The DHS Program User Forum
Discussions regarding The DHS Program data and results
Home » Data » Dataset use in SPSS » Predictors of Abortion in Rwanda
Predictors of Abortion in Rwanda [message #6674] Thu, 25 June 2015 13:45 Go to next message
hacassien is currently offline  hacassien
Messages: 1
Registered: June 2015
Location: Stockholm
Member
Dear DHS expert,

I am analyzing the Rwanda DHS 2010 on the predictors of abortion. I am having problems of running logistic regression analysis, by using "ever had a terminated pregnancy (v228)" as dependent variable.
I am always receiving the following message:

"The dependent variable has less than two non-missing values. For logistic regression, the dependent value must assume exactly two values on the cases being processed".

I thank you very much for your help,

Sincerely,

Cassien


Cassien Havugimana
Re: Predictors of Abortion in Rwanda [message #6679 is a reply to message #6674] Fri, 26 June 2015 04:37 Go to previous message
Trevor-DHS is currently offline  Trevor-DHS
Messages: 639
Registered: January 2013
Senior Member
1) Please note that v228 (ever had a terminated pregnancy) means any type of pregnancy other than a live birth, including stillbirths, miscarriages and abortions. In most surveys it is not possible to determine if these are abortions or not.
2) I tried running a simple logistic regression using v228 and I had no problem. I suspect that the problem is related to either a selection you have applied or a combination of the other variables used in the regression. If you provide the logistic regression commands you are using we can advise better.
Previous Topic: With merged datasets, which weight to use?
Next Topic: Decoding Calendar Data provided in DHS in SPSS
Goto Forum:
  


Current Time: Thu Mar 21 18:47:07 Eastern Daylight Time 2019