# Trend analysis in temperature time series

Does anyone know how to determine the significance of the slope from linear model fitted using generalised least squares (GLS)? I am fitting a linear model to temperature time series with the aim of assessing for trends using gls function in nlme package, but I could not figure out the p-value (s) for the slope in model outputs. I chose GLS because of serial correlation.

• gls() in nlme does allow you to alter the off-diagonal elements of the variance covariance matrix and Fox's (2008) Applied Regression Analysis & GLMs has GLS very much at the centre of a chapter on time series regression. The details are in Pinhiero & Bates on mixed models in S Apr 2 '12 at 16:51