BIC of many simple univariate regressions.
BIC of many simple univariate regressions.
bic.regs(y, x, family = "normal")
y |
The dependent variable, a numerical vector. |
x |
A matrix with the indendent variables. |
family |
The family of the regression models. "normal", "binomial", "poisson", "multinomial", "normlog" (Gaussian regression with log link), "spmpl" (SPML regression) or "weibull" for Weibull regression. |
Many simple univariate regressions are fitted and the BIC of every model is computed.
A vector with the BIC of each regression model.
Michail Tsagris
R implementation and documentation: Michail Tsagris mtsagris@uoc.gr.
y <- rbinom(100, 1, 0.6) x <- matrix( rnorm(100 * 50), ncol = 50 ) bic.regs(y, x, "binomial")
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.