|
|
|
||||
|
|
|||||
Historically speaking, preceding to MLwiN, there was MLn, a DOS based program for multilevel modeling. MLwiN's major improvement on MLn is its graphical user interface. It also keeps a Command interface through Data Manipulation menu for users to issue commands as in MLn. The Command interface will update other screens of MLwiN interactively through the commands issued.
Let's first enter some data into MLwiN. We rename the three variables to be id, sex and score. Click here for more detail on how to rename a variable.


WAIT 0 init 5 1000 400 150 20 track c90 c91 prior c92 GALLfilter c95 echo 0 fpath C:\Program Files\MLwiN1.10\discrete prefile pre postfile post EDIT 1 c1 1 EDIT 2 c1 2 EDIT 3 c1 3 EDIT 4 c1 4 EDIT 5 c1 5 EDIT 6 c1 6 EDIT 7 c1 7 EDIT 1 c2 1 EDIT 2 c1 0 EDIT 2 c2 0 EDIT 3 c2 1 EDIT 4 c2 1 EDIT 5 c2 0 EDIT 6 c2 0 EDIT 7 c2 0 EDIT 1 c3 89 EDIT 2 c3 71 EDIT 3 c3 68 EDIT 4 c3 45 EDIT 5 c3 76 EDIT 6 c3 39 EDIT 7 c3 81 NAME C3 'score' NAME C2 'sex' NAME C1 'id'

Let's say we want to know the mean value for variable score. We can do this through Averages and Correlations from Basic Statistics menu. The content of the output window is shown below. The first line is the command that produces the result. The first four letters are capitalized, because MLwiN only requires the first four letters to by typed.
->AVERage 1 "score"
N Missing Mean s.d. score 7 0 68.571 20.951
Now we can type a command such as "aver 1 "sex" to get the mean for variable sex instead of going through the point-and-click process.
For more information
For more information on using MLwiN commands through Command interface window, see the introductory tutorial part from the manual.
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