Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: Item selectivity

From   Ronán Conroy <>
Subject   Re: st: RE: Item selectivity
Date   Tue, 20 Mar 2007 18:03:43 +0000

On 20 Márta 2007, at 17:46, Anderson, Bradley J wrote:

Dear stata members,

I want to do an item selectivity but I don?t know the stata command (I
always use SPSS). Is it right that I use the correlation between the
item and the total sum of the construct, e.g:
correlate allgAZ GesamtAZ
You need to investigate the options for -alpha-, notably -item- and - detail-

But then I don?t get any significane level.......

The significance level would be a test that the item had no correlation with the rest of the test, which is not a sensible hypothesis. Neither is the hypothesis that the test has a reliability of zero.

If you want to select items, I suggest you try -msp- which is a nonparametric method of constructing a scale or scales from an item pool.


. findit msp

to find it.

Ronán Conroy
Royal College of Surgeons in Ireland
+353 (0) 1 402 2431
+353 (0) 87 799 97 95

* For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index