General Linear Models

Builds a linear model to predict continuous dependent variables. The parameters in Statistica allow full access to the GLM syntax for specifying models. Default results include the ANOVA/ANCOVA (MANOVA/MANCOVA) table; set the Level of detail parameter to All results to request tables of means and other statistics. Residual and predicted values can be computed on request.

General

Detail of computed results reported. Specifies the detail of computed results reported. If All results is requested, Statistica will report all univariate results (for multivariate designs), descriptive statistics, details about the design terms, the whole-model R, regression coefficients, and the least-squares means for all effects. Residual and predicted statistics (for observations) can be requested as options.

Analysis syntax. Analysis syntax string for general linear models. You can specify here the complete syntax, as, for example, copied from a Statistica analysis. Set this string to empty, or just GLM; to create the syntax from the specific options specified below.

Design. Specifies the design for the between group design (categorical and continuous predictors); by default (if no design is specified) a full factorial design will be constructed for categorical predictors, and continuous predictor main effects are evaluated.

Use the syntax:
DESIGN = Design specifications

Example 1.
DESIGN = GROUP | GENDER | TIME | PAID; {makes a full factorial design}

Example 2.
DESIGN = SEQUENCE + PERSON(SEQUENCE) + TREATMNT + SEQUENCE*TREATMNT;

Example 3.
DESIGN = MULLET | SHEEPSHD | CROAKER @2; {Makes factorial design to degree 2}

Example 4.
DESIGN = TEMPERAT | MULLET | SHEEPSHD | CROAKER - TEMPERAT; {Removes main effect for TEMPERAT from factorial design}

Example 5.
DESIGN = BLOCK + DEGREES + DEGREES*DEGREES + TIME + TIME*TIME + TIME*DEGREES;

Parameterization. Specifies either the sigma-restricted model (keyword SIGMA), or the overparameterized model (keyword OVERP); SIGMA is the default parameterization, except for nested designs or mixed-model ANOVA and ANCOVA designs.; see the Electronic Manual topic: The Sigma-Restricted vs. Overparameterized Model for additional details.

Intercept. Specifies whether the intercept (constant) is to be included in the model (i.e., a parameter is to be estimated for the intercept); the default is INTERCEPT=INCLUDE.

Type of sums of squares. Specifies how to construct the hypotheses for the tests of main effects and interactions; for the sigma-restricted model (PARAM=SIGMA) the default value is 6 (unique or effective hypothesis decomposition; see Hocking, 1985) and option 4 is not valid; for the overparameterized model (PARAM=OVERP) the default value is 3 (orthogonal; see Goodnight, 1980), and option 6 is not valid. For a description and discussion of the different options for constructing main effect and interaction hypotheses in unbalanced and incomplete designs, see also the Six Types of Sums of Squares topic in the Electronic Manual.

Random effects. Optional; specify the names of the between-group factors (categorical predictors); all effects (main effects and interactions) involving random factor effects will also be treated as random effects in the analysis.

SDelta. Specifies the negative exponent for a base-10 constant Delta (delta = 10^-sdelta); the default value is 7. Delta is used (1) in sweeping, to detect redundant columns in the design matrix, and (2) for evaluating the estimability of hypotheses; specifically a value of 2*delta is used for the estimability check.

IDelta. specify the negative exponent for a base-10 constant Delta (delta = 10^-idelta); the default value is 12. Delta is used to check for matrix singularity in matrix inversion calculations.

Generates data source, if N for input less than. Generates a data source for further analyses with other Data Miner nodes if the input data source has fewer than k observations, as specified in this edit field; note that parameter k (number of observations) will be evaluated against the number of observations in the input data source, not the number of valid or selected observations.

Repeated Measures

Repeated measures. Specifies the names and number of levels for the repeated measures factors; specify the within-subject (repeated measures) design via the Within subject design edit field; if no Within subject design is specified, the analysis will be performed on the within-model intercept, i.e., effectively on the overall mean for the variables specified in the dependent variable list.

Syntax:
Repeated measures:
{ NONE }{ Name Value Name Value ... Name Value}

Example.
Repeated measures:
TIME 3 DIALS 3

Within subject design. Specifies the design for the within-subject (repeated measures) factors specified in the Repeated measures edit field; if no Within subject design is specified, the analysis will be performed on the within-model intercept, i.e., effectively on the overall mean for the variables specified in the dependent variable list.

Syntax:
Within subject design:
{ NONE }{ Design specs }

Example.
Within subject design:
TIME | DIALS

Selected Results

Least Square Means. Creates the expected marginal means, given the current model; either all marginal means tables can be computed, or only the means for the highest-order effect of the factorial design.

Post Hoc Tests. Performs post-hoc comparisons between the means in the design.

Lack of fit. Requests the computation of pure error for testing the lack-of-fit hypothesis.

Tests homogeneity of variances. Tests the homogeneity of variances/covariances assumption. One of the assumptions of univariate ANOVA is that the variances are equal (homogeneous) across the cells of the between-groups design. In the multivariate case (MANOVA), this assumption applies to the variance/covariance matrix of dependent variables (and covariates).

Plots of means vs. std. dev. Plots the (unweighted) marginal means (see also the Means tab) for the selected Variables against the standard deviations; this option is not applicable to within-subjects (repeated measures) designs.

Residual analysis. In addition to the predicted, observed, and residual values, Statistica will compute the (default) 95% Prediction intervals and 95% Confidence limits, the Standardized predicted and Standardized residual score, the Leverage values, the Deleted residual and Studentized deleted residual scores, Mahalanobis and Cook distance scores, the DFFITS statistic, and the Standardized DFFITS statistic.

Normal probability plot. Normal probability plot of residuals.

Contrast coefficients. Specifies contrasts for least squares means; consult the Electronic Manual for syntax details.

Estimate (custom hypotheses). Optional; specify the coefficients that are to be used in the linear combination of parameter estimates for the custom hypothesis; multiple ESTIMATE specifications can appear in the same analysis. Note that tests of linear combinations of parameter estimates can also be requested from the Results dialog, where a convenient and efficient user interface is provided for specifying the coefficients.

Deployment. Deployment is available if the Statistica installation is licensed for this feature.

Generates C/C++ code. Generates C/C++ code for deployment of predictive model (for a single dependent variable only).

Generates SVB code. Generates Statistica Visual Basic code for deployment of predictive model (for a single dependent variable only).

Generates PMML code. Generates PMML (Predictive Models Markup Language) code for deployment of predictive model (for a single dependent variable only). This code can be used via the Rapid Deployment options to efficiently compute predictions for (score) large data sets.

Saves C/C++ code. Save C/C++ code for deployment of predictive model (for a single dependent variable only).

File name for C/C code. Specify the name and location of the file where to save the (C/C++) deployment code information.

Saves SVB code. Save Statistica Visual Basic code for deployment of predictive model (for a single dependent variable only).

File name for SVB code. Specify the name and location of the file where to save the (SVB/VB) deployment code information.

Saves PMML code. Saves PMML (Predictive Models Markup Language) code for deployment of predictive model (for a single dependent variable only). This code can be used via the Rapid Deployment options to efficiently compute predictions for (score) large data sets.

File name for PMML (XML) code. Specify the name and location of the file where to save the (PMML/XML) deployment code information.