negbin.reg: Negative binomial regression

In Rfast2: A Collection of Efficient and Extremely Fast R Functions II

Negative binomial regression

Description

Negative binomial regression.

Usage

negbin.reg(y, x, tol = 1e-07, maxiters = 100)
negbin.regs(y, x, type = 1, tol = 1e-07, logged = FALSE, parallel = FALSE, maxiters = 100)

Arguments

y	The dependent variable, a numerical vector with integer valued numbers.
x	A matrix or a data.frame with the indendent variables. For the many regression models, a matrix with continuous variables.
type	This argument is for the negative binomial and the geometric distribution. In the negative binomial you can choose which way your prefer. Type 1 is for smal sample sizes, whereas type 2 is for larger ones as is faster. For the geometric it is related to its two forms. Type 1 refers to the case where the minimum is zero and type 2 for the case of the minimum being 1.
tol	The tolerance value required by the Newton-Raphson to stop.
logged	If you want the logarithm of the p-values set this equal to TRUE.
parallel	Do you want this to be executed in parallel or not. The parallel takes place in C++, therefore you do not have the option to set the number of cores.
maxiters	The maximum iterations allowed.

Details

In the first function a negative binomial regression model is fitted. The standard errors of the regressions are not returned as we do not compute the full Hessian matrix at each step of the Newton-Raphson. The second function implements many simple negative binomial regressions with a log-link are fitted.

Value

For the single regression model function a list including:

be	The regression coefficients.
loglik	The loglikelihood of the regression model.
iters	The iterations required by the Newton-Raphson.

For the many regression models function a matrix with the test statistic values and their relevant (logged) p-values.

Author(s)

Stefanos Fafalios and and Michail Tsagris.

R implementation and documentation: Stefanos Fafalios [e-mail] and Michail Tsagris [e-mail].

References

McCullagh, Peter, and John A. Nelder. Generalized linear models. CRC press, USA, 2nd edition, 1989.

Zakariya Yahya Algamal and Intisar Ibrahim Allyas (2017). Prediction of blood lead level in maternal and fetal using generalized linear model. International Journal of Advanced Statistics and Probability, 5(2): 65–69.

See Also

ztp.reg, binom.reg, bic.regs, score.zipregs

Examples

y <- rnbinom(100, 10, 0.7)
x <- matrix( rnorm(100 * 3), ncol = 3 )
mod <- negbin.reg(y, x)
x <- matrix( rnorm( 100 * 20), ncol = 20 )
a <- negbin.regs(y, x)
x <- NULL

Rfast2 documentation built on April 11, 2025, 6:15 p.m.