Logistic Regression Prediction Equation

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

Logistic Regression Prediction Equation

Weinberg, Jerry

I’ve done a logistic regression using a number of continuous (interval) predictor variables and some categorical predictor variables and now have my model. Is there something in SPSS that will allow me to apply the resulting ‘regression’ coefficients to new data and create an equation for use in predicting membership in the dependent variable?  If not, what is it that I need to do to create this prediction equation?

 

 

 

Jerry Weinberg, Ph.D

St. Thomas University

===================== 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
Reply | Threaded
Open this post in threaded view
|

Re: Logistic Regression Prediction Equation

Jon K Peck
Save your  model as pmml (xml) when you estimate it, and the use Utilities > Scoring Wizard to generate new predicted values.   You can paste the syntax generated by the scoring wizard for reuse.  It will include a MODEL HANDLE command to select the pmml file and COMPUTE commands using the APPLYMODEL function for the calculations.  If there are transformations needed for the new data, they be part of the pmml (see the  TMS command), or they could just be repeated with regular syntax before doing the predictions.


Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
phone: 720-342-5621




From:        "Weinberg, Joseph A." <[hidden email]>
To:        [hidden email]
Date:        11/13/2014 08:53 AM
Subject:        [SPSSX-L] Logistic Regression Prediction Equation
Sent by:        "SPSSX(r) Discussion" <[hidden email]>




I’ve done a logistic regression using a number of continuous (interval) predictor variables and some categorical predictor variables and now have my model. Is there something in SPSS that will allow me to apply the resulting ‘regression’ coefficients to new data and create an equation for use in predicting membership in the dependent variable?  If not, what is it that I need to do to create this prediction equation?
 
 
 
Jerry Weinberg, Ph.D
St. Thomas University

===================== To manage your subscription to SPSSX-L, send a message to LISTSERV@... (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

MR
Reply | Threaded
Open this post in threaded view
|

Re: Logistic Regression Prediction Equation

MR
Hi Jon,

Is the scoring wizard only available in latest version of SPSS? I have version 20.0.1 but could not find this option. 

Mike
On Nov 13, 2014, at 1:18 PM, Jon K Peck <[hidden email]> wrote:

Save your  model as pmml (xml) when you estimate it, and the use Utilities > Scoring Wizard to generate new predicted values.   You can paste the syntax generated by the scoring wizard for reuse.  It will include a MODEL HANDLE command to select the pmml file and COMPUTE commands using the APPLYMODEL function for the calculations.  If there are transformations needed for the new data, they be part of the pmml (see the  TMS command), or they could just be repeated with regular syntax before doing the predictions.


Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
phone: 720-342-5621




From:        "Weinberg, Joseph A." <[hidden email]>
To:        [hidden email]
Date:        11/13/2014 08:53 AM
Subject:        [SPSSX-L] Logistic Regression Prediction Equation
Sent by:        "SPSSX(r) Discussion" <[hidden email]>




I’ve done a logistic regression using a number of continuous (interval) predictor variables and some categorical predictor variables and now have my model. Is there something in SPSS that will allow me to apply the resulting ‘regression’ coefficients to new data and create an equation for use in predicting membership in the dependent variable?  If not, what is it that I need to do to create this prediction equation?
 
 
 
Jerry Weinberg, Ph.D
St. Thomas University

===================== 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


===================== 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