Doctoral Program in Epidemiology for Clinicians, April 2001 Computing notes

Transcription

1 Doctoral Program in Epidemiology for Clinicians, April 2001 Computing notes Paul Dickman, Rino Bellocco April 18, 2001 We will be using the computer teaching room located on the second floor of Norrbacka, KS. This laboratory contains personal computers running the Windows NT operating system and we have chosen to use the the statistical software program Stata. These notes give a brief introduction to Stata in general, along with specific information on running Stata under Windows. Copies of the book Getting started with Stata for Windows will be made available for you to loan for the duration of the course. 1 Background There exists a broad range of software programs for performing statistical analyses on personal computers. There is, in general, an inverse association between the ease-of-use and the functionality of these programs. Programs which are easy-to-use generally have limited capabilities and those programs which can do everything generally have a very steep learning curve. We have chosen to use Stata ( which we believe provides the best compromise between power and ease-of-use. Stata is sufficiently powerful that it has a strong user base among applied statisticians and researchers, but it is also relatively easy to get started. We envisage that this program will fulfill your present and future statistical software needs. Stata is relatively cheap and is available for Windows, Macintosh, and Unix computers. KI staff and students can purchase a full version of Stata 7 together with the Getting started manual for SEK1350:- (plus moms). Further information on the price and availability of Stata at KI can be found at based, in part, on notes written by David Clayton, Michael Hills, and Jeroen Weesie 1

2 2 A brief introduction to Stata Starting the Stata program We assume you have a computer in front of you and that you know how to open an application in Windows. To start Stata: 1. Click on Start 2. Click on Programs 3. Click on Stata It is also possible to start Stata by double-clicking on the Stata icon on your desktop, or clicking on a Stata data set. If everything has gone smoothly so far, then you should be able to see the Stata default windows. 1. Review 2. Variables 3. Results 4. Command 5. Stata Toolbar The viewer The viewer is where you can see help information, view (and print) logs of your current and previous Stata sessions, view (and print) any other Stata formatted (SCML) or plain text (ASCII) file, add new commands to Stata from the internet and install updates of Stata. This remarkable feature is new in Stata 7. More information can be found in the getting started book. StataQuest Some Stata commands (mostly basic commands) can be run via a menu system. The pull-down menu system is an optional component called StataQuest that is not installed by default. StataQuest has been installed on the computers you will be using and Stata has been configured so that the menus are available when you start Stata. We recommend this menu system while you are learning Stata, but for more serious work, you will find that typing commands directly is more efficient. Tutorials The command tutorial starts a somewhat interactive series of tutorials to learn some of the Stata facilities in specific areas. At the end of the notes we will come back to this. 2

3 Getting help Click on Help, or type help followed by a command name, for on-line help. whelp. Try also Useful STATA links Resources for learning Stata: Official Stata Technical-Support FAQs, Stata Corporation, USA Answers to the most frequently asked questions in statistics, data management, graphics, and operating system issues. The Stata listserver FAQ, Stata Corporation, USA Information on subscribing, unsubscribing, and using the free Stata discussion list at Harvard University. The Stata Technical Bulletin FAQ, Stata Corporation, USA Information on the bimonthly journal The Stata Technical Bulletin. Includes information on how to obtain over the net the software associated with the published articles. Introduction to Stata, Stata Corporation, USA Introduction to Stata by Jeroen Weesie, Utrecht University. An introduction to Stata in PDF format. Inleiding tot het gebruik van Stata 6 onder Windows 95/98/NT, Netherlands An introduction book on Stata written in Dutch. Danish Short Course Materials, Denmark Homepage for Jens M. Lauritsen containing tutorials in Danish and other Stata materials. Includes a 78-page introductory text in Danish in pdf format and also course datasets and supplementary ado files. Resources to help you learn and use Stata, UCLA Academic Technology Services, USA An extensive resource of Stata information including FAQs, learning modules, quick reference guide, annotated output, textbook examples, more. Stata Tutorial, Princeton University, USA An extensive introduction to Stata covering a wide range of commands from beginning usage to data management and statistics. Programs and tutorials by Stas Kolenikov, Russian-European Center for Economic Policy, Russia Many Stata programs and tutorials, including an introductory tutorial to bootstrapping with Stata, describing the basic principles and Stata routines to implement bootstrap, and an 80-page Russian pdf introduction to Stata. Survival Analysis with Stata: Course EC968, Institute for Social and Economic Research, University of Essex, UK Course notes and exercises using Stata for a survival analysis course Population Studies Center FAQ, University of Pennsylvania, USA A FAQ focusing on the basics of using Stata. Stata Homepage on MIMAS, University of Manchester, UK A FAQ focusing on the basics of using Stata. 3

4 Using Stata in the Windows Labs, University of Massachussetts Boston, USA How to get started using Stata in a Windows environment. Training videos for Stata, Johns Hopkins School of Public Health, USA Four sets of training videos (QuickTime movies) to teach the basic workings of Stata Closing the program Click on File and choose exit, or type exit. You will have to type clear first if you have any data in memory. Note that Stata is case sensitive. To interrupt a Stata command, click on break or press ctrl break. Types of Stata files Files of data in Stata format are given the extension.dta. These are created using save filename and read in with use filename. There are four other types of input file:.raw for raw data,.dct for data plus variable names,.do for batch files containing Stata commands,.ado for Stata programs, and.log for log files. Syntax command varnames if... in... using..., options The if part restricts the command to records satisfying certain logical conditions (eg sex==1), the in part restricts the command to certain line numbers, and the using part specifies any files which may be needed. Abbreviations Stata accepts unambiguous abbreviations for commands and variable names. 3 A sample session : The IVF data To introduce you to Stata we use the IVF data which consists of 641 records on mothers who had singleton births following in-vitro fertilisation. The variables in the dataset are shown in Table 1. Variable Units or Coding Type Name Subject number categorical id Maternal age years metric matage Hypertension 1=hypertensive, 0=normal binary hyp Gestational age weeks metric gestwks Sex of infant 1=male, 2=female binary sex Birthweight grams metric bweight Table 1: Variables in the IVF dataset 4

5 4 A hands-on introduction to Stata Type in the commands which start with the Stata prompt (. ). Do not type the. prompt this is used to indicate a Stata command. Stata distinguishes between upper and lower case letters, and accepts abbreviations for both commands and variable names. Think carefully about what is happening after each command. The file ivf.dta contains the variables names and values for the 641 records. To read the data, type. use ivf. describe The file ivf.dta is stored in the course directory, which is c:\data\clinepi. We have configured Stata so that this directory is the default location where Stata looks for files. In general, you have to specify the complete file address, for example. use c:\data\clinepi\ivf Now type the following. Describe Stata will return an error message (unrecognised command: Describe). Stata is case sensitive; describe is a valid Stata command, whereas Describe is not. A good way to start the analysis is to ask for a summary of the data by typing. summarize This will produce the mean, standard deviation, and range, for each variable in turn. In most datasets there will be some missing values. These are coded using the symbol. in place of the value which is missing. Stata can recognize other codes for missing values, but this is the one which is recommended. The summarize command is useful for seeing whether there are missing values. For a more detailed summary of the variable gestwks try. codebook gestwks or. summarize gestwks, detail Many Stata commands can be accessed using menus. For example, from the Summaries menu, select Median/Percentiles. You will notice that the result is identical to that obtained from the command typed previously (summarize gestwks, detail) and that Stata even shows the command which was used. 5

6 The list command is used to list the values in the data file. Try out the following and see their consequences:. list in 1/5. list matage in 1/10. list matage. list matage bweight in 1/20 Stata stops after each screenfull of output. Click on more (or hit the spacebar) to get another screenfull, or press enter to continue line by line. The command list on its own would list all of the data. You can cancel this command (and any other Stata command) by clicking on Break (the icon in the toolbar which looks like a red circle with a white cross through it). Stata also contains a spreadsheet-style editor which can be brought to the front by typing. edit Close this window by clicking in the close box (in the top right corner of the window). The browse command will bring up a similar window, except changes cannot be made to the data. The data window can also be opened using icons on the toolbar (the two icons look like spreadsheets, with a magnifying glass over the data browser icon) or from the Data menu. When starting to look at any new data the first step is to check that the values of the variables make sense and correspond to the codes defined in the coding schedule. For categorical variables this can be done by looking at one-way frequency tables and checking that only the specified codes occur. For metric variables we need to look at ranges. This first look at the data will also indicate whether all values are present or whether there are some missing values on some variables. Let us begin by looking at the categorical variables. The distribution of the categorical variables hyp and sex can be viewed by typing. tabulate hyp. tab sex The same results can be obtained via the Summaries / Tables / One-way (frequency) menu. Note that tab is an abbreviation for tabulate. The cross-tabulation of hyp and sex is obtained by typing. tab hyp sex Cross tabulations are useful when checking for consistency. The basic output from a cross tabulation reports frequencies only; to include row and/or column percentages add the options row, col, cell, or any combination, as in. tab hyp sex, col 6

7 The command table is used for preparing tables of summary statistics by one, two, or even more categorical variables. For example, to obtain the means and standard deviations of bweight separately by sex, type. table sex, contents(freq mean bweight sd bweight) To make a table of the median and interquartile range for birthweight, by sex, try. table sex, contents(freq med bweight iqr bweight) Note that tab is an abbreviation for tabulate, NOT for table, which must be typed in full. You can type whelp tabulate and whelp table to understand how, if, you can abbreviate the command. 5 Restricting commands Stata commands can be restricted to records 1, 2,..., 10 (for example), by adding in 1/10 to the command. The letters f and l can be used as abbreviations for first and last, so 20/l refers to the records from 20 onwards. Commands can also be restricted to operate only on records which satisfy given conditions. The conditions are added to the command using if followed by a logical expression which takes the values true or false. For example, to restrict the command list to records with birthweight less than or equal to 2000g, type. list id bweight if bweight <= 2000 The record is listed only if the logical expression bweight <= 2000 is true. A useful command when exploring data is count which counts the number of records which satisfy some logical expression. For example. count if bweight <= count if bweight <= 2000 & sex==1 Note the use of & to link two conditions both of which must be satisfied and that a double equal sign (==) is used for equality testing. A common error is to use = in a logical expression instead of ==. The following comparison operators and logical functions are available: Arithmetic Logical Comparison addition ~ not > greater than - subtraction or < less than * multiplication & and >= > or equal / division <= < or equal ^ power == equal ~= not equal 7

8 6 Generating and recoding variables New variables are generated using the command generate, and variables can be recoded using recode. For example, to create a new variable sex2 which is the same as sex but coded 1 for male and 0 for female, try. gen sex2=sex. recode sex2 2=0. tab sex2 7 Sorting The records in a dataset can be sorted according to the values of one or more variables. The births dataset is currently sorted by id but for some purposes it might be better to have it sorted by bweight. Try. list id bweight in 1/10. sort bweight. list id bweight in 1/10 The records are now in order of bweight and the id numbers and all other variables have also been sorted in this order. Stata commands which use the option by() usually require the data to be first sorted by the variable in the by() option. The sort is not done automatically because you should always be aware of how your data are sorted. 8 Editing commands The PageUp and PageDown keys (represented as arrows on the top right of the keypad) can be used to cycle through previous commands, which can then be edited. For example, if you decide that you would also like to list the values of the variable matage you could use the PageUp key to recall the previous command and then edit it in the command line to be:. list id bweight matage in 1/10 This capability is especially useful if you make a small mistake while typing a command. The command can be recalled, edited, and resubmitted. It also makes it easy to resubmit the same command with additional options. 8

9 9 Using Stata as a calculator The display command can be used to carry out simple calculations. For example, the command. display 2+2 will display the answer 4, while. display log(10) will display the answer Note that log means natural log in Stata. Standard probability functions can also be displayed, as in. display normprob(1.96) which will return the probability that a random variable with a standard normal distribution (i.e. mean 0 and variance 1) is less that Graphical displays The graph command has many options. Bar charts are used to display the distributions of categorical variables, while histograms and box plots are used to display the distributions of metric variables. To obtain a histogram of bweight, type. graph bweight To improve the visual display, add xlabel ylabel to this command, anywhere after the comma. You can vary the number of rectangles in the histogram (called bins) by adding bin(8), etc. To superimpose the histogram with a normal curve which has the same mean and standard deviation as the data, add the option normal. Try, for example,. graph bweight, xlabel ylabel bin(8) normal Note that you can save time by using the PageUp to recall the previous command, to which you then can add the additional options. We can also produce separate graphs for each level of a categorical variable by using a by() command. Note that we must first sort the data when using a by() command.. sort hyp. graph gestwks, bin(20) by(hyp) Scatter plots can be used to evaluate the association between bweight and the metric variable matage by typing. graph bweight matage, xlab ylab 9

10 To change the plotting symbol, try. graph bweight matage, xlab ylab s(.) To plot bweight against gestwks, try. graph bweight gestwks, xlabel ylabel 11 Missing values The missing value symbol in Stata is. and is treated as plus infinity in logical comparisons. Stata commands automatically exclude missing values when they are coded in this way. 12 Icons on the Stata toolbar Some file operations are easier to perform by clicking on the appropriate icon on the toolbar rather than typing commands at the command line. The most commonly used icons are the first four from the left: Open a Stata data file Save a Stata data file Print (graph or log file (if a log file is open)). Log file operations (Open, Close, Suspend, Resume). 13 Saving data files The Stata data currently in memory can be saved in a file by clicking on the Save icon (the floppy disk) on the toolbar. You will need to type in a name for your file which, by default, will be saved in the default directory with the extension.dta. 14 Logging and printing results Graphs can be printed directly by selecting Print graph from the File menu, or you can copy it and past it into any of your word processor (for instance MS Word). Other output must first be written to a log file before it can be printed. A log file can be opened by clicking on the log icon on the toolbar (the fourth icon from the left. You will need to type in a name for your file which, by default, will be saved in your personal directory with the extension.log. In the new version of Stata, Stata7, you choose either the SMCL or ascii format. 10

11 15 Using the StataQuest menus Many standard commands can be accessed from the menus. Experiment with some of the commands in the Graphs and Summaries menus. For example, select Graphs / Scatterplots / Plot Y vs. X and then select bweight as the Y axis variable and matage as the X axis variable and click OK. The resulting graph is the same as if you typed the command. graph bweight matage, xlab ylab bor This command is shown in the results window (bor is an abbreviation for border). 16 Some practice with basic commands 1. List the variables bweight and hyp for records inclusive. 2. Obtain the frequency distribution of matage together with its histogram. 3. Obtain the two way table of frequencies of matage and hyp, first with row, then column, then cell percentages. 4. Use count to find how many hypertensive women have babies with birthweight less than 2000g. 11

12 Some useful commands A, B are categorical variables. X, Y are metric variables. Data Management use Read in a data set already in Stata format infile using Read in data in a txt file with names describe (or f3) Describe contents of data in memory list List values of variables drop A Drops the variable called A drop if... Drops all records satisfying... generate A = Creates a new variable called A replace A = Replaces contents of A recode A Recodes the variable called A save filename Save data set in Stata format sort A Sort records according to the variable A count if... Count number of observations satisfying... Statistics and Graphics summarize Y tabulate A tabulate A B table A, c(mean X) graph Y, hist graph Y X, scatter hist A regress Y X predict P Display summary statistics for Y One-way table of frequencies for A (categorical) Two-way table of frequencies for A and B Table of mean X by levels of A Displays histogram of Y Displays scatter plot of Y vs X Histogram of the categorical variable A Linear regression of Y on X Obtain prediction after regress and put in P Utilities clear Clear data from memory display 2+2 Display the result of 2+2 do filename Execute commands from filename.do exit Exit Stata exit, clear Clear and exit Stata help Obtain on-line help for both data and commands log using filename Write output to filename.log 12

13 The Stata tutorials The official Stata package provides the following tutorials Tutorial intro graphics tables regress anova logit survival factor ourdata yourdata Description An introduction to Stata How to make graphs How to make tables Estimating regression models, including 2SLS Estimating one-, two- and N-way ANOVA and ANOCOVA models Estimating maximum-likelihood logit and probit models Estimating maximum-likelihood survival models Estimating factor and principal component models Description of the data we provide How to input your own data into Stata Useful ones to try are intro, graphics, and yourdata. To run the tutorial intro type. tutorial intro 13