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

st: RE: chi squared test for trend

From   "Newson, Roger B" <>
To   "''" <>
Subject   st: RE: chi squared test for trend
Date   Thu, 23 Jul 2009 12:35:12 +0100

Yes, you could use -nptrend- to test for trend between 2 ordinal variables such as yours. However, -nptrend- only gives you a P-value. It might be more informative to have a confidence interval for a trend measure, such as Somers' D. To get this, use the -somersd- package, which you can download from SSC.

I hope this helps.

Best wishes


Roger B Newson BSc MSc DPhil
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton Campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322
Web page:
Departmental Web page:

Opinions expressed are those of the author, not of the institution.

-----Original Message-----
From: [] On Behalf Of Rune Nielsen
Sent: 23 July 2009 09:12
Subject: st: chi squared test for trend

Dear all!
I've tried searching the archives concerning this without finding it  

I've got two categorical variables, one ordered with three groups, and  
the other as an dichotomous outcome. Can I use the nptrend command to  
test for trend of proportion over the three (ordered) groups?

Best wishes

Rune N.

Rune Nielsen, MD, research fellow
Institute of Medicine
Department of Thoracic Medicine
Haukeland University Hospital
N-5021 Bergen
*   For searches and help try:

*   For searches and help try:

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