Binary Logistic Regression Analysis

[mkzaman]

Hello
I am trying to run Binary logistic regression analysis in SPSS with 5 model. Odd Ratio of two is being calculated and showing the following message "Logistic Regression Due to redundancies, degrees of freedom have been reduced for one or more variables". How could I solve the problem. Would anyone suggest any option to solve this problem.

Regards
Kamruzzaman

[Jignesh Sutar]

It's likely you may have a predictor which is perfectly correlated with the dependent?:

https://www.ibm.com/developerworks/community/forums/html/topic?id=1b1718c8-93b5-414a-993f-a3565ee87882

On 11 February 2015 at 12:28, mkzaman <[hidden email]> wrote:

Hello
I am trying to run Binary logistic regression analysis in SPSS with 5 model.
Odd Ratio of two is being calculated and showing the following message
"Logistic Regression Due to redundancies, degrees of freedom have been
reduced for one or more variables". How could I solve the problem. Would
anyone suggest any option to solve this problem.

Regards
Kamruzzaman



--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Binary-Logistic-Regression-Analysis-tp5728641.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

[Rich Ulrich]

Jingnesh,

NO.  A predictor that is perfectly correlated with the dependent
is probably a mistake in specification, and you probably do want
to leave it out; but I'm pretty sure that the proper answer is given
at the URL that you cite.  - redundancy among the predictors.

--
Rich Ulrich

---

Date: Wed, 11 Feb 2015 12:36:46 +0000
From: [hidden email]
Subject: Re: Binary Logistic Regression Analysis
To: [hidden email]

It's likely you may have a predictor which is perfectly correlated with the dependent?:

https://www.ibm.com/developerworks/community/forums/html/topic?id=1b1718c8-93b5-414a-993f-a3565ee87882

On 11 February 2015 at 12:28, mkzaman <[hidden email]> wrote:

Hello
I am trying to run Binary logistic regression analysis in SPSS with 5 model.
Odd Ratio of two is being calculated and showing the following message
"Logistic Regression Due to redundancies, degrees of freedom have been
reduced for one or more variables". How could I solve the problem. Would
anyone suggest any option to solve this problem.

Regards
KamruzzamanREFCARD

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD