ml_g function

Function to fit linear regression using maximum likelihood.

This function demonstrates the use of maximum likelihood to fit ordinary least-squares regression models, by maximizing the likelihood as a function of the parameters. Only conditional normal errors are supported.

ml_g(formula, data)

Arguments

• formula: an object of class '"formula"' (or one that can be coerced to that class): a symbolic description of the model to be fitted. (See the help for 'lm' for more details).
• data: a data frame containing the variables in the model.

Details

This function has limited functionality compared with R's internal lm function, which should be preferred in general.

Returns

• fit: the output of optim.

• X: the design matrix.

• y: the response variable.

• call: the call used for the function.

• beta.hat: the parameter estimates.

• se.beta.hat: estimated standard errors of the parameter estimates.

• sigma.hat: the estimated conditional standard deviation of the response variable.

References

Hilbe, J.M., and Robinson, A.P. 2013. Methods of Statistical Model Estimation. Chapman & Hall / CRC.

Author(s)

Andrew Robinson and Joe Hilbe.

Note

We use least squares to get initial estimates, which is a pretty barbaric hack. But the purpose of this function is as a starting point, not to replace existing functions.

See Also

lm

Examples

data(ufc)
ufc <- na.omit(ufc)

ufc.g.reg <- ml_g(height.m ~ dbh.cm, data = ufc)

summary(ufc.g.reg)