# remlscore

##### REML for heteroscedastic regression

Fits a heteroscedastic regression model using residual maximum likelihood (REML).

##### Usage

`remlscore(y, X, Z, trace=FALSE, tol=1e-5, maxit=40)`

##### Arguments

- y
- numeric vector of responses
- X
- design matrix for predicting the mean
- Z
- design matrix for predicting the variance
- trace
- Logical variable. If true then output diagnostic information at each iteration.
- tol
- Convergence tolerance
- maxit
- Maximum number of iterations allowed

##### Value

- List with the following components:
beta Vector of regression coefficients for predicting the mean se.beta gamma Vector of regression coefficients for predicting the variance se.gam Standard errors for gamma mu Estimated means phi Estimated variances deviance Minus twice the REML log-likelihood h Leverages

##### item

details

##### eqn

$\mu_i=E(y_i)$

##### var

(y_i)$.
We assume the heteroscedastic regression model
$$\mm_i=\bold{x}_i^T\bold{\beta}$$
$$\log(\sigma^2_i=\bold{z}_i^T\bold{\gamma},$$
where $**x**_i$ and $**z**_i$ are vectors of covariates, and $*Journal of Computational and Graphical Statistics* **11**, 1-12.

*Documentation reproduced from package statmod, version 0.6, License: GPL version 2 or newer*