.- help for ^arpois^ (STB-46: sts13) .- Poisson regression allowing for autocorrelation and oversdispersion -------------------------------------------------------------------- ^arpois^ [varlist] [weight] [^if^ exp] [^in^ range] [^,^ ^ar(^#^) delete prev^ ] ^aweight^s, ^fweight^s, ^iweight^s, and ^pweight^s are allowed. Description ----------- ^arpois^ estimates a Poisson model allowing for autocorrelation and overdispersion (Schwartz et al 1996). This model was developed for the APHEA project (Katsouyanni et al. 1996), and has been extensively used to analyse time series regression for counts. Options ------- ^ar(^#^)^ specifies the number of autoregressive terms to be included in the model. ^delete^ drops the working dependent variabel, named _z, and the auto- regressive terms, named _rho1, _rho2, etc. By default these variables are stored in the data set. ^prev^ shows the previous, standard, Poisson model which neither allows for autocorrelation nor for overdispersion. Examples -------- ^. arpois mortal year89 year90 sine cosine temp no2, ar(4)^ ^. arpois mortal year89 year90 sine cosine temp no2, ar(4) delete^ ^. arpois mortal year89 year90 sine cosine temp no2, ar(4) delete prev^ References ---------- Schwartz, J., Spix, C., Touloumi, G., et al. (1996). Methodological issues in studies of air pollution and daily counts of deaths or hospital admissions. Journal of Epidemiology and Community Health 50(Suppl 1): S3-S11. Katsouyanni K., Schwartz J., Spix C., et al. (1996). Short-term effects of air pollution on health: a European approach using epidemiological time series data. The APHEA protocol. J Epidemiol Community Health 50(Suppl 1): S12-S18. Authors ------- Aurelio Tobias Institut Municipal d'Investigacio Medica (IMIM) atobias@@imim.es Michael J. Campbell Institute of General Practice and Primary Care University of Sheffield m.j.campbell@@sheffield.ac.uk Also see -------- STB: sts13 (STB-46) On-line: help for @poisson@, @nl@ lookup for @time series@