ANSWERS -- Prep for Psyc350 Laboratory Final Statistics Part Prep a Put the following data into an spss data set: Be sure to include variable and value labels and missing value specifications for all variables Save the data file onto your TA s disk as xxxprep.sav -- where "xxx" are your initials Save the output file onto your TA s as xxxprep.spo where "xxx" are your initials Here's the data information The variables (in order) are: age when the first decided what major they wanted to be (-9 for missing values), gender (1=male, 2=female, -9 = missing value), major (1=psych, 2=bio, 3=other, -9 = missing value), gengpa GPA from general studies courses(-9 for missing), majgpa GPA from major courses (-9 for missing). Chad had scores of 20 1 3 3.15 3.55 Marcy had scores of -9 2 2 2.35 2.85 Clancy had scores of 18 2 1 1.41 1.98 Pat had scores of 21 1 1 3.35 3.54 Shemp had scores of 19 1-9 1.87 2.21 Chris had scores of 22 2 1 3.02 3.84 REM: Save the data file onto the desktop as xxxprep.sav -- where "xxx" are your initials Perform the following analyses and answer the related questions in the spaces below. 1. Combine the two GPA variables (taking their average) into a new variable (call it gpaave with -9 for missing). 2. Create a new variable (call it psyc_maj) for which 1 = psych majors and 2 = everybody else (-9 = missing) 3. Start with gpaave -- make a new variable (called gpagrp) with a value of 1 if gpaave < 2.51 and 2 if gpaave > 2.51 4. We expect that more women than men will have gpaave > 2.5. Stat test X² value 0 df 1 p 1.00 H0: reject retain RH: support not 5. Our hypothesis is that people who decide their major earlier tend to have a higher major GPA Stat test r value.928 df 3 p.023 H0: reject retain RH: support not 6. We hypothesized that students have the same mean GPA in their general studies courses as in their major. Stat test WG ANOVA value 28.37 df 1, 5 p.003 H0: reject retain RH: support not 7. Psychology majors have a higher mean GPA for their major courses than everybody else. Stat test BG ANOVA value.01 df 1,3 p.926 H0: reject retain RH: support not 8. Get the mean 2.86 std 1.00 and n 3 of gpaave for Psychology majors. 9. Get the mean 2.10 std.162 and n 2 of majgpa for those under 20 years of age. 10. Get the frequencies of gpagrp = 1 2 and gpagrp = 2 4 REM: Save your data and output files onto your TA s disk before leaving!!!
Answers The initial data should look like below 1. Combine the two GPA variables (taking their average) into a new variable (call it gpaave with -9 for missing). Transform Compute Type the name of the new variable into the Target Variable window Put the formula (for a mean, not a sum) into the Numeric Expression window Remember to set -9 to be a missing value for this new variable In the Variable View spread sheet, click in the Missing Values column for gpaave, then click the gray box Click the Discreet missing values button and enter -9
2. Create a new variable (call it psyc_maj) for which 1 = psych majors and 2 = everybody else (-9 = missing) Transform Recode Into different variables Move major into the numeric variable -> output variable window Type the name of the new variable into the Name window under Output Variable Click the change button Click the Old and New Values button Remember to set missing values from major to be missing in psyc_maj, as shown in the first line in the Old -> New window Set psych (1) to stay coded as 1 Set all other values (else) to be coded as 2 Remember to check the data set to see if the recode worked as you intended Remember to set the Values and Missing for this new variable in the Variable View
3. Start with gpaave -- make a new variable (called gpagrp) with a value of 1 if gpaave < 2.51 and 2 if gpaave > 2.50 Transform Recode Into different variables Move major into the numeric variable -> output variable window Type the name of the new variable into the Name window under Output Variable Click the change button Click the Old and New Values button Remember to set missing values from gpaave to be missing in gpagrp, as shown in the first line in the Old -> New window Set values of gpaave up to 2.50 to be coded as 1 Set values of gpaave 2.51 or larger to be coded as 2 Remember to check the data set to see if the recode worked as you intended Remember to set the Values and Missing for this new variable in the Variable View
With the transformations complete the data set should look like
4. We expect that more women than men will have gpaave > 2.5. Stat test X² value 0 df 1 p 1.00 H0: reject retain RH: support not gender & gpagrp both variables are qualitative, so we ll use a X² Analyze Descriptives Cross-tabs Move one of the qualitative variables into the Rows window and the other into the Columns window which is which doesn t matter Click Statistics Be sure that Chi-Square is checked on the statistics window Output: GENDER * GPAGRP Crosstabulation Chi-Square Tests Count GENDER Total male female GPAGRP below 2.51 above 2.50 Total 1 2 3 1 2 3 2 4 6 Pearson Chi-Square Continuity Correction a Likelihood Ratio Fisher's Exact Test Linear-by-Linear Association N of Valid Cases Asymp. Sig. Value df (2-sided).000 b 1 1.000.000 1 1.000.000 1 1.000.000 1 1.000 6 Exact Sig. (2-sided) Exact Sig. (1-sided) 1.000.800 a. Computed only for a 2x2 table b. 4 cells (100.0%) have expected count less than 5. The minimum expected count is 1.00. X² =.000 df = 1 and p = 1.00, based on the p-value we d retain H0: Since the RH: is that there is a relationship, retaining the H0: means there is no support for the RH:
5. Our hypothesis is that people who decide their major earlier tend to have a higher major GPA Stat test r value.928 df 3 p.023 H0: reject retain RH: support not age & majgpa both are quantitative and because we want to know if they are related, we ll use a correlation Analyze Correlation Bivariate move both quantitative variables into the Variables window You can also get univariate statistics for these variables using the Options button Output r =.928, df = N-2 = 3, p =.023 Based on the p-value, we would reject H0: The RH: is of a negative relationship, but we found a significant positive relationship, so there is no support for the RH:. Correlations AGE MAJGPA AGE Pearson Correlation 1.928* Sig. (2-tailed)..023 N 5 5 MAJGPA Pearson Correlation.928* 1 Sig. (2-tailed).023. N 5 6 *. Correlation is significant at the 0.05 level (2-tailed).
6. We hypothesized that students have the same mean GPA in their general studies courses as in their major. Stat test WG ANOVA value 28.37 df 1, 5 p.003 H0: reject retain RH: support not gengpa & majgpa both variables are quantitative and because we want to know whether there is a mean difference between them we will use WG ANOVA Analyze General Linear Model Repeated Measures You can change the name of the factor (IV) or not There are two conditions/variables being compared, so put a 2 in the Number of Levels window Click the Add button Click the Define button Move the two quantitative variables into the Within-Subjects Variables window gengpa and majgpa for this analysis Use the Options button to request the univariate statistics F = 28.369 df = 1 & 5 Tests of Within-Subjects Effects p =.003 with this p-value we would reject H0: The RH: is that there is no difference, but we found a significant difference, so there is no support for the RH:. Measure: MEASURE_1 Source FACTOR1 Error(FACTOR1) Sphericity Assumed Greenhouse-Geisser Huynh-Feldt Lower-bound Sphericity Assumed Greenhouse-Geisser Huynh-Feldt Lower-bound Type III Sum of Squares df Mean Square F Sig..663 1.663 28.369.003.663 1.000.663 28.369.003.663 1.000.663 28.369.003.663 1.000.663 28.369.003.117 5 2.336E-02.117 5.000 2.336E-02.117 5.000 2.336E-02.117 5.000 2.336E-02
7. Psychology majors have a higher mean GPA for their major courses than everybody else. Stat test BG ANOVA value.01 df 1,3 p.926 H0: reject retain RH: support not psyc_maj & majgpa psyc_maj is qualitative and majgpa is quantitative, so we will use BG ANOVA Analysis Compare Means One-way ANOVA Put the quantitative variable in Dependent List window Put the qualitative variable in the Factor window You the Options button to obtain univariate statistics MAJGPA Descriptives psych major everybody else Total N Mean Std. Deviation 3 3.1200.99860 2 3.2000.49497 5 3.1520.74951 F =.010 df = 1 & 3 p =.926 with this p- value we would retain H0: The RH: is of a mean difference, but the results are nonsignificant, so there is no support for the RH:. MAJGPA Between Groups Within Groups Total ANOVA Sum of Squares df Mean Square F Sig..008 1.008.010.926 2.239 3.746 2.247 4
8. Get the mean 2.86 std 1.00 and n 3 of gpaave for Psychology majors. Select only Psychology majors for the analysis Data Select Cases Click the IF condition is satisfied button Click If button Move the selection variable into the window Identify the values of this variable that specify the desired subgroup for the analysis Note: this analysis could also be done selecting group = 1 using the variable major Analyze Descriptive Statistics Frequencies Move the variable in to the Variable(s) window Use the Statistics window to obtain the mean and standard deviation Mean = 2.86 Statistics Std = 1.01 n = 3 GPAAVE N Mean Std. Deviation Valid Missing 3 0 2.8567 1.00606
10. Get the frequencies of gpagrp = 1 2 and gpagrp = 2 4 Turn off the selection from the last anlaysis. Data Select Cases Click the All cases button Analyze Descriptive Statistics Frequencies Move the variable in to the Variable(s) window GPAGRP 2 have average gpa values below 2.51 4 have average gpa values below 2.50 Valid below 2.51 above 2.50 Total Cumulative Frequency Percent Valid Percent Percent 2 33.3 33.3 33.3 4 66.7 66.7 100.0 6 100.0 100.0