Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st:multiple imputation for missing items of a scale


From   Mandy fu <mandy.fu1@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st:multiple imputation for missing items of a scale
Date   Wed, 2 Dec 2009 15:59:24 -0500

Hi all,

I would like to impute for the missing items for a scale measuring
stress. The stress scale is calculated by adding 18 items all
together, where each item is about one respect about stress. An
example of one of the items is like this:

item1 : question: How often did you feel no interest in things in last 30 days?
0:   never
1:   occasionally
2:   often
3:   very often

In the data set, many respondents have a couple of missing items out
of the 18 items. So, I am thinking to use multiple imputation to
impute the missing items in order to get the scale measurement.

My question is, using multiple imputation (command -ice- ) to impute
the missing items, is there anything different than , say, any other
18 usual variables? Or is there anything I need to be especially
cautious when imputing these items?  Thanks in advance!

Best wishes,

Mandy
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index