No abstract

Data for this research come from time series of monthly average temperatures from 28 sites over the Valle del Cauca of Colombia in South America, collected over the period 1971-2002. Because of the geographical location of the study area, monthly average temperature is affected by altitude and El Niño-La Niña (El Niño-Southern Oscillation, or ENSO phenomenon). Time series for some of the sites show a tendency to increase. Also, because of the two dry and wet periods in the study area, a seasonal pattern of behavior in monthly average temperature is seen. Linear mixed models are formulated and fitted to account for withinand between-site variations. The ENSO phenomenon is modeled by the Southern Oscillation index (SOI) and dummy variables. Spatial and temporal covariance structures in the errors are modeled individually using isotropic variogram models. The fitted models demonstrate the influence of the ENSO phenomenon on monthly average temperatures; this is seen in the maps produced from the models for ENSO and normal conditions. These maps show the predicted spatial patterns for differences in temperature throughout the study area.

No abstract

Long-term series of monthly average temperatures taken at 28 sites in Valle del Cauca, Colombia, are studied. Mixed models are applied to cater for the within-and between-site variation. Outliers are inevitable in such studies, due to faulty equipment, slip-ups in the recording process, or unusual weather patterns. We apply a simulation-based approach to the assessment of the outlier status of suspected observations. It is a method based on graphical comparisons of user-defined features, related to large residuals, in the real and simulated data sets. Robustness in the identification of the outliers is achieved by applying the procedure with several alternative models. The impact of the identified outliers is assessed. Two meteorological stations, Zaragoza and Monteloro, are identified as having many outliers, so that all the data from them should be discarded.