Conditional least-squares estimate for Poisson INAR(1) models {Rfast2}

Conditional least-squares estimate for Poisson INAR(1) models

Description

Conditional least-squares estimate for Poisson INAR(1) models.

Usage

pinar1(x, unbiased = FALSE)
colpinar1(x, unbiased = FALSE)

Arguments

x

Either a numerical vector or a matrix, depending on the function.

unbiased

If you want the unbiased estimation select TRUE.

Details

The function computes the constant and slope coefficients of the Poisson Integer Autoregressive of order 1 (Poisson INAR(1)) model using the conditional least-squares method.

Value

For pinar1() a vector with two values, the \lambda coefficient (constant) and the \alpha coefficient (slope). See references for more information.

For the colpinar1() a matrix with two columns, the \lambda coefficient (constant) and the \alpha coefficient (slope) for each variable (column of x).

Author(s)

Michail Tsagris.

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

References

M. Bourguignon and K.L.P. Vasconcellos (2015). Improved estimation for Poisson INAR(1) models. Journal of Statistical Computation and Simulation, 85(12): 2425-2441

See Also

fipois.reg, hp.reg

Examples

x <- rpois(200, 10)
pinar1(x)