14.03.2014 Views

Modeling and Multivariate Methods - SAS

Modeling and Multivariate Methods - SAS

Modeling and Multivariate Methods - SAS

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

34 Introduction to the Fit Model Platform Chapter 2<br />

Launch the Fit Model Platform<br />

Table 2.1 Description of the Fit Model Launch Window (Continued)<br />

Weight<br />

Freq<br />

By<br />

(Optional) Identifies one column whose values supply weights for the<br />

response. The corrected sum of squares is the number of observations minus<br />

1.<br />

(Optional) Identifies one column whose values assign a frequency to each<br />

row for the analysis. The corrected sum of squares in the number of<br />

frequencies minus one. Fractional frequencies (Freq values below 1) are<br />

included in the analysis.<br />

Performs a separate analysis for each level of the variable.<br />

Add Adds effects to the model. See “Add” on page 39.<br />

Cross<br />

Creates an interaction effect by crossing two or more variables. See “Cross”<br />

on page 40.<br />

Nest Creates a nested effect. See “Nest” on page 40.<br />

Macros<br />

Degree<br />

Attributes<br />

Transform<br />

No Intercept<br />

Automatically generates effects for commonly used models. See “Macros” on<br />

page 41.<br />

Enter the desired degree for factorials or polynomials.<br />

Specify the attributes that you want to assign to an effect in a model. See<br />

“Attributes” on page 45.<br />

(St<strong>and</strong>ard Least Squares only) Transforms selected continuous effects or Y<br />

columns. See “Transformations” on page 48.<br />

Only supported for continuous main effects.<br />

Excludes the intercept term from the model.<br />

Personality Specifies a fitting method. See “Fitting Personalities” on page 48.<br />

Emphasis<br />

Method<br />

(St<strong>and</strong>ard Least Squares only) Controls the types of plots <strong>and</strong> reports that<br />

appear in the initial report window. See “Emphasis Options for St<strong>and</strong>ard<br />

Least Squares” on page 50.<br />

(St<strong>and</strong>ard Least Squares with r<strong>and</strong>om effects only) Applies one of the<br />

following methods to the model:<br />

• REML. See “Restricted Maximum Likelihood (REML) Method” on<br />

page 113.<br />

• EMS. Also called the Method of Moments. See “Method of Moments<br />

Results” on page 123.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!