Regular revisions of the classification of diseases and the consequent disruptions of mortality series are well-known issues in long-term cause-of-death analysis. Given basic assumptions and medical knowledge about possible exchanges across causes of death in the revision years, redistribution of counts of causes of death into a new classification can be viewed as a constrained optimization problem. Penalized likelihood within a quadratic programming framework allows estimation of exchanges that vary smoothly over age groups. The approach is illustrated using both German data on malignant neoplasms and French data on heart diseases.
CamardaCGPechholdováM (2014) Assessing the presence of disruptions in cause-specific mortality series: A statistical approach. In European Population Conference 2014. Budapest: European Association for Population Studies.
2.
EilersPHCMarxBD (1996) Flexible smoothing with B-splines and penalties (with discussion). Statistical Science, 11, 89–102.
3.
GoldfarbDIdnaniA (1983) A numerically stable dual method for solving strictly convex quadratic programs. Mathematical Programming, 27, 1–33.
4.
GrigorievPMesléFVallinJ (2012) Reconstruction of continuous time series of mortality by cause of death in Belarus, 1965-2010 (MPIDR Working Paper 2012-023). Rostock: Max Planck Institute for Demographic Research.
Human Cause-of-Death Database (2018). French Institute for Demographic Studies (France) and Max Planck Institute for Demographic Research (Germany). Available at www.causeofdeath.org.
7.
JanssenFKunstAE (2004) ICD coding changes and discontinuities in trends in cause-specific mortality in six European countries, 1950–99. Bulletin of the World Health Organization, 82, 904–913.
8.
MesléFVallinJ (1996) Reconstructing long-term series of causes of death: The case of France. Historical Methods, 29, 72–87.
9.
MoriyamaIMLoyRMRobb-SmithAHT (2011) History of the Statistical Classification of Diseases and Causes of Death. Atlanta, GA: Centers for Disease Control and Prevention; Hyattsville, MD: National Center for Health Statistics.
10.
Pawlowsky-GlahnVBucciantiA (eds) (2011) Compositional Data Analysis: Theory and Applications. Hoboken, NJ: Wiley.
11.
PechholdováM (2009) Results and observations from the reconstruction of continuous time series of mortality by cause of death: Case of West Germany, 1968–1997. Demographic Research, 21, 535–568.
12.
PechholdováMCamardaCGMesléFVallinJ (2017) Reconstructing long-term coherent cause-of-death series: A necessary step for analyzing trends. European Journal of Population, 33, 629–650.
13.
R Development Core Team (2018) R: A Language and Environment for Statistical Computing. Vienna: R Foundation for Statistical Computing. http://www.R-project.orglast accessed 8 February 2019.
14.
ReyGAoubaAPavillonGHoffmannRPlugIWesterlingRJouglaEMackenbachJ (2011) Cause-specific mortality time series analysis: A general method to detect and correct for abrupt data production changes. Population Health Metrics, 9, 1–11.
15.
TibshiraniR (1996) Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society, 58, 267–288.
16.
van der StegenRHMKorenLGHHartelohPPMKardaunJWPFJanssenF (2014) A novel time series approach to bridge coding changes with a consistent solution across causes of death. European Journal of Population, 30, 317–335.
17.
ZouHHastieT (2005) Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society, 67, 301–20.
