|
|
|
||||
|
|
|||||
Please note that the "early_int" data file (which is used in Chapter 3) is not included among the data files. This was done at the request of the researcher who contributed this data file to ensure the privacy of the participants in the study. Although the web page shows how to obtain the results with this data file, we regret that visitors do not have access to this file to be able to replicate the results for themselves.
Table 3.1 on page 48.
Data Manipulation -> Select or omit cases
Table 3.3, page 69
In this model, the constant, called cons, is random at both levels 1 and 2. The variable age-1 is random at level 2, and program and the interaction, age-1*program, are fixed. MLwiN offers a point-n-click way to build up an interaction term.
The results of running the above model are shown below.
Figure 3.5, page 71
To obtain the predicted values after running the model shown in Table 3.3, click on "Model" and then "Predictions". Click on all of the grayed-out symbols at the top. This will make all of the symbols black. Now click on everything on the lines marked "level 1" and "level 2". This will remove these terms from the equation. In the bottom right corner, select a new variable to put the values into (you can change the name of the variable by pressing the control key and the N key at the same time). Finally, click on "Calc" in the lower left of the dialogue box. Next, click on "Graphs" at the top of the program and then "Customized Graph(s)". Select the variable into which you put the predicted values for the y-axis and age for the x-axis and program as groups. Click on "Apply" in the top left of the dialogue box to create the graph. The resulting graph will not look like the one shown below. You will need to adjust the range of values on the axes. To do this, click on the graph and select the "Scales" tab on the top right. Be sure to change the radio button for both axes to "User-defined scale" or your changes will not take effect. After you make your changes, click on "Apply" and they will appear on the graph.
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