Use this to determine the significance of the fixed terms in a REML model by calculating marginal and conditional tests for these. This uses the VSCREEN procedure to perform the tests. This dialog is opened from the Further Output dialog when there are at least two fixed terms in the model.
This specifies which items of output are to be produced by the screening tests.
|F tests||F tests for fixed model terms|
|Wald tests||Wald tests for fixed model terms|
Exclude higher order interactions in conditional model
Setting this option will exclude higher order terms than the tested term in the conditional tests, otherwise the term is added to the most complex possible model that contains no terms involving the term to be tested. For example, for the model A*B*C*D*E, interaction A.B would be added to the model containing all terms except those involving A.B (such as the interaction A.B.C), and so the interaction C.D.E would be included when testing A.B. In this case, setting this option would exclude the higher-order terms like C.D.E when testing A.B.
You can specify terms in this field that should always be included in the model. These terms are fitted first, and are not tested.
Use these items to save results from the screening tests. After selecting the appropriate boxes, you need to type the identifiers of the data structures into the corresponding In: fields.
|F tests||Pointer Statistics from the F tests for each fixed term|
|Wald tests||Pointer Statistics from the Wald tests for each fixed term|
Note: the labels of the F tests pointer will be ‘Fixed term’, ‘n.d.f.’, ‘d.d.f.’, ‘Marginal F test’, ‘Marginal pr.’, ‘Conditional F test’ and ‘Conditional pr.’ for the name of the term, numerator degrees of freedom, denominator degrees of freedom, marginal F ratio, marginal F probability, conditional F ratio and conditional F probability respectively. The labels of the Wald tests pointer will be ‘Fixed term’, ‘d.f.’, ‘Marginal Wald test’, ‘Marginal pr.’, ‘Conditional Wald test’ and ‘Conditional pr.’ for the name of the term, degrees of freedom, marginal Wald test statistic, marginal Wald probability, conditional Wald test statistic and conditional Wald probability respectively.
Display in spreadsheet
When selected the data structures that are saved will be displayed within spreadsheets.
- Linear Mixed Model menu
- Initial Values for specifying initial gamma.
- Further Output for obtaining additional output after fitting a model.
- Save for saving the results from a REML analysis.
- Save REML results in a spreadsheet.
- Residual Plots for generating plots of residuals.
- Means Plots for generating plots of one- or two-way tables of means.
- REML directive for command mode use of REML, with additional options to control the algorithm and for more sophisticated analyses.
- VCOMPONENTS directive for further information about fixed, random, and spline model terms.
- Linear Mixed Models (REML) – Correlated Errors for setting up covariance models.
- REML Detect Outliers dialog for identifying outliers
- REML Power calculations dialog for calculating the power of a REML analysis.
- REML Permutation Test dialog for calculating the significance of a random term using a permutation test.
- VCHECK procedure to check the residuals.
- VSCREEN procedure to perform screening tests for fixed effects.