# A Fortran 90 Program for the Generalized Order-Restricted Information Criterion

## Main Article Content

## Abstract

_{0}: β

_{1,1}= … = β

_{t,k}and H

_{u}: β

_{1,1}, …, β

_{t,k}and hypotheses containing simple order restrictions H

_{m}: β

_{1,1}≥ … ≥ β

_{t,k}, where any "≥" may be replaced by "=" and m is the model/hypothesis index; with β

_{h,j}the parameter for the h-th dependent variable and the j-th predictor in a t-variate regression model with k predictors (which might include the intercept). But, the GORIC can also be applied to restrictions of the form H

_{m}: R

_{1}β = r

_{1}; R

_{2}β ≥ r

_{2}, with β a vector of length tk, R

_{1}a c

_{m1}× tk matrix, r

_{1}a vector of length c

_{m1}, R

_{2}a c

_{m2}× tk matrix, and r

_{2}a vector of length c

_{m2}. It should be noted that [R

_{1}

^{T}, R

_{2}

^{T}]

^{T}should be of full rank when [R

_{1}

^{T}, R

_{2}

^{T}]

^{T}≠ 0. In practice, this implies that one cannot examine range restrictions (e.g., 0 < β

_{1,1}< 2 or β

_{1,2}< β

_{1,1}< 2β

_{1,2}) with the GORIC. A Fortran 90 program is presented, which enables researchers to compute the GORIC for hypotheses in the context of multivariate regression models. Additionally, an R package called goric is made by Daniel Gerhard and the first author.