Сравнение на методи

	Age-Period-Cohort Analysis	Lee-Carter Mortality Model
Област	Social Epidemiology	Демография
Семейство	Regression model	Regression model
Година на възникване	1983	1992
Създател	Theodore R. Holford; Yang Yang & Kenneth C. Land (intrinsic estimator)	Ronald D. Lee & Lawrence R. Carter
Тип	Generalized linear model for rates indexed by age, period, and cohort	Log-bilinear model for forecasting age-specific mortality
Основополагащ източник	Holford, T. R. (1983). The Estimation of Age, Period and Cohort Effects for Vital Rates. Biometrics, 39(2), 311-324.	Lee, R. D., & Carter, L. R. (1992). Modeling and Forecasting U.S. Mortality. Journal of the American Statistical Association, 87(419), 659-671.
Други названия	APC Analysis, Age-Period-Cohort Models, Cohort Analysis of Rates, Intrinsic Estimator APC	Lee-Carter Method, Log-Bilinear Mortality Model, LC Mortality Forecast, Poisson Lee-Carter Model
Свързани	4	3
Резюме	Age-period-cohort (APC) analysis decomposes variation in disease or mortality rates into three temporal components: the effect of age (biological and accumulated risk), the effect of period (influences hitting everyone alive at a given calendar time, such as a new treatment or a recession), and the effect of cohort (lasting imprints of the conditions into which a birth generation was born). Theodore Holford's 1983 Biometrics paper gave the canonical generalized-linear-model formulation and exposed the method's defining obstacle: because cohort equals period minus age, the three predictors are exactly linearly dependent, so their individual linear slopes cannot be separately identified. A large methodological literature has since proposed constraints, reparameterizations, and estimators to extract whatever the data can legitimately support. Yang, Schulhofer-Wohl, Fu, and Land's 2008 work popularized the intrinsic estimator, a principled choice among the infinitely many fitting solutions. APC analysis is a workhorse of descriptive epidemiology and demography, used to read the temporal fingerprints left on rates of cancer, suicide, obesity, and mortality. Done carefully it separates signal from artifact; done carelessly it manufactures trends that the identification problem makes unknowable.	The Lee-Carter model is the benchmark method for forecasting human mortality. Introduced by Ronald Lee and Lawrence Carter in 1992 for U.S. data, it captures the entire schedule of age-specific death rates with a remarkably parsimonious structure: the logarithm of the death rate at each age is a fixed average age profile, plus an age-specific sensitivity multiplied by a single time index that summarizes the overall level of mortality in each year. Because mortality has fallen steadily across the twentieth century, this single index trends downward over time, and forecasting it as a simple time-series process, typically a random walk with drift, propagates the historical pace of improvement into the future for every age at once. Brouhns, Denuit, and Vermunt later recast the fitting step as a Poisson regression on observed death counts, giving the model a proper statistical likelihood and more reliable uncertainty, and the approach now anchors official population and pension projections worldwide.