The IRT Procedure

where assignment represents: var-list < = parameter-spec>

The MEAN statement specifies the factor mean parameters in connection with the FACTOR statement.

In each assignment of the MEAN statement, you list the var-list that you want to specify for their means. Optionally, you can provide a list of parameter specifications in a parameter-spec after an equal sign for each var-list. The syntax of the MEAN statement is exactly the same as that of the VARIANCE statement. For more information, see the VARIANCE statement .

You can specify the following five types of the parameters for the means in the MEAN statement:

For example, consider a confirmatory factor model with latent factors F1, F2, F3, F4, F5. The following MEAN statement illustrates the five types of specifications in five assignments:

mean F1 ,
     F2 = (3.0),
     F3 = 1.5,
     F4 = fmean1,
     F5 = fmean2(0.6);

In this statement, the mean of F1 is specified as an unnamed free parameter. For this mean, PROC IRT generates a parameter name with the _Parm prefix appended with a unique integer (for example, _Parm1). The mean of F2 is an unnamed free parameter with an initial value of 3.0. PROC IRT also generates a parameter name for this mean. The mean of F3 is a fixed value of 1.5. This value stays the same during the estimation. The mean of F4 is a free parameter named fmean1. The mean of F5 is a free parameter named fmean2 with an initial value of 0.6.

If you do not use the MEAN statement, all the means of latent factors are fixed to 0 by default. For the confirmatory FACTOR models, you can override these default fixed 0 values by using the MEAN statement specifications. However, you cannot override the fixed 0 factor means for the exploratory FACTOR model.