Age–period–cohort models are a popular tool for studying population-level rates; for example, trends in cancer incidence and mortality. Age–period–cohort models decompose observed trends into age effects that correlate with natural history, period effects that reveal factors impacting all ages simultaneously (e.g. innovations in screening), and birth cohort effects that reflect differential risk exposures that vary across birth years. Methodology for the analysis of multiple population strata (e.g. ethnicity, cancer registry) within the age–period–cohort framework has not been thoroughly investigated. Here, we outline a general model for characterizing differences in age–period–cohort model parameters for a potentially large number of strata. Our model incorporates stratum-specific random effects for the intercept, the longitudinal age trend, and the model-based estimate of annual percent change (net drift), thereby enabling a comprehensive analysis of heterogeneity. We also extend the standard model to include quadratic terms for age, period, and cohort, along with the corresponding random effects, which quantify possible stratum-specific departures from global curvature. We illustrate the utility of our model with an application to metastatic prostate cancer incidence (2004–2013) in non-Hispanic white and black men, using 17 population-based cancer registries in the Surveillance, Epidemiology, and End Results Program.
WangZKYuCHWangJYet al.Age-period-cohort analysis of suicide mortality by gender among white and black Americans, 1983-2012. Int J Equity Health2016; 15: 107–116.
2.
KramerMRValderramaALCasperML. Decomposing black-white disparities in heart disease mortality in the United States, 1973-2010: An age-period-cohort analysis. Am J Epidemiol2015; 182: 302–312.
3.
RosenbergPSAndersonWF. Age-period-cohort models in cancer surveillance research: ready for prime time?Cancer Epidemiol Biomarkers Prev2011; 20: 1263–1268.
4.
McNallyRJBlakeyKJamesPWet al.Increasing incidence of thyroid cancer in Great Britain, 1976-2005: age-period-cohort analysis. Eur J Epidemiol2012; 27: 615–622.
5.
GordonPHArtaudFAoubaAet al.Changing mortality for motor neuron disease in France (1968-2007): an age-period-cohort analysis. Eur J Epidemiol2011; 26: 729–737.
6.
ShielsMSChernyavskiyPAndersonWFet al.Diverging trends in premature mortality in the U.S. by sex, race and ethnicity in the 21st century. The Lancet2017; 389: 1043–1054.
7.
SiegelRLFedewaSAAndersonWFet al.Colorectal cancer incidence patterns in the United States, 1974–2013. JNCI: J Natl Cancer Inst2017; 109: 1–6.
8.
RyersonABEhemanCRAltekruseSFet al.Annual report to the nation on the status of cancer, 1975‐2012, featuring the increasing incidence of liver cancer. Cancer2016; 122: 1312–1337.
9.
RosenbergPSAndersonWF. Proportional hazards models and age-period-cohort analysis of cancer rates. Stat Med2010; 29: 1228–1238.
10.
SimXAliRAWedrenSet al.Ethnic differences in the time trend of female breast cancer incidence: Singapore, 1968-2002. BMC Cancer2006; 6: 261–272.
11.
SungHNRosenbergPSChenWQet al.Female breast cancer incidence among Asian and Western populations: More similar than expected. JNCI-J Natl Cancer Inst2015; 107: 1–7.
12.
KellySPRosenbergPSAndersonWFet al.Trends in the incidence of fatal prostate cancer in the United States by race. Eur Urol2017; 71: 195–201.
13.
RosenbergPSBarkerKAAndersonWF. Estrogen receptor status and the future burden of invasive and in situ breast cancers in the United States. J Natl Cancer Inst2015; 107: 1–7.
14.
PetrickJLKellySPAltekruseSFet al.Future of hepatocellular carcinoma incidence in the United States forecast through 2030. J Clin Oncol2016; 34: 1787–1794.
15.
HolfordTR. The estimation of age, period and cohort effects for vital rates. Biometrics1983; 39: 311–324.
16.
HolfordTR. Understanding the effects of age, period, and cohort on incidence and mortality rates. Annu Rev Publ Health1991; 12: 425–457.
17.
HolfordTR. Analysing the temporal effects of age, period and cohort. Stat Methods Med Res1992; 1: 317–337.
18.
HolfordTR. Approaches to fitting age‐period‐cohort models with unequal intervals. Stat Med2006; 25: 977–993.
19.
YangYLandKC. Age-period-cohort analysis: New models, methods, and empirical applications, Boca Raton, FL: CRC Press, 2013.
20.
YangYSchulhofer-WohlSFuWJJet al.The intrinsic estimator for age-period-cohort analysis: What it is and how to use it. Am J Sociol2008; 113: 1697–1736.
21.
AndersonWFJatoiITseJet al.Male breast cancer: a population-based comparison with female breast cancer. J Clin Oncol2010; 28: 232–239.
22.
SmithTRWakefieldJ. A review and comparison of age–period–cohort models for cancer incidence. Stat Sci2016; 31: 591–610.
23.
PapoilaALRieblerAAmaral-TurkmanAet al.Stomach cancer incidence in Southern Portugal 1998–2006: A spatio‐temporal analysis. Biometr J2014; 56: 403–415.
24.
Surveillance, Epidemiology, and End Results (SEER) Program (www.seer.cancer.gov): Incidence - SEER 18 Regs Research Data, Nov 2015 sub, National Cancer Institute, DCCPS, Surveillance Research Program, 2017.
25.
RiderJR. Lead time, like trains and tides, stops for no one. Eur Urol2017; 71: 202–203.
26.
SiegelRLMillerKDJemalA. Cancer statistics, 2016. CA: Cancer J Clin2016; 66: 7–30.
27.
DeSantisCNaishadhamDJemalA. Cancer statistics for African Americans, 2013. CA: Cancer J Clin2013; 63: 151–166.
ClaytonDSchifflersE. Models for temporal variation in cancer rates. II: age–period–cohort models. Stat Med1987; 6: 469–481.
30.
FayMPTiwariRCFeuerEJet al.Estimating average annual percent change for disease rates without assuming constant change. Biometrics2006; 62: 847–854.
31.
RosenbergPSCheckDPAndersonWF. A web tool for age-period-cohort analysis of cancer incidence and mortality rates. Cancer Epidemiol Biomarkers Prev2014; 23: 2296–2302.
32.
MaccullaghPNelderJA. Generalized linear models, New York, NY: Chapman and Hall, 1992.
33.
JemalAMaJMRosenbergPSet al.Increasing lung cancer death rates among young women in southern and midwestern states. J Clin Oncol2012; 30: 2739–2744.
34.
ZengPZhaoYLiHet al.Permutation-based variance component test in generalized linear mixed model with application to multilocus genetic association study. BMC Med Res Methodol2015; 15: 37–46.
35.
GiampaoliVSingerJM. Likelihood ratio tests for variance components in linear mixed models. J Stat Plann Inference2009; 139: 1435–1448.
36.
FitzmauriceGMLipsitzSRIbrahimJG. A note on permutation tests for variance components in multilevel generalized linear mixed models. Biometrics2007; 63: 942–946.
37.
LeeOEBraunTM. Permutation tests for random effects in linear mixed models. Biometrics2012; 68: 486–493.
38.
Akaike H. Information theory and an extension of the maximum likelihood principle. In: Petrov BN and Budapest FC (eds) Second international symposium on information theory, vol. 19, Budapest, 1974, pp.716–723.
39.
SchwarzG. Estimating the dimension of a model. Ann Stat1978; 6: 461–464.
40.
TeamRC. R: A language and environment for statistical computing, Vienna, Austria: R Foundation for Statistical Computing, 2015.
41.
BatesDMachlerMBolkerBMet al.Fitting linear mixed-effects models using lme4. J Stat Softw2015; 67: 1–48.
42.
StroupWW. Generalized linear mixed models: Modern concepts, methods and applications, Boca Raton, FL: CRC Press, 2012.
43.
PinheiroJCChaoEC. Efficient Laplacian and adaptive Gaussian quadrature algorithms for multilevel generalized linear mixed models. J Comput Graph Stat2006; 15: 58–81.
44.
JoeH. Accuracy of Laplace approximation for discrete response mixed models. Comput Stat Data Anal2008; 52: 5066–5074.
45.
MATLAB. MATLAB and statistics toolbox release, Natick, MA: The MathWorks Inc., 2012.
46.
RipattiSPalmgrenJ. Estimation of multivariate frailty models using penalized partial likelihood. Biometrics2000; 56: 1016–1022.
47.
KalbfleischJDPrenticeRL. The statistical analysis of failure time data, Hoboken, NJ: Wiley, 2011.
48.
LunnDJThomasABestNet al.WinBUGS - A Bayesian modelling framework: Concepts, structure, and extensibility. Stat Comput2000; 10: 325–337.
49.
Plummer M. JAGS: A program for analysis of Bayesian graphical models using Gibbs sampling. In: Proceedings of the 3rd international workshop on distributed statistical computing, Vienna, Austria, 2003, p.125.
50.
MullerSScealyJLWelshAH. Model selection in linear mixed models. Stat Sci2013; 28: 135–167.
51.
VaidaFBlanchardS. Conditional Akaike information for mixed-effects models. Biometrika2005; 92: 351–370.
52.
YangY. Can the strengths of AIC and BIC be shared? A conflict between model identification and regression estimation. Biometrika2005; 92: 937–950.
53.
DonohueMCOverholserRXuRet al.Conditional Akaike information under generalized linear and proportional hazards mixed models. Biometrika2011; 98: 685–700.
54.
AhoKDerryberryDPetersonT. Model selection for ecologists: the worldview of AIC and BIC. Ecology2014; 95: 631–636.
55.
BurnhamKPAndersonDR. Model selection and multimodel inference: A practical information-theoretic approach, 2nd ed. New York: Springer-Verlang, 2002, pp. 488–488.
56.
BrownHPrescottR. Applied mixed models in medicine, Hoboken, NJ: Wiley, 2006.
GelmanA. Analysis of variance - Why it is more important than ever. Ann Stat2005; 33: 1–31.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
