Bent Nielsen: Package apc

apc: Age-Period-Cohort Analysis

Functions for age-period-cohort analysis. The 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. The canonical parametrisation of Kuang, Nielsen and Nielsen (2008) is used. Thus, the analysis does not rely on ad hoc identification.

Papers on Age-Period-Cohort Analysis

apc on CRAN

Version: 1.3
Published: 2016-12-01
Download: CRAN

apc: Development version

Version: 1.3.3
Published: 2018-08-27
Package source: apc_1.3.3.tar.gz
Windows binaries: apc_1.3.3.zip
R file: combined.functions.R Script file with the updates. Run this as a script file if working with an earlier version of apc.

apc in Python

Jonas Harnau has written a version of apc in Python.

Vignettes

ReadData Illustrates how to read data from files and construct apc.data.list. Uses the Belgian lung cancer data from Clayton and Schiffler (1987). Considers data store in csv format: response.csv, rates.csv and xlsx format: both.xlsx. 1.3 R code
Identification Illustrate and check identification used in plot fit function 1.1 PDF source R code
NewDesign Generating new models from design matrix function 1.1 PDF source R code
ReproducingMMNN2015 Reproducing Martinez Miranda, Nielsen and Nielsen (2015). Inference and forecasting in the age-period-cohort model with unknown exposure with an application to mesothelioma mortality. Journal of the Royal Statistical Society series A 178, 29-55. Download: Nuffield DP. Published version. Estimation, forecasting using data.asbestos() 1.2.2 PDF source R code
ReproducingMMNN2016 Reproducing Martinez-Miranda, Nielsen and Nielsen (2016). A simple benchmark for mesothelioma projection for Great Britain. Download: Nuffield DP. Estimation, forecasting using data.asbestos.2013() 1.2.1 PDF source R code
ReproducingHN2016 Reproducing Harnau and Nielsen (2016). Asymptotic theory for over-dispersed age-period-cohort and extended chain ladder models Estimation, forecasting using data.loss.TA() 1.3.2 PDF source R code

apc: Development Versions, Previous Releases

Version: 1.3.1
Published: 2017-05-07
Package source: apc_1.3.1.tar.gz
Windows binaries: apc_1.3.1.zip

Version: 1.3.2
Published: 2018-08-15
Package source: apc_1.3.2.tar.gz
Windows binaries: apc_1.3.2.zip