S******y
发帖数: 1123 | 1 I have split my data into training(70%) and hold-out (30%) data.
I fit a linear model with k parameters on training data, and obtained
model M1.
Then I used the parameter estimates from training data to compute
predicted values for hold-out data (i.e. score the hold-out data).
Aside from MSE or RMSE (Root Mean Square Error), can I use other model
diagnostic metrics to evaluate model fit on hold-out data? For example,
does it make sense to compute AIC value for my model M1 on hold-out data?
(we |
s*********e
发帖数: 1051 | 2 ******************************************;
* HOW TO USE IML PROCEDURE TO CALCULATE *;
* THE LIKELIHOOD FUNCTION OF A LOGIT *;
* MODEL TOGETHER WITH AIC AND BIC. *;
* -------------------------------------- *;
* WITH THE SAME ROUTINE, AIC AND BIC *;
* FROM A SEPARATE HOLDOUT DATASET CAN BE *;
* CALCULATED. *;
******************************************;
*** REMISSION DATA IS FROM EXAMPLES OF ***;
*** LOGISTIC PROCEDURE IN SAS MANUAL ***;
ods output Param |
s*r
发帖数: 2757 | 3 bic is better than aic to get a smaller model
they are old. there are many recent development on this area |
S******y
发帖数: 1123 | 4 Thanks both of you for helping out!
Sir, can you give some examples on the recent development?
Thanks again! |
