Abstract
This paper presents a method that uses observed data from an age-period table to set bounds on the age, period, and cohort effects in an age-period-cohort multiple classification (APCMC) model. The rationale is that with enough periods over a long time span the age distributions within periods on the dependent variable will be affected by different sets of cohorts for each of the periods. This is likely to result in different trends in these separate period age distributions such that the trends in the age distributions will encompass the trend in the age effects that generated the dependent variable values. This approach can help to identify bounds that likely encompass the age, period, cohort parameters that generated the data. The data used in this papers are estimated homicide arrests by single years for those aged 15–64 for the periods 1964 to 2019 in the United States. I utilize the observed trends in the age-distributions for each of the 56 periods as different constraints on the trends for the age effects in the APCMC fixed effects model. These estimates are used to form bounds on the age effects, period effects, and cohort effects.
Similar content being viewed by others
Notes
In the fixed effect APCMC model an infinity of solutions fit the data equally well. Most researchers are interested in which solution comes closest to the parameters that actually generated the dependent variable values. I label these parameters as the data generating parameters.
See O’Brien (2016) for a critique of this assumption. The question about this assumption is: Why should a linear trend without much variability around the trend (usually considered a good fit to the trend of the data and that makes the confidence limit for the trend smaller) be considered an argument for a zero linear trend? Or on the other hand: Is a poor linear fit, a good argument for confidence in a linear trend?
As Glenn (2005) notes: “... a definitive separation of age, period, and cohort effects is not just difficult, but impossible. However,... a definitive separation of the effects is not necessary in order for cohort analysis to be useful.”.
Using arrest rates by age or estimated homicide rates by age would not affect the pattern of results from the APCMC model, and if the reader prefers, they can think of the pattern of results as applying to homicide arrest rates.
I used the constrained regression package in Stata (Stata Corp 2019) to conduct the constrained regression.
This was accomplished by constraining the age effect in the APCMC model to one of the values for the age effects using the minimum trend and then one of the age effects using the maximum trend for the age observations within in periods in Step 4 of the Computing Bounds section above.
References
Baumer, E.P., Rosenfeld, R., Wolff, K.T.: Are the criminogenic consequences of economic downturns Conditional? Assessing potential moderators of the link between adverse economic conditions and crime rates. In: Rosenfeld, R., Edberg, M., Fang, X., Florence, C. (eds.) Economics and Youth Violence: Crime, Disadvantage, and Community, pp. 53–84. NYU Press, New York (2013)
Bell, A., Jones, K.: Bayesian informative priors with Yang and Land’s hierarchical age-period-cohort model. Quality Quant. 49, 255–266 (2015)
Blumstein, A., Cohen, J.G., Piquero, A.R., Visher, C.A.: Linking the crime and arrest processes to measure variations in individual arrest risk per crime (Q). J. Quant. Criminol. 26, 533–548 (2010)
Blumstein, A., Rosenfeld, R.: Factors contributing to U.S. crime trends. In: Goldberger A., Rosenfeld, R. (eds.) Understanding Crime Trends: Workshop Report, pp. 13–43. The National Academies Press Washington, DC: (2008). https://doi.org/10.17226/12472.
Blumstein, A., Wallman, J.: The crime drop and beyond. Ann. Rev. Law Soc. Sci. 2, 125–146 (2006)
Booth, H.: Demographic techniques: data adjustment and correction. In: Smelser, N.J., Baltes, P.B. (eds.) International Encyclopedia of the Social and Behavioral Sciences, pp. 3452–3456. Elsevier, New York (2001)
Britt, C.L.: Constancy and change in the U.S. age distribution of crime: a test of the "Invariance Hypothesis." J. Quant. Criminol. 8, 175–187 (1992).
Calot, G., Sardon. J.P.: Methodology for the Calculation of Eurostat’s Demographic Indicators Detailed Report by the European Demographic Observatory– EDO. Luxembourg office for official Publications of the European Communities, Luxembourg (2004).
CDC: Population by Age Groups, Race, and Sex for 1960-97. https://www.cdc.gov/nchs/data/statab/pop6097.pdf retrieved Feb 12, 2021.
CDC Wonder: United States Department of Health and Human Services (US DHHS), Centers for Disease Control and Prevention (CDC), National Center for Health Statistics (NCHS). Accessed at http://wonder.cdc.gov/bridged-race-v 2019.html on Feb 14, 2021.
Chauvel, L., Schröeder, M.: Generational inequalities and welfare regimes. Soc. Forces 2014(92), 1259–1283 (2014)
Dixon, A., Farrell, G.: Age‑period‑cohort effects in half a century of motor vehicle theft in the United States. Crime Science online first: 2020: https://doi.org/10.1186/s40163-020-00126-5.
FBI (various years). Crime in the United States (1964–2019). U.S. Government Printing Office, Washington, DC (1964–2019).
Fosse, E., Winship, C.: Bounding analyses of age-period-cohort effects. Demography 56, 1975–2004 (2019)
Glenn, N.D.: Cohort Analysis, 2nd edn. Sage, Thousand Oaks, California (2005)
Greenberg, D.: Age, crime, and social explanation. Am. J. Sociol. 91, 1–21 (1985)
Hirschi, T., Gottfredson, M.: Age and the explanation of crime. Am. J. Sociol. 89, 552–584 (1983)
Holford, T.R.: The estimation of age, period, and cohort effects for vital rates. Biometrics 39, 311–324 (1983)
Keyes, M., Utz, R.L., Robinson, W., Li, G.: What is a Cohort Effect? Comparison of Three Statistical Methods for Modeling Cohort Effects in Obesity Prevalence in the United States, 1971–2006. Soc. Sci. Med. 70, 1100–1108 (2010)
Kupper, L.L., Janis, J.M., Salama, I.A., Yoshizawa, C.N., Greenberg, B.G.: Age-period-cohort analysis: an illustration of the problems of assessing interaction in one observation per cell data. Communications in Statistics – Theory and Methods 12:2779–2807 (1983).
LaFree, G.: Losing Legitimacy: Street Crime and the Decline of Institutions in America. Westview Perseus, Boulder, CO (1998).
Levitt, S.D.: Understanding why crime fell in the 1990s: four factors that explain the decline and six that do not. Journal of Economic Perspectives. 18, 163–190 (2004)
Manski, C.F.: The Identification Problem in the Social Sciences. Harvard University Press, Cambridge Massachusetts (1999)
Mason, W.M., Smith, H.L.: Age-period-cohort analysis and the study of deaths from pulmonary tuberculosis. In: Mason, W.M., Fienberg, S.E. (eds.) Cohort Analysis in Social Research: Beyond the Identification Problem, pp. 151–227. Springer-Verlag, New York (1985)
Myck, M., Czkowska, M.O.: Healthier over time? Period effects in health among older Europeans in a step-wise approach to identification. Soc. Sci. Med. (2022). https://doi.org/10.1016/j.socscimed.2022.114791
National Research Council: The Growth of Incarceration in the United States: Exploring Causes and Consequences. Committee on Causes and Consequences of High Rates of Incarceration. Travis, J., Western, B., Redburn, S. (eds.). The National Academies Press, Washington, DC (2014).
O’Brien, R.M.: The age-period-cohort conundrum as two fundamental problems. Qual. Quant. 45, 1429–1444 (2011)
O’Brien, R.M.: Age–Period–Cohort Models: Approaches with Aggregate Data. Chapman-Hall, New York (2015)
O’Brien, R.M.: Model misspecification when eliminating a factor in age-period-cohort multiple classification models. Sociol. Methodol. 46, 358–372 (2016)
O’Brien, R.M.: Homicide arrest rate trends in the United States: the contributions of periods and cohorts (1965–2015). J. Quant. Criminol. 35, 211–236 (2019)
O’Brien, R.M.: Using old results to produce new solutions in age-period-cohort multiple classification models. Qual. Quant. 54, 111–124 (2020)
O’Brien, R.M., Stockard, J.: Can cohort replacement explain changes in the relationship between age and homicide offending? J. Quant. Criminol. 25, 79–101 (2009)
O’Brien, R.M., Stockard, J., Isaacson, L.: The enduring effects of cohort characteristics on age-specific homicide rates: 1960–1995. Am. J. Sociol. 104, 1061–1095 (1999)
Parker, K.F., Mancik, A., Stansfield, R.: American crime drops: investigating the breaks, dips and drops in temporal homicide. Soc. Sci. Res. 64, 154–170 (2017)
Quetelet, A.: Adolphe Quetelet's Research On the Propensity for Crime at Different Ages. Anderson Publishing, Cincinnati, Ohio (1984 [1831]).
Rodgers, W.L.: Estimable functions of age, period, and cohort effects. Am. Sociol. Rev. 47, 774–787 (1982)
Sprague, T.B.: Explanation of a new formula for interpolation. Journal of the Institute of Actuaries. 22, 270–285 (1880)
StataCorp.: Stata Statistical Software: Release 16. StataCorp LLC, College Station¸TX (2019).
Steffensmeier, D., Allan, E., Harer, M.D., Streifel, C.: Age and the distribution of crime. Am. J. Sociol. 94, 803–831 (1989)
Steffensmeier, D., Streifel, C., Shihadeh, E.S.: Cohort size and arrest rates over the life course: The Easterlin hypothesis reconsidered. Am. Sociol. Rev. 57, 306–314 (1992)
Utz, R.: Obesity in America, 1960–2000: is it an age, period, or cohort phenomenon? Population Association of America, Philadelphia, PA: (Annual Meeting 2005).
Wickramaratne, P.J., Weissman, M.M., Leaf, P.J., Holford, T.R.: Age, period and cohort effects on the risk of major depression: results from five United States communities. J. Clin. Epidemiol. 42, 333–343 (1989)
Yang, Y., Land, K.C.: Age-Period-Cohort Analysis: New Models, Methods, and Empirical Applications. Chapman Hall, New York (2013)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
O’Brien, R.M. Setting bounds on age, period, and cohort effects using observed data. Qual Quant 57, 2841–2857 (2023). https://doi.org/10.1007/s11135-022-01503-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11135-022-01503-9