SPSS files for the British Social Attitudes Survey: a warning

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

SPSS files for the British Social Attitudes Survey: a warning

John F Hall
SPSS files for British Social Attitudes wave 32 (2011)_A cautionary tale for the unwary  is a detailed commentary on the SPSS file for BSAS 32 (2011) distributed by UKDS.  


Since it was first released, the file has been modified, so that missing values for all items using 5-point Agree - Disagree scales are now declared, not as (-1) but in the range (-9 thru -9). However, the original positive value 9 = "Missing" has not been re-coded and this has caused errors in the calculation of scales derived by adding up item scores.  In the distributed SPSS file, the derived variables affected are:

welfare2  Welfareism scale
leftrigh     Left-right scale
libauth     Libertarian authoritarian scale

Values for these variables were derived by adding up the response codes for their constituent items and dividing by the number of items in the scale.  They should all lie between 1 and 5, but all three have outlying values of 9.  In my commentary, the constituent items and the derived variables welfare2, leftrigh and libauth are examined and recalculated to give the correct scores.  Improved SPSS syntax is suggested and the results compared with the distributed file.

However, potential users of BSAS data should be aware that my technical comments apply not only to many other variables in the file for the 2011 survey, but also to the files for other waves of the BSAS.  If you are using any of these files for research or teaching, be sure to check the frequencies and missing values for any variables in your exercises and examples.

John F Hall

[Retired academic survey researcher]

IBM-SPSS Academic author 9900074

 

Email:        johnfhall@... 

Website:   http://surveyresearch.weebly.com/

Course:     http://surveyresearch.weebly.com/1-survey-analysis-workshop-spss.html

Research: http://surveyresearch.weebly.com/3-subjective-social-indicators-quality-of-life.html

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD