How to use correctly fitlm modelspec ?
5 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Hello,
I want to make a linear regression using three variables (SlopeS, SlopeD, MaxWRatio) and my response vector errorPs. When I use the function fitlm with the model specification "interactions" it gives me y = x1 + x2 + x3 + x1*x2 + x1*x3 + x2*x3. Now I want to test the fitlm for y = x1*x2 + x1*x3 + x2*x3. How can I do it ? I try with a terms matrix and also with a formula but I always have errors... Could you help me ? Below is my code. Thank you very much in advance ! N0N0.
% first with term matrix
XS = [SlopeS,SlopeD,MaxWRatio]; % it is 13x3 doubles
y = errorPs; % it is 13 doubles
T = [0 0 0 0, 1 1 0 0, 0 1 1 0, 1 0 1 0];
Regression = fitlm(XS,y,T);
I obtain the error and I don't understand what I have to change:
Error using classreg.regr.TermsRegression/createFormula (line 818)
The terms matrix must have one column for each predictor variable, and the
last column for the response variable.
And with formula:
% second with formula
XS = [SlopeS,SlopeD,MaxWRatio]; % it is 13x3 doubles
y = errorPs; % it is 13 doubles
Regression = fitlm(XS,y,'y ~ SlopeS:SlopeD:MaxWRatio'
And here I obtain this error and I still don't know what to change !
The model formula contains names not recognized as predictor or response
names.
Thank you for your help !!!!
0 Kommentare
Antworten (0)
Siehe auch
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!