thad) Pennas, FHI360 Integrated SBCC Programs: Key Challenges and Promising Strategies New horizons in data collection for integrated SBC Programs. Experience from Ghana and Malawi. Thaddeus (Thad) Pennas, FHI360 Overview

More information

Research Report: Voice over Internet Protocol (VoIP)

Research Report: Voice over Internet Protocol (VoIP) Research Report: Voice over Internet Protocol (VoIP) Statement Publication date: 26 July 2007 Contents Section Page 1 Executive Summary 1 2 Background and research objectives 3 3 Awareness of VoIP 5 4

More information

Test designs for evaluating the effectiveness of mail packs Received: 30th November, 2001

Test designs for evaluating the effectiveness of mail packs Received: 30th November, 2001 Test designs for evaluating the effectiveness of mail packs Received: 30th November, 2001 Leonard Paas previously worked as a senior consultant at the Database Marketing Centre of Postbank. He worked on

More information

New Jersey economic issues poll April 5-14, 2018 Stockton Polling Institute Weighted frequencies

New Jersey economic issues poll April 5-14, 2018 Stockton Polling Institute Weighted frequencies New Jersey economic issues poll April 5-14, 2018 Stockton Polling Institute Weighted frequencies Q1. How would you rate the U.S. economy: Frequency Valid Valid Excellent 47 6.6 6.6 6.6 Good 302 42.1 42.1

More information

Bring Your Own Device and the 2020 Census Research & Testing

Bring Your Own Device and the 2020 Census Research & Testing Bring Your Own Device and the 2020 Census Research & Testing Ryan King, Evan Moffett, Jennifer Hunter Childs, Jay Occhiogrosso, Scott Williams U.S. Census Bureau 4600 Silver Hill Rd, Suitland, MD 20746

More information

Billing Zip Codes in Cellular Telephone Sampling

Billing Zip Codes in Cellular Telephone Sampling Vol. 7, Issue 4, 2014 Billing Zip Codes in Cellular Telephone Sampling David Dutwin 1 Survey Practice 10.29115/SP-2014-0019 Aug 01, 2014 Tags: telephone, sampling, cellphone 1 Institution: Social Science

More information

Almost half of all internet users now use search engines on a typical day

Almost half of all internet users now use search engines on a typical day Data Memo BY: Senior Research Fellow Deborah Fallows CONTACT: Associate Director Susannah Fox (202-419-4500) RE: Search Engine Use August 6, 2008 Almost half of all internet users now use search engines

More information

Victim Personal Statements 2017/18

Victim Personal Statements 2017/18 Victim Personal Statements / Analysis of the offer and take-up of Victim Personal Statements using the Crime Survey for England and Wales, April to March. October Foreword A Victim Personal Statement (VPS)

More information

Annual Gadgets Survey Final Topline 4/21/06

Annual Gadgets Survey Final Topline 4/21/06 Annual Gadgets Survey Final Topline 4/21/06 Data for February 15 April 6, 2006 1 Princeton Survey Research Associates International for the Pew Internet & American Life Project Sample: n = 4,001 adults

More information

Entertainment Services: The future is mobile White Paper December 2016

Entertainment Services: The future is mobile White Paper December 2016 Entertainment Services: The future is mobile White Paper December 2016 Entertainment Services: The future is mobile White Paper Published December 2016 Version 1.0 Report Number: 042016-07 igr 12400 W.

More information

WELCOME! Lecture 3 Thommy Perlinger

WELCOME! Lecture 3 Thommy Perlinger Quantitative Methods II WELCOME! Lecture 3 Thommy Perlinger Program Lecture 3 Cleaning and transforming data Graphical examination of the data Missing Values Graphical examination of the data It is important

More information

DATA MEMO. BY: PIP Senior Research Fellow Deborah Fallows ( )

DATA MEMO. BY: PIP Senior Research Fellow Deborah Fallows ( ) DATA MEMO BY: PIP Senior Research Fellow Deborah Fallows (202-419-4500) RE: CAN-SPAM a year later DATE: April, 2005 Email users get more spam, but the harmful impact of unsolicited messages is diminishing

More information

Telephone Appends. White Paper. September Prepared by

Telephone Appends. White Paper. September Prepared by September 2016 Telephone Appends White Paper Prepared by Rachel Harter Joe McMichael Derick Brown Ashley Amaya RTI International 3040 E. Cornwallis Road Research Triangle Park, NC 27709 Trent Buskirk David

More information

Topline Questionnaire

Topline Questionnaire 24 Topline Questionnaire HOME4NW Do you currently subscribe to internet service at HOME? 3 Based on all internet users [N=1,740] YES NO DON T KNOW REFUSED Current 84 16 * 0 April 2015 89 11 * 0 September

More information

CHART BOOK: HAND-HELD MOBILE DEVICE USE TRENDS FOR MISSISSIPPI ADULTS

CHART BOOK: HAND-HELD MOBILE DEVICE USE TRENDS FOR MISSISSIPPI ADULTS CHART BOOK: HAND-HELD MOBILE DEVICE USE TRENDS FOR MISSISSIPPI ADULTS March 2018 Overview issue brief HAND-HELD MOBILE DEVICE USE WHILE DRIVING Policy Considerations in Mississippi Published december 2017

More information

First-Class Versus Pre-Canceled Postage: A Cost/ Benefit Analysis

First-Class Versus Pre-Canceled Postage: A Cost/ Benefit Analysis University of Nebraska - Lincoln DigitalCommons@University of Nebraska - Lincoln Publications from the Center for Applied Rural Innovation (CARI) CARI: Center for Applied Rural Innovation November 1998

More information

Students Preferences for Receiving Communication from the University: A Report from the Student Life Survey

Students Preferences for Receiving Communication from the University: A Report from the Student Life Survey Preferences for Receiving Communication from the University: A Report from the Student Life Survey Center for the Study of Student Life March 2017 INTRODUCTION This report explores questions on the Student

More information

THE AP/AOL POLL CONDUCTED BY IPSOS PUBLIC AFFAIRS PROJECT # ONLINE VIDEO STUDY

THE AP/AOL POLL CONDUCTED BY IPSOS PUBLIC AFFAIRS PROJECT # ONLINE VIDEO STUDY 1101 Connecticut Avenue NW, Suite 200 Washington, DC 20036 (202) 463-7300 Interview dates: July 27-30, August 1-3, & August 7-9, 2006 Interviews: 3003 adults, 1347 online video watchers Margin of error:

More information

Sample: n=2,252 national adults, age 18 and older, including 1,127 cell phone interviews Interviewing dates:

Sample: n=2,252 national adults, age 18 and older, including 1,127 cell phone interviews Interviewing dates: Survey Questions Spring 2013 Tracking Survey Final Topline 5/21/2013 Data for April 17-May 19, 2013 Princeton Survey Research Associates International for the Pew Research Center s Internet & American

More information

The Smartphone Consumer June 2012

The Smartphone Consumer June 2012 The Smartphone Consumer 2012 June 2012 Methodology In January/February 2012, Edison Research and Arbitron conducted a national telephone survey offered in both English and Spanish language (landline and

More information

Should the Word Survey Be Avoided in Invitation Messaging?

Should the Word Survey Be Avoided in  Invitation Messaging? ACT Research & Policy Issue Brief 2016 Should the Word Survey Be Avoided in Email Invitation Messaging? Raeal Moore, PhD Introduction The wording of email invitations requesting respondents participation

More information

To start, please type the ID number from your invitation letter here, then click Log in.

To start, please type the ID number from your invitation letter here, then click Log in. ANES 2016 Time Series Web Screening Questionnaire [PROGRAMMING: Define preload variable PRESELECTED. Set PRESELECTED=0 for all cases (meaning there is no pre-selected person, meaning that the household

More information

Mobile Internet & Smartphone Adoption

Mobile Internet & Smartphone Adoption Mobile Internet & Smartphone Adoption New Insights into Consumer Usage of Mobile Devices, the Shift to Smartphones & the Emergence of Tablets United States (US), United Kingdom (UK), Germany (DE), France

More information

Using Mixed-Mode Contacts in Client Surveys: Getting More Bang for Your Buck

Using Mixed-Mode Contacts in Client Surveys: Getting More Bang for Your Buck June 2013 Volume 51 Number 3 Article # 3FEA1 Using Mixed-Mode Contacts in Client Surveys: Getting More Bang for Your Buck Abstract Surveys are commonly used in Extension to identify client needs or evaluate

More information

Homeless Management Information System (HMIS)

Homeless Management Information System (HMIS) Mid-America Regional Council 600 Broadway, Suite 200 Kansas City, Missouri 64105 (816)474-4240 Kcmetrohmis.org Homeless Management Information System (HMIS) Data Quality Plan Kansas City Metro-Jackson,

More information

T he Inbox Report 2017

T he Inbox Report 2017 Search Inbox Sent 1 Fluent LLC to me 2:10 Drafts Spam Trash T he Inbox Report 2017 CONSUMER PERCEPTIONS OF EMAIL loading... REVEAL MORE Click here to Reply Inbox Report 2017 Page 1

More information

The Changing Costs of Random Digital Dial Cell Phone and Landline Interviewing

The Changing Costs of Random Digital Dial Cell Phone and Landline Interviewing Vol. 11, Issue 2, 2018 The Changing Costs of Random Digital Dial Cell Phone and Landline Interviewing Thomas Guterbock 1, Grant Benson 2, Paul Lavrakas 3 Survey Practice 10.29115/SP-2018-0015 Mar 05, 2018

More information

Mobility Enabled: Effects of Mobile Devices on Survey Response and Substantive Measures

Mobility Enabled: Effects of Mobile Devices on Survey Response and Substantive Measures Mobility Enabled: Effects of Mobile Devices on Survey Response and Substantive Measures Frances M. Barlas, Randall K. Thomas, and Patricia Graham GfK Custom Research Presented at CASRO Digital Research

More information

CICS insights from IT professionals revealed

CICS insights from IT professionals revealed CICS insights from IT professionals revealed A CICS survey analysis report from: IBM, CICS, and z/os are registered trademarks of International Business Machines Corporation in the United States, other

More information

The Effectiveness of Mobile Wireless Service as a Competitive Constraint on Landline Pricing: Was the DOJ Wrong?

The Effectiveness of Mobile Wireless Service as a Competitive Constraint on Landline Pricing: Was the DOJ Wrong? 11 December 2008 The Effectiveness of Mobile Wireless Service as a Competitive Constraint on Landline Pricing: Was the DOJ Wrong? William E. Taylor and Harold Ware 1 The US Department of Justice (DOJ)

More information

A Study of Distracted Driving in New Jersey 2016

A Study of Distracted Driving in New Jersey 2016 A Study of Distracted Driving in New Jersey 2016 Eating while driving; making handheld cellphone calls while driving; personal grooming while driving. The term distracted driving covers a broad range of

More information

Kristine Wiant 1, Joe McMichael 1, Joe Murphy 1 Katie Morton 1, Megan Waggy 1 1

Kristine Wiant 1, Joe McMichael 1, Joe Murphy 1 Katie Morton 1, Megan Waggy 1 1 Consistency and Accuracy of USPS-Provided Undeliverable Codes: Implications for Frame Construction, Data Collection Operational Decisions, and Response Rate Calculations Kristine Wiant 1, Joe McMichael

More information

Distracted Driving Attitudes and Behaviors Survey Final Results Report Bend, Oregon 2015

Distracted Driving Attitudes and Behaviors Survey Final Results Report Bend, Oregon 2015 Distracted Driving Attitudes and Behaviors Survey Final Results Report Bend, Oregon 2015 Survey Research Lab This report was prepared for: Oregon Department of Transportation, Transportation Safety Division

More information

2013 Local Arts Agency Salary & Benefits Summary EXECUTIVE DIRECTOR / PRESIDENT / CEO

2013 Local Arts Agency Salary & Benefits Summary EXECUTIVE DIRECTOR / PRESIDENT / CEO Local Arts Agency Salary & Benefits Summary EXECUTIVE DIRECTOR / PRESIDENT / CEO PRIVATE LAAS ONLY PUBLIC LAAS ONLY The Executive Director / President / Chief Executive Officer (CEO) is the chief staff

More information

Internet, Science & Tech RESEARCH AREAS. Mobile Fact Sheet MORE FACT SHEETS: INTERNET/BROADBAND SOCIAL MEDIA

Internet, Science & Tech RESEARCH AREAS. Mobile Fact Sheet MORE FACT SHEETS: INTERNET/BROADBAND SOCIAL MEDIA NUMBERS, FACTS AND TRENDS SHAPING YOUR WORLD ABOUT FOLLOW US Search Internet, Science & Tech MENU RESEARCH AREAS FACT SHEET JANUARY 12, 217 Mobile Fact Sheet MORE FACT SHEETS: INTERNET/BROADBAND SOCIAL

More information

The State of the American Traveler TM

The State of the American Traveler TM The State of the American Traveler TM MOBILE EDITION Fall 2018 Volume 30 The Mobile Edition THIS FALL EDITION of The State of the American Traveler TM continues our ongoing exploration of travelers use

More information

MAKING MONEY FROM YOUR UN-USED CALLS. Connecting People Already on the Phone with Political Polls and Research Surveys. Scott Richards CEO

MAKING MONEY FROM YOUR UN-USED CALLS. Connecting People Already on the Phone with Political Polls and Research Surveys. Scott Richards CEO MAKING MONEY FROM YOUR UN-USED CALLS Connecting People Already on the Phone with Political Polls and Research Surveys Scott Richards CEO Call Routing 800 Numbers Call Tracking Challenge Phone Carriers

More information

Wireless Opportunities

Wireless Opportunities Wireless Opportunities Chris Bingley, RuffaloCODY Cell phone future Trends Smart phones Opinions Uses Mobile communication research Problem or Opportunity Old cell phone plans Privacy Phone number data

More information

Customer Insights Customer Insights

Customer Insights Customer Insights ustomer Insights ustomer Insights riving While istracted ell Phone Ban August, 009 ustomer Insights Market Research Methodology This survey was conducted by Harris Interactive via its National Quorum SM

More information

PHPM 672/677 Lab #2: Variables & Conditionals Due date: Submit by 11:59pm Monday 2/5 with Assignment 2

PHPM 672/677 Lab #2: Variables & Conditionals Due date: Submit by 11:59pm Monday 2/5 with Assignment 2 PHPM 672/677 Lab #2: Variables & Conditionals Due date: Submit by 11:59pm Monday 2/5 with Assignment 2 Overview Most assignments will have a companion lab to help you learn the task and should cover similar

More information

Fighting Hunger Worldwide. mvam for Nutrition. Kenya Case Study

Fighting Hunger Worldwide. mvam for Nutrition. Kenya Case Study Fighting Hunger Worldwide mvam for Nutrition Kenya Case Study Using Computer-Assisted Telephone Interviewing (CATI) to collect data on nutrition indicators Collecting nutrition data at an individual level

More information

Mobile calls to 13 numbers Research report JULY 2014

Mobile calls to 13 numbers Research report JULY 2014 Mobile calls to 13 numbers Research report JULY 2014 Canberra Red Building Benjamin Offices Chan Street Belconnen ACT PO Box 78 Belconnen ACT 2616 T +61 2 6219 5555 F +61 2 6219 5353 Melbourne Level 32

More information

November 2016 G. Oscar Anderson, Senior Research Advisor AARP Research

November 2016 G. Oscar Anderson, Senior Research Advisor AARP Research November 2016 G. Oscar Anderson, Senior Research Advisor AARP Research https://doi.org/10.26419/res.00140.001 AARP is a nonprofit, nonpartisan organization, with a membership of nearly 38 million that

More information

Outside of Working Hours Not a Burden to US Workers

Outside of Working Hours Not a Burden to US Workers Email Outside of Working Hours Not a Burden to US Workers May 10, 2017 by Frank Newport Story Highlights 91% who email outside of working hours say amount is reasonable Most say after-hours emailing doesn't

More information

The State of the American Traveler TM

The State of the American Traveler TM The State of the American Traveler TM MOBILE EDITION Fall 2016 Volume 22 The Mobile Edition THIS FALL EDITION of The State of the American Traveler TM explores travelers use of mobile devices in planning

More information

AAPOR 2013 Methodological Briefs: Cell Phones. Howard Speizer, Marcus Berzofsky, Tom Duffy, Jamie Ridenhour (RTI) Tim Sahr (Ohio State University)

AAPOR 2013 Methodological Briefs: Cell Phones. Howard Speizer, Marcus Berzofsky, Tom Duffy, Jamie Ridenhour (RTI) Tim Sahr (Ohio State University) Alternative Sample Selection and Data Collection Strategies for Balancing Cell Phone Response Distribution Across County/Region Level Geographies in a Dual Frame Telephone Survey AAPOR 2013 Methodological

More information