Hi all,
I am using glm function with family binomial(logit) to fit logistic
regression model. My data is very big and the algorithm is such that it
has to run glm function hundreds of times. Now *I need only the
**estimates of the coefficients and std. error in my output, *but
apparently glm function is computing several other statistics and
parameters (mentioned below) which increases the run time.
[aic, boundary, call, coefficients, contrasts, control, converged,
data, deviance, df.null, df.residual, effects, family, fitted.values,
formula, iter, linear.predictors, method, model, null.deviance, offset,
prior.weights, qr, R, rank, residuals, terms, weights, xlevels, y]
Is there a way (apart from scratching the glm code), which only do the
minimal computations to output my requirements.
Any hints can be helpful.
Regards
Utkarsh
[[alternative HTML version deleted]]
