Project

General

Profile

Support #579

attrition question

Added by zoe young about 6 years ago. Updated about 6 years ago.

Status:
Closed
Priority:
Immediate
Assignee:
Category:
-
Start date:
06/11/2016
% Done:

100%


Description

Hi I have merged 3 variables from wave3 to wave 5 they are : c_cgwri_dv, c_cgvfc_dv, and c_cgna_dv. I want to obtain the mean for these variables but only for those who are present in wave 5. I created 2 dummy variables where wave 5 =1 is present in wave 5 and wave 3=1 if present in wave 3. when i ran a cross tab it showed that the entire sample that were in wave 3 were in wave 5. Can someone confirm this as it seems strange that no attrition occured between wave 3 and 5?

Thanks Zoe

#1

Updated by Alita Nandi about 6 years ago

  • Status changed from New to In Progress
  • Assignee set to zoe young
  • % Done changed from 0 to 50
  • Private changed from Yes to No

Assuming you are Stata, some common minor mistakes that could have led to this problem:
(i) You coded the dummy variables=0 as default, so the dummy variables = 0 even for individuals not present in either wave instead of being "."
(ii) You did not do (i) but when looking at the cross-tab of wave3 wave5 dummies you did not use the missing option, that is, you typed
tab wave3 wave5
Instead of
tab wave3 wave5, missing

There is attrition between Waves 3 and 5 and there are new entrants in Wave 5 who were not present in Wave 3.

Best wishes,
Alita

#2

Updated by Victoria Nolan about 6 years ago

  • Status changed from In Progress to Closed
  • % Done changed from 50 to 100

Also available in: Atom PDF