LS

LS is a solver for estimating linear regression models in GAMS. It uses a stable QR decomposition that allows one to solve the regression problem quickly and accurately. LS provides a number of regression statistics such as standard errors, p-values, t-values, covariances and confidence intervals. These statistics are written to a GDX file so they can be read by a GAMS model. Erwin Kalvelagen is the original author and further information can be found in the solver manual or at the Amsterdam Optimization Modeling Group's web site.