I am looking for the proper way to generate the Multinomial logit regression.
My data set is based on a survey responses which vary from 1 to 7 from Most Disatisfied to Most Satisfied. I was given SPSS syntax to validate the output that we need to calculate using an external library. In this case, I am hoping to make use of this library for it.
The SPSS syntax is:
plum satscore with score1 score2 score3
/link = logit
/print = parameter summary tparallel.
Data:
{6.0, 6.0, 7.0, 6.0} ,{5.0, 6.0, 7.0, 5.0} ,{4.0, 6.0, 7.0, 4.0} ,{7.0, 6.0, 7.0, 5.0} ,{6.0, 6.0, 7.0, 6.0} ,{7.0, 6.0, 7.0, 6.0} ,{5.0, 5.0, 7.0, 6.0} ,{7.0, 5.0, 7.0, 5.0} ,{4.0, 6.0, 6.0, 5.0} ,{5.0, 6.0, 7.0, 5.0} ,{5.0, 6.0, 7.0, 3.0} ,{5.0, 6.0, 7.0, 3.0} ,{6.0, 7.0, 6.0, 4.0} ,{6.0, 6.0, 6.0, 4.0} ,{5.0, 6.0, 6.0, 5.0} ,{7.0, 6.0, 6.0, 6.0} ,{4.0, 6.0, 7.0, 1.0} ,{6.0, 6.0, 7.0, 6.0} ,{5.0, 6.0, 6.0, 4.0} ,{4.0, 5.0, 5.0, 2.0} ,{7.0, 7.0, 7.0, 5.0} ,{5.0, 7.0, 7.0, 5.0} ,{7.0, 7.0, 7.0, 6.0} ,{6.0, 6.0, 6.0, 5.0} ,{3.0, 6.0, 6.0, 0.0}
{score1, score2, score3, satscore}
Score 1 to 3 have been left unmodified in their respective ranges from 1 to 7, but following the instructions I have adjusted satscore to a range from 0 to 6 (rather than 1 to 7).
Code:
int nAttributes = 3;
int nSamples = 25;
int nClasses = 7;
double[,] tsData = new double[25, 4] {
{6.0, 6.0, 7.0, 6.0} ,{5.0, 6.0, 7.0, 5.0} ,{4.0, 6.0, 7.0, 4.0} ,{7.0, 6.0, 7.0, 5.0} ,{6.0, 6.0, 7.0, 6.0} ,{7.0, 6.0, 7.0, 6.0} ,{5.0, 5.0, 7.0, 6.0} ,{7.0, 5.0, 7.0, 5.0} ,{4.0, 6.0, 6.0, 5.0} ,{5.0, 6.0, 7.0, 5.0} ,{5.0, 6.0, 7.0, 3.0} ,{5.0, 6.0, 7.0, 3.0} ,{6.0, 7.0, 6.0, 4.0} ,{6.0, 6.0, 6.0, 4.0} ,{5.0, 6.0, 6.0, 5.0} ,{7.0, 6.0, 6.0, 6.0} ,{4.0, 6.0, 7.0, 1.0} ,{6.0, 6.0, 7.0, 6.0} ,{5.0, 6.0, 6.0, 4.0} ,{4.0, 5.0, 5.0, 2.0} ,{7.0, 7.0, 7.0, 5.0} ,{5.0, 7.0, 7.0, 5.0} ,{7.0, 7.0, 7.0, 6.0} ,{6.0, 6.0, 6.0, 5.0} ,{3.0, 6.0, 6.0, 0.0}
};
alglib.logitmodel lm = new alglib.logitmodel();
alglib.mnlreport rep = new alglib.mnlreport();
int info = -1;
alglib.mnltrainh(tsData, nSamples, nAttributes, nClasses, out info, out lm, out rep);
int nSamples = 25;
int nClasses = 7;
double[,] tsData = new double[25, 4] {
{6.0, 6.0, 7.0, 6.0} ,{5.0, 6.0, 7.0, 5.0} ,{4.0, 6.0, 7.0, 4.0} ,{7.0, 6.0, 7.0, 5.0} ,{6.0, 6.0, 7.0, 6.0} ,{7.0, 6.0, 7.0, 6.0} ,{5.0, 5.0, 7.0, 6.0} ,{7.0, 5.0, 7.0, 5.0} ,{4.0, 6.0, 6.0, 5.0} ,{5.0, 6.0, 7.0, 5.0} ,{5.0, 6.0, 7.0, 3.0} ,{5.0, 6.0, 7.0, 3.0} ,{6.0, 7.0, 6.0, 4.0} ,{6.0, 6.0, 6.0, 4.0} ,{5.0, 6.0, 6.0, 5.0} ,{7.0, 6.0, 6.0, 6.0} ,{4.0, 6.0, 7.0, 1.0} ,{6.0, 6.0, 7.0, 6.0} ,{5.0, 6.0, 6.0, 4.0} ,{4.0, 5.0, 5.0, 2.0} ,{7.0, 7.0, 7.0, 5.0} ,{5.0, 7.0, 7.0, 5.0} ,{7.0, 7.0, 7.0, 6.0} ,{6.0, 6.0, 6.0, 5.0} ,{3.0, 6.0, 6.0, 0.0}
};
alglib.logitmodel lm = new alglib.logitmodel();
alglib.mnlreport rep = new alglib.mnlreport();
int info = -1;
alglib.mnltrainh(tsData, nSamples, nAttributes, nClasses, out info, out lm, out rep);
The output I am looking for are the estimates for each score and thresholds for further analysis. The attached image has what I am looking for based on the SPSS output.
At this point I am unclear what I can do to this model to obtain what I need. Any suggestions?
| Attachments: |
|
File comment: SPSS Output Logit.png [ 8.26 KiB | Viewed 3859 times ] |