|
|
|
||||
|
|
|||||
Table 6.2 on page 203 on data set wages_pp.ws. The estimation method we use is IGLS, corresponding full ML used to create the table from SAS proc mixed.
Model A: EXPER, HGC-9, BLACK*EXPER, UE-7. We use MLwiN's option Main effects and interactions from Model menu to build up the interaction term of variable black and exper.
Model B:
Model C:
Model D:
Model E:
Model F:
Model G:
Model H:
Model I: We can use the option Main Effects and Interactions from Model menu to build up the interaction term of the categorical variable ged and continuous variable exper. When we declare ged as a categorical variable, we can rename each of the categories, for example, we name the category 0 as ged0 and category 1 as ged1. Then ged0 or ged1 will be used in the interaction term upon our choice.
This model has some problem converge. From Estimation Control, we have chosen the following: suppress numeric warnings and allow negative variances during the computation. It takes MLwiN 179 iterations for the model to converge.
Model J:
The model below is Model F from Table 6.2. The intercept (called cons) is random at levels 1 and 2, and the predictors exper, ged and postexp are random at level 2.
The results of the above model are shown below.
Table 6.4, page 214
This has been skipped for now.
Table 6.5, page 221
Model A:
This is an intercept-only model. The intercept (cons) is random at both levels 1 and 2.
The results of running the above model are shown below.
Model B:
Model B is the same as Model A, except that time has been added as a predictor. This variable is random at level 2.
The results of running the above model are shown below.
Model C:
Model C is the same as Model C, except that time2 has been added as a predictor. This variable is random at level 2.
The results of running the above model are shown below.
Model D:
Model D is the same as Model C, except that time3 has been added as a predictor. This variable is random at level 2.
The results of running the above model are shown below.
This has been skipped for now.
UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services