Log-linear models for contingency tables are a key tool for the study of categorical inequalities in sociology. However, the conventional approach to model selection and specification suffers from at least two limitations: reliance on oftentimes equivocal diagnostics yielded by fit statistics, and the inability to identify patterns of association not covered by model candidates. In this article, we propose an application of Lasso regularization that addresses the aforementioned limitations. We evaluate our method through a Monte Carlo experiment and an empirical study of educational assortative mating in Chile, 1990–2015. Results demonstrate that our approach has the virtue, relative to ad hoc specification searches, of offering a principled statistical criterion to inductively select a model. Importantly, we show that in situations where conventional fit statistics provide conflicting diagnostics, our Lasso-based approach is consistent in its model choice, yielding solutions that are both predictive and parsimonious.
AgrestiA.2002. Categorical Data Analysis. New Jersey: Wiley-Interscience.
2.
AtkinsonA. C.1978. “Posterior Probabilities for Choosing a Regression Model.” Biometrika65:39–48.
3.
BelloniA.ChernozhukovV.. 2013. “Least Squares after Model Selection in High-dimensional Sparse Models.” Bernoulli19:521–47.
4.
BelloniA.ChernozhukovV.HansenC.. 2013. “Inference on Treatment Effects after Selection among High-dimensional Controls.” Review of Economic Studies81:608–50.
5.
BurnhamK. P.AndersonD. R.. 2004. “Multimodel Inference: Understanding AIC and BIC in Model Selection.” Sociological Methods and Research33:261–304.
6.
ChenJ.ChenZ.. 2012. “Extended BIC for Small-n-large-p Sparse GLM.” Statistica Sinica22:555–74.
CloggC. C.1982. “Some Models for the Analysis of Association in Multiway Cross-classifications Having Ordered Categories.” Journal of the American Statistical Association77:803.
9.
DuncanO. D.1979. “How Destination Depends on Origin in the Occupational Mobility Table.” American Journal of Sociology84:793.
10.
DziakJ. J.CoffmanD. L.LanzaS. T.LiR.. 2015. “Sensitivity and Specificity of Information Criteria.” PeerJ Preprints1:1–20.
11.
EriksonR.GoldthorpeJ. H.. 1992. The Constant Flux: A Study of Class Mobility in Industrial Societies. Oxford, United Kingdom: Clarendon Press.
12.
EsteveA.McCaaR.LópezL.. 2013. “The Educational Homogamy Gap between Married and Cohabiting Couples in Latin America.” Population Research and Policy Review32:81–102.
13.
FitzmauriceG.GoldthorpeJ. H.. 1997. “Adjusting for Overdispersion in an Analysis of Comparative Social Mobility.” Sociological Methods & Research25:267–83.
14.
FriedmanJ.HastieT.TibshiraniR.. 2010. “Regularization Paths for Generalized Linear Models via Coordinate Descent.” Journal of Statistical Software33:1–22.
15.
GruskyD. B.HauserR. M.. 1984. “Comparative Social Mobility Revisited: Models of Convergence and Divergence in 16 Countries.” American Sociological Review49:19–38.
16.
GullicksonA.2005. “The Significance of Color Declines: A Re-analysis of Skin Tone Differentials in Post-civil Rights America.” Social Forces84:157–80.
17.
GullicksonA.TorcheF.. 2014. “Patterns of Racial and Educational Assortative Mating in Brazil.” Demography51:835–56.
18.
HastieT.TibshiraniR.FriedmanJ.. 2009. The Elements of Statistical Learning. New York: Springer Series in Statistics.
19.
HauserR. M.1980. “Some Exploratory Methods for Modeling Mobility Tables and Other Cross-classified Data.” Sociological Methodology11:413–58.
20.
HoutM.1983. Analyzing Mobility Tables. Beverly Hills, CA: Sage.
21.
HoutM.1984. “Occupational Mobility of Black Men: 1962 to 1973.” American Sociological Review49:308–22.
HurvichC. M.TsaiC. L.. 1989. “Regression and Time Series Model Selection in Small Samples.” Biometrika76:297–307.
24.
JaggiM.2014. “An Equivalence between the Lasso and Support Vector Machines.” Pp. 1–26 in Regularization, Optimization, Kernels, and Support Vector Machines, 1st ed., edited bySuykensJ. A.SignorettoM.ArgyriouA.. New York: Chapman and Hall/CRC.
25.
JamesG.WittenD.HastieT.TibshiraniR.. 2013. An Introduction to Statistical Learning. New York: Springer Texts in Statistics.
26.
JonssonJ.GruskyD.Di CarloM.PollakR.BrintonM.. 2009. “Microclass Mobility: Social Reproduction in Four Countries.” American Journal of Sociology114:977–1036.
27.
KuhaJ.2004. “AIC and BIC Comparisons of Assumptions and Performance.” Sociological Methods & Research33:188–229.
28.
LeebH.PötscherB. M.. 2008. “Sparse Estimators and the Oracle Property, or the Return of Hodges’ Estimator.” Journal of Econometrics142:201–11.
29.
LittleJ.RaymerJ.. 2013. “Log-linear Models of Migration Flows.” Pp. 403–19 in Tools for Demographic Estimation, edited byMoultrieT.DorringtonR.HillA.HillK.TimæusI.ZabaB.. Paris, France: International Union for the Scientific Study of Population.
30.
LuoL.HodgesJ.WinshipC.PowersD.. 2016. “The Sensitivity of the Intrinsic Estimator to Coding Schemes: Comment on Yang, Schulhofer-Wohl, Fu, and Land.” American Journal of Sociology112:881–94.
31.
MareR. D.1991. “Five Decades of Educational Assortative Mating.” American Sociological Review56:15–32.
32.
MareR. D.SchwartzC. R.. 2006. “Educational Assortative Mating and the Family Background of the Next Generation.” Sociological Theory and Methods21:253–78.
33.
McFarlandD. A.LewisK.GoldbergA.. 2016. “Sociology in the Era of Big Data: The Ascent of Forensic Social Science.” The American Sociologist47:12–35.
34.
MeierL.Van De GeerS.BühlmannP.. 2008. “The Group Lasso for Logistic Regression.” Journal of the Royal Statistical Society. Series B: Statistical Methodology70:53–71.
35.
PowersD. A.XieY.. 2000. Statistical Methods for Categorical Data Analysis. San Diego, CA: Academic Press.
36.
QianZ.1997. “Breaking the Racial Barriers: Variations in Interracial Marriage between 1980 and 1990.” Demography34:263–76.
37.
RafteryA.1995. “Bayesian Model Selection in Social Research.” Sociological Methodology25:111–69.
38.
RaymerJ.RogersA.. 2007. “Using Age and Spatial Flow Structures in the Indirect Estimation of Migration Streams.” Demography44:199–223.
39.
RaymoJ. M.XieY.. 2000. “Temporal and Regional Variation in the Strength of Educational Homogamy.” American Sociological Review65:773–81.
40.
SchwartzC.R.2010. “Earnings Inequality and the Changing Association between Spouses’ Earnings.” American Journal of Sociology115:1524–57.
41.
SchwartzC. R.2013. “Trends and Variation in Assortative Mating: Causes and Consequences.” Annual Review of Sociology39:451–70.
42.
SchwartzC. R.MareR. D.. 2005. “Trends in Educational Assortative Marriage from 1940 to 2003.” Demography42:621–46.
43.
SchwartzC. R.MareR. D.. 2012. “The Proximate Determinants of Educational Homogamy: The Effects of First Marriage, Marital Dissolution, Remarriage, and Educational Upgrading.” Demography49:629–50.
44.
SchwartzC.R.ZengZ.XieY.. 2016. “Marrying up by Marrying Down: Status Exchange between Social Origin and Education in the United States.” Sociological Science3:1003–27.
45.
TibshiraniR.1996. “Regression Shrinkage and Selection via the Lasso.” Journal of the Royal Statistical Society58:267–88.
46.
TibshiraniR.1997. “The Lasso Method for Variable Selection in the Cox Model.” Statistics in Medicine16:385–95.
47.
TillyC.1999. Durable Inequality. Berkeley: University of California Press.
48.
TorcheF.2005. “Unequal but Fluid: Social Mobility in Chile in Comparative Perspective.” American Sociological Review70:422–50.
49.
TorcheF.2010. “Educational Assortative Mating and Economic Inequality: A Comparative Analysis of Three Latin American Countries.” Demography47:481–502.
50.
TutzG.GertheissJ.. 2016. “Regularized Regression for Categorical Data.” Statistical Modelling16:161–200.
51.
WeakliemD. L.1999. “A Critique of the Bayesian Information Criterion for Model Selection.” Sociological Methods & Research27:359–97.
52.
WeakliemD. L.2004. “Introduction to the Special Issue on Model Selection.” Sociological Methods and Research33:167–87.
53.
WeedenK. A.GruskyD. B.. 2005. “The Case for a New Class Map.” American Journal of Sociology111:141–212.
54.
WeedenK. A.GruskyD. B.. 2012. “The Three Worlds of Inequality.” American Journal of Sociology117:1723–85.
55.
WillekensF.1983. “Log-linear Modelling of Spatial Interaction.” Papers in Regional Science52:187–205.
56.
WillekensF.2016. “Migration Flows: Measurement, Analysis and Modeling.” Pp. 225–41 in International Handbook of Migration and Population Distribution, edited byWhiteM. J.. Dordrecht, the Netherlands: Springer.
57.
XieY.1992. “The Log-multiplicative Layer Effect Model for Comparing Mobility Tables.” American Sociological Review57:380–95.
58.
YoungC.2009. “Model Uncertainty in Sociological Research: An Application to Religion and Economic Growth.” American Sociological Review74:380–97.
59.
YoungC.HolsteenK.. 2017. “Model Uncertainty and Robustness: A Computational Framework for Multimodel Analysis.” Sociological Methods and Research46:3–40.
60.
YuanM.LinY.. 2006. “Model Selection and Estimation in Regression with Grouped Variables.” Journal of the Royal Statistical Society68:49–67.
61.
ZouH.2006. “The Adaptive Lasso and Its Oracle Properties.” Journal of the American Statistical Association101:1418–29.
62.
ZouH.HastieT.. 2005. “Regularization and Variable Selection via the Elastic-net.” Journal of the Royal Statistical Society67:301–20.
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.
