scottish social survey network: master class 1 data analysis with stata dr vernon gayle and dr paul...

15
Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling The SSSN is funded under Phase II of the ESRC Research Development Initiative

Upload: alice-morrison

Post on 29-Dec-2015

219 views

Category:

Documents


3 download

TRANSCRIPT

Page 1: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Scottish Social Survey Network: Master Class 1

Data Analysis with Stata

Dr Vernon Gayle and Dr Paul Lambert23rd January 2008, University of Stirling

The SSSN is funded under Phase II of the ESRC Research Development Initiative

Page 2: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Introducing Stata

Windows environmentOpening and processing commands – the

do-file editorOpening and saving dataViewing data Preserving outputs (logs)Tips (and wrinkles)Further examples on our website

Page 3: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

STATA SOFTWARE – GOOD POINTS

• Does all the simple stuff (SPSS)

• Fits many more models than standard software (esp. Longitudinal)

• Specialist survey analysis functions (Svy)

• You can get started easily (menus and help)

• Strong documentation

• There is a growing user community (lists etc)

• New features emerge almost daily

• There are good labour market opportunities (UK little known; USA well known)

Page 4: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Main data window

Command window – interactive use

Variable names

Review – what you’ve done

Page 5: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Open the do file editor (or ‘ctrl-8’) A Do File (.do)

Page 6: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Highlight the command and run it from the icon

(or ctrl D)

Page 7: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Opening and Saving Data

• use “C:\data\dataset2.dta”

• save “C:\data\dataset2.dta”

To overwrite…

• use “C:\data\dataset2.dta”, clear

• save “C:\data\dataset2.dta”, replace

Page 8: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

variables names & descriptions

Page 9: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Data Windows

Data browser (can’t edit here)

Data editor (dangerous - can edit here)

Page 10: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Data Editor (familiar spreadsheet)

Page 11: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Log files (keeping track)

log using “C:\data\temp1.log”, replace

Page 12: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Using Stata – Some tips

• Session settings– set more off (once in command window)– set mem 64M (, permanently)

• Data overwrite– use dataset1.dta, clear– save dataset1.dta, replace

• Do not double click on .do files in windows they will crash

• Generate variables– drop varname before gen varname

• See values and labels– numlabel _all, add

• File information– codebook

Page 13: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Using Stata – Some tips

• File locations– global path1 "d:\lda\work\" – use “$path1\data1.dta”, clear

• Output– capture – suppresses output (*including errors*)– nolog – e.g. suppresses interactions in logit– noheader - suppresses the display of the ANOVA table etc in regression– nodots – jacknife “not a lot of people know that”

• Line breaks– /// tells Stata to read the next line too

• Looking at the data– edit– browse– list in1/10 – shows data for cases 1 to 10

Page 14: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

STATA SOFTWARE – BAD POINTS

• Poor data visualisation (compared with SPSS etc)• In practice, survey analysis functionality comes with

limitations (complex methods but weak data) • There are some models that can’t be fitted / some

critiques of estimation procedures• Stata syntax has some quirks (set more off)• There is a growing user community, but they are

generally GEEKBOYS (like myself!)• New features emerge almost daily these are sometimes

tricky to get to grips with

Page 15: Scottish Social Survey Network: Master Class 1 Data Analysis with Stata Dr Vernon Gayle and Dr Paul Lambert 23 rd January 2008, University of Stirling

Taking Stata further

• Online resources– Stata website for FAQs, manual, training– Net use and update

• Specialist modelling suites– XT – Cross sectional panel– ST – Survival data– SV – Survey data– Xtmixed - Multilevel models (v9)– GLLAMM

• Programming: .do; .ado; macros