Outliers in Mixed Models for Monthly Average Temperatures

Mercedes Andrade-Bejarano; Nicholas T. Longford

doi:10.17713/ajs.v39i3.245

Authors

Mercedes Andrade-Bejarano School of Industrial Engineering and Statistics, Universidad del Valle, Cali, Colombia, and University of Reading, United Kingdom
Nicholas T. Longford SNTL and Department of Economics and Business, University Pompeu Fabra, Barcelona, Spain

DOI:

https://doi.org/10.17713/ajs.v39i3.245

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.

References

Andrade, M. (2009). Monthly Average Temperature Modelling for Valle del Cauca (Colombia). (Unpublished PhD. Thesis. The University of Reading, United Kingdom)

Atherton, J. G., and Rudich, J. (1986). The Tomato Crop; A Scientific Basis for Improvement. Chapman and Hall.

Atkinson, A. C. (1985). Plots, Transformations and Regression. An Introduction to Graphical Methods of Diagnostic Regression Analysis. Oxford University Press.

Belsley, D. A., Kuh, E., and Welsch, R. E. (1980). Regression Diagnostics. Identifying Influential Data and Sources of Collinearity. John Wiley and Sons.

Brown, H., and Prescott, R. (1999). Applied Mixed Models in Medicine. John Wiley and Sons.

Cook, R. D., and Weisberg, S. (1982). Residuals and Influence in Regression. Chapman and Hall.

Demidenko, E. (2004). Mixed Models. Theory and Applications. John Wiley and Sons.

Hadi, A. S., and Simonoff, J. S. (1993). Procedures for the identification of multiple outliers in linear models. Journal of the American Statistical Association, 88, 1264-1272.

Haslett, J., and Haslett, S. J. (2007). The three basic types of residuals for a linear model. International Statistical Review, 75, 1-24.

Hawkins, D. M. (1980). Identification of Outliers. Chapman and Hall.

Henderson, C. R. (1982). Analysis of covariance in the mixed model: higher-level, nonhomegeneous, and random regressions. Biometrics, 38, 623-640.

Isaaks, E. H., and Srivastava, R. M. (1989). An Introduction to Applied Geostatistics. Oxford University Press.

Jones, J. B. (2000). Tomato Plant Culture. In the Field, Greenhouse and Home Garden. CRC Press LLC.

Laird, N. M., and Ware, J. H. (1982). Random-effects models for longitudinal data. Biometrics, 38, 963-974.

Langford, I. H., and Lewis, T. (1998). Outliers in multilevel data. Journal of the Royal Statistical Society, Series A, 161, 121-160.

Longford, N. T. (1998). Discussion of the paper Outliers in multilevel data by I. Langford and T. Lewis. Journal of the Royal Statistical Society, Series A, 161, 154-155.

Longford, N. T. (2001). Simulation-based diagnostics in random-coefficient models. Journal of the Royal Statistical Society, Series A, 164, 259-273.

Madl, P. (2000). The El Niño (ENSO) Phenomenon. Environmental Physics Letter, 437-503.

Rubin, D. B. (1984). Bayesianly justifiable and relevant frequency calculations for the applied statistician. The Annals of Statistics, 12, 1151-1172.

Schanberger, O. (2004). Mixed model influence diagnostics. In Proceedings of the Twenty-Ninth Annual SAS Users Group International Conference.

Verbeke, G., and Molenberghs, G. (2000). Linear Mixed Models for Longitudinal Data. Springer-Verlag.

Villareal, R. L. (1980). Tomatoes in the Tropics. Westview Press Inc.