Censored Time Series Analysis with Autoregressive Moving Average Models

Time series measurements are often observed with data irregularities, such as censoring due to a detection limit. Practitioners commonly disregard censored data cases which often result into biased estimates. We present an attractive remedy for handling autocorrelated censored data based on a class of autoregressive and moving average (ARMA) models. In particular, we introduce an imputation method well suited for fitting ARMA models in the presence of censored data. We demonstrate the effectiveness of the technique in terms of bias, efficiency, and information loss, and describe its adaptation to a particular data on a meteorological time series of cloud ceiling height, which are measured subject to the detection limit of the recording device. Some key words: Censored time Series; Fisher Information Matrix; Gibbs Sampling; Imputation Method; Truncated Multivariate Normal. Short title: Censored Time Series Analysis Clinical Pharmacology Statistics and Programming, GlaxoSmithKline, PO Box 13398, Five Moore Drive, Research Triangle Park, NC 27709-3398, USA. E-mail: [email protected] Department of Statistics, Texas A&M University, College Station, TX 77843-3143, USA. E-mail: [email protected] Department of Statistics, North Carolina State University, Box 8203, Raleigh, NC 27695-8203, USA. E-mail: [email protected]