PSPP: Testing data consistency

A sensible check to perform on survey data is the calculation of reliability. This gives the statistician some confidence that the questionnaires have been completed thoughtfully. If you examine the labels of variables v1, v3 and v4, you will notice that they ask very similar questions. One would therefore expect the values of these variables (after recoding) to closely follow one another, and we can test that with the RELIABILITY command (see RELIABILITY). Example 5.4 shows a PSPP session where the user (after recoding negatively scaled variables) requests reliability statistics for v1, v3 and v4.

PSPP> get file='/usr/local/share/pspp/examples/hotel.sav'.
PSPP> display dictionary.
PSPP> * recode negatively worded questions.
PSPP> compute v3 = 6 - v3.
PSPP> compute v5 = 6 - v5.
PSPP> reliability v1, v3, v4.

Output (dictionary information omitted for clarity):

1.1 RELIABILITY.  Case Processing Summary
#==============#==#======#
#              # N|   %  #
#==============#==#======#
#Cases Valid   #17|100.00#
#      Excluded# 0|   .00#
#      Total   #17|100.00#
#==============#==#======#

1.2 RELIABILITY.  Reliability Statistics
#================#==========#
#Cronbach's Alpha#N of Items#
#================#==========#
#             .81#         3#
#================#==========#

Example 5.4: Recoding negatively scaled variables, and testing for reliability with the RELIABILITY command. The Cronbach Alpha coefficient suggests a high degree of reliability among variables v1, v3 and v4.

As a rule of thumb, many statisticians consider a value of Cronbach’s Alpha of 0.7 or higher to indicate reliable data. Here, the value is 0.81 so the data and the recoding that we performed are vindicated.

5.2.4 Testing data consistency