Generalized Linear Autoregressive Moving Average Models
Extract AIC from a GLARMA Model
Extract GLARMA Model Fitted Values
Forecasting GLARMA time series
Generalized Linear Autoregressive Moving Average Models with Various D...
Extract GLARMA Model Coefficients
Initial Parameter Generator for GLARMA from GLM
Likelihood Ratio Test and Wald Test for GLARMA Fit
Extract Log-Likelihood from GLARMA Models
Extracting the Model Frame of the GLARMA Model
Matrix Inversion of the Hessian of the Log-Likelihood
Extract the Number of Observations from a GLARMA Model Fit
Parameter Generators
Non-randomized Probability Integral Transformation
Plot Diagnostics for a glarma Object
PIT Plots for a glarma Object
Random normal probability integral transformation
Extract GLARMA Model Residuals
Summarize GLARMA Fit
Functions are provided for estimation, testing, diagnostic checking and forecasting of generalized linear autoregressive moving average (GLARMA) models for discrete valued time series with regression variables. These are a class of observation driven non-linear non-Gaussian state space models. The state vector consists of a linear regression component plus an observation driven component consisting of an autoregressive-moving average (ARMA) filter of past predictive residuals. Currently three distributions (Poisson, negative binomial and binomial) can be used for the response series. Three options (Pearson, score-type and unscaled) for the residuals in the observation driven component are available. Estimation is via maximum likelihood (conditional on initializing values for the ARMA process) optimized using Fisher scoring or Newton Raphson iterative methods. Likelihood ratio and Wald tests for the observation driven component allow testing for serial dependence in generalized linear model settings. Graphical diagnostics including model fits, autocorrelation functions and probability integral transform residuals are included in the package. Several standard data sets are included in the package.