GAM: Normal, Gamma, Poisson

Full featured implementation of generalized additive models (GAM) techniques developed and popularized by Hastie and Tibshirani (1990); Statistica supports various continuous distributions (Normal, Gamma) and the Poisson distribution, and the log, identity, and inverse link functions (use the GAM: Binomial option to analyze binomial variables and distributions, and the logit-link). Complete summary statistics including predicted and observed values, and plots of the cubic spline smoother functions are computed.

General

Element Name Description
Distribution Select the distribution for the dependent variables.

Statistica supports various continuous distributions (Normal, Gamma) and the Poisson distribution, and the log, identity, and inverse link functions; use the GAM: Binomial option to analyze binomial variables and distributions, and the logit-link.
Link function Specifies the link function.

Statistica supports various continuous distributions (Normal, Gamma) and the Poisson distribution, and the log, identity, and inverse link functions; use the GAM: Binomial option to analyze binomial variables and distributions, and the logit-link.
Degrees of freedom Specifies the degrees of freedom for the cubic spline smoother that will be applied to each continuous predictor variable. The fewer degrees of freedom you specify, the smoother is the cubic spline fit to the partial residuals, and typically, the worse is the overall fit of the model. The issue of degrees of freedom for smoothers is discussed in detail in Hastie and Tibshirani (1990).
Includes intercept Specifies whether to include the intercept term in the generalized additive model; note that if categorical predictors are selected into the model, the intercept is required, and this option is ignored.
Missing data deletion Missing data can be deleted casewise (a case or observation will be excluded from the analysis if it has missing data for any variable in the analysis), or substituted by means.

Estimation

Element Name Description
Threshold, inner model, 1E- Specifies the negative exponent for a base-10 constant Delta (delta = 10^-idelta); this parameter controls the iterative estimation loop for the inner model.

 The iterative estimation procedure will terminate when the likelihood of the data given the model cannot be improved, relative to the threshold parameters specified in the Threshold field, or when the maximum number of iterations specified in the Maximum number of iterations field has been exceeded.
Max iterations; inner model Specifies the maximum number of iterations for the estimation loop for the inner model.

 The iterative estimation procedure will terminate when the likelihood of the data given the model cannot be improved, relative to the threshold parameters specified in the Threshold field, or when the maximum number of iterations specified in the Maximum number of iterations field has been exceeded.
Threshold, outer model, 1E- Specifies the negative exponent for a base-10 constant Delta (delta = 10^-idelta); this parameter controls the iterative estimation loop for the outer model.

 The iterative estimation procedure will terminate when the likelihood of the data given the model cannot be improved, relative to the threshold parameters specified in the Threshold field, or when the maximum number of iterations specified in the Maximum number of iterations field has been exceeded.
Max iterations; outer model Specifies the maximum number of iterations for the estimation loop for the outer model.

 The iterative estimation procedure will terminate when the likelihood of the data given the model cannot be improved, relative to the threshold parameters specified in the Threshold field, or when the maximum number of iterations specified in the Maximum number of iterations field has been exceeded.