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.

310 Fitting Dispersion Effects with the Loglinear Variance Model Chapter 12<br />

Loglinear Platform Options<br />

Does the variance model fit significantly better than the original model? The likelihood ratio test for this<br />

question compares the fitted model with the model where all parameters are zero except the intercept, the<br />

model of equal-variance. In this case the p-value is highly significant. Changes in Hold Time change the<br />

variance.<br />

The Variance Effect Likelihood Ratio Tests refit the model without each term in turn to create the<br />

likelihood ratio tests. These are generally more trusted than Wald tests.<br />

Loglinear Platform Options<br />

The red triangle menu next to Loglinear Variance Fit contains the following options.<br />

Table 12.1 Descriptions of Loglinear Platform Options<br />

Save Columns<br />

Creates one or more columns in the data table. See “Save Columns” on<br />

page 310.<br />

Row Diagnostics Plots row diagnostics. See “Row Diagnostics” on page 311.<br />

Profilers<br />

Model Dialog<br />

Script<br />

Opens the Profiler, Contour Profiler, or Surface Profiler. See “Factor<br />

Profiling” on page 92 in the “Fitting St<strong>and</strong>ard Least Squares Models”<br />

chapter.<br />

Shows the completed launch window for the current analysis.<br />

Contains options that are available to all platforms. See Using JMP.<br />

Save Columns<br />

Table 12.2 Descriptions of Save Columns Options<br />

Prediction Formula<br />

Variance Formula<br />

Std Dev Formula<br />

Residuals<br />

Studentized Residuals<br />

Creates a new column called Mean. The new column contains the predicted<br />

values for the mean, as computed by the specified model.<br />

Creates a new column called Variance. The new column contains the<br />

predicted values for the variance, as computed by the specified model.<br />

Creates a new column called Std Dev. The new column contains the<br />

predicted values for the st<strong>and</strong>ard deviation, as computed by the specified<br />

model.<br />

Creates a new column called Residual that contains the residuals, which are<br />

the observed response values minus predicted values. See “Examining the<br />

Residuals” on page 311.<br />

Creates a new column called Studentized Resid. The new column values are<br />

the residuals divided by their st<strong>and</strong>ard error.

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

Saved successfully!

Ooh no, something went wrong!