Missing observations in longitudinal data

PhanS · Posted 10-12-2018 11:19 AM

Dear All,

I much appreciate your help.

I am analyzing a longitudinal survey data that collected 3 times (T1, T2, and T3). T1=600 observations, T2=500 (15%) was drop-out and T3=400 (13% was drop-out). Thus totally, 28% were a drop-out. Time-unvarying variables like sex, ethnicity did not collect in T2 and T3. An outcome of interests is a continuous variable. The main predictor is a categorical variable.

1) My inclusion criteria, I included only Subjects who had at least 2-time surveys. For instance, to exclude id_102 who missed a variable "ssup_cat" and id_107 who missed all variables. Please kindly see the attached file (I am use a SAS studio).

2) I want to create missing data files (lost to follow-up) in T1 and T2, T2 and T3 and T1 and T3.

How can I tell SAS to do the jobs. Thank you for your time in advance!

Phan S.

mkeintz · Posted 10-18-2018 08:26 PM

Show examples of the data illustrating all the anticipated conditions, in a DATA step format. The show what you want the result data set to look like.

--------------------------
The hash OUTPUT method will overwrite a SAS data set, but not append. That can be costly. Consider voting for Add a HASH object method which would append a hash object to an existing SAS data set

Would enabling PROC SORT to simultaneously output multiple datasets be useful? Then vote for
Allow PROC SORT to output multiple datasets

--------------------------

Missing observations in longitudinal data

Re: Missing observations in longitudinal data

SAS Innovate 2025: Call for Content

Click image to register for webinar

Classroom Training Available!