Functions for age-period-cohort analysis. Aggregate data can be organised in matrices indexed by age-cohort, age-period or cohort-period. The data can include dose and response or just doses. The statistical model is a generalized linear model (GLM) allowing for 3,2,1 or 0 of the age-period-cohort factors. Individual-level data should have a row for each individual and columns for each of age, period, and cohort. The statistical model for repeated cross-section is a generalized linear model. The statistical model for panel data is ordinary least squares. The canonical parametrisation of Kuang, Nielsen and Nielsen (2008)
Package: apc Version: 1.3 Date: 2016-11-17
CHANGES in version 1.3 Improvements apc.fit.model model.family="od.poisson.response" added, uses "quasipoisson" family apc.fit.table model.family="od.poisson.response" added apc.forecast.apc new apc.plot.data.within can take averages or sums apc.data.sums can take averages or sums Bugs apc.data.list defaults for time labels fixed model.design.reference option added. apc.plot.fit.pt dependent variable corrected for gaussian.rates
CHANGES in version 1.2 New functions apc.forecast.ac distribution forecasts for model.family="poisson.response" model.design="AC" Improvements apc.data.list.subset Generates row and column names for trapezoid data matrix Warning adjusted Bugs apc.get.index default for time.adjust fixed calculation of coh1 adjusted for "AP" and "PA"
CHANGES in version 1.1.2 Bugs data.loss.VNJ counts fixed
CHANGES in version 1.1.1 New functions apc.plot.data.level level plot of data apc.plot.data.within now plotting only one combination apc.plot.data.within.all.six apc.plot.fit.residuals level plot of residuals apc.plot.fit.linear.predictors level plot of linear predictors apc.plot.fit.fitted.values level plot of fitted.values apc.plot.fit.all Documentation apc.data.list.Rd Example of generating labels of data matrix To do: Discuss what the labels of the data matrix do Perhaps make labels of data matrix automatic? Improvements apc.data.list Generates row and column names for data matrices when none have been provided. Bugs apc.plot.data.within Legend fixed
CHANGES in version 1.1 New functions vector.2.triangle: For input of reserving triangles recorded in vector form Data format "CL.as.vector" then dropped data.loss.BZ: Reserving triangle data.loss.TA: Reserving triangle data.loss.VNJ: Reserving triangle New vignettes Identification NewDesign Improvements apc.plot.data.sparsity now allows for NA observations swap order of age axis for "CL" apc.plot.fit.pt swap order of age axis for "CL" apc.plot.fit Rd rewritten apc.identify Rd rewritten Bugs apc.plot.fit Constant in panel (e) corrected apc.fit.model model.design="P" corrected apc.identify Constant for type "detrend" corrected apc.data.list Input check for data.format "CL" and "CL.as.vector" corrected