Alternative Methods for Handling Attrition

Using data from the evaluation of the Fast Track intervention, this article illustrates three methods for handling attrition. Multiple imputation and ignorable maximum likelihood estimation produce estimates that are similar to those based on listwise-deleted data. A panel selection model that allows for selective dropout reveals that highly aggressive boys accumulate in the treatment group over time and produces a larger estimate of treatment effect. In contrast, this model produces a smaller treatment effect for girls. The article’s conclusion discusses the strengths and weaknesses of the alternative approaches and outlines ways in which researchers might improve their handling of attrition.

[1]  Craig K. Enders,et al.  A Primer on Maximum Likelihood Algorithms Available for Use With Missing Data , 2001 .

[2]  J. Schafer.  Multiple imputation: a primer , 1999, Statistical methods in medical research.

[3]  D. Hedeker,et al.  Statistical analysis of randomized trials in tobacco treatment: longitudinal designs with dichotomous outcome. , 2001, Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco.

[4]  Constantijn Panis,et al.  Panel Attrition from the Panel Study of Income Dynamics Household Income, Marital Status, and Mortality , 1998 .

[5]  R. Littell.  SAS System for Mixed Models , 1996 .

[6]  K. Bierman.  The Implementation of the Fast Track Program: An Example of a Large-Scale Prevention Science Efficacy Trial , 2002 .

[7]  C. Edelbrock,et al.  Manual for the Child: Behavior Checklist and Revised Child Behavior Profile , 1983 .

[8]  Jeffrey M. Woodbridge.  Econometric Analysis of Cross Section and Panel Data , 2002 .

[9]  M. Verbeek,et al.  Testing for selectivity bias in panel data models , 1992 .

[10]  P. Chamberlain,et al.  Parent observation and report of child symptoms. , 1987 .

[11]  K. Dodge,et al.  Initial impact of the Fast Track prevention trial for conduct problems: I. The high-risk sample. Conduct Problems Prevention Research Group. , 1999, Journal of consulting and clinical psychology.

[12]  Scott Menard,et al.  Multiple Problem Youth: Delinquency, Substance Use, and Mental Health Problems , 1991 .

[13]  J L Schafer,et al.  Multiple Imputation for Multivariate Missing-Data Problems: A Data Analyst's Perspective. , 1998, Multivariate behavioral research.

[14]  J. Schafer,et al.  Missing data: our view of the state of the art. , 2002, Psychological methods.

[15]  Steven R. Asher,et al.  Identifying Children Who Are Rejected by Their Peers. , 1986 .

[16]  T. Shakespeare,et al.  Observational Studies , 2003 .

[17]  Geert Molenberghs,et al.  Linear Mixed Models in Practice , 1997 .

[18]  K. Dodge,et al.  Dimensions and types of social status: A cross-age perspective. , 1982 .

[19]  M. Kenward.  Selection models for repeated measurements with non-random dropout: an illustration of sensitivity. , 1998, Statistics in medicine.

[20]  M. Kenward,et al.  Informative Drop‐Out in Longitudinal Data Analysis , 1994 .

[21]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[22]  J. Schafer,et al.  A comparison of inclusive and restrictive strategies in modern missing data procedures. , 2001, Psychological methods.

[23]  K. Bierman.  Predictor Variables Associated with Positive Fast Track Outcomes at the End of Third Grade , 2002, Journal of abnormal child psychology.

[24]  Larry L. Orr,et al.  Social Experiments: Evaluating Public Programs With Experimental Methods , 1998 .

[25]  Jae-Kyoung Shin,et al.  Application of NORM to the Multiple Imputation for Multivariate Missing Data , 2002 .

[26]  J. Lochman.  Screening of child behavior problems for prevention programs at school entry. , 1995 .

[27]  D. Rubin,et al.  Statistical Analysis with Missing Data. , 1989 .

[28]  D. Relles,et al.  Tools for intuition about sample selection bias and its correction , 1997 .

[29]  David E. Booth,et al.  Analysis of Incomplete Multivariate Data , 2000, Technometrics.

[30]  K. Bierman.  Evaluation of the First 3 Years of the Fast Track Prevention Trial with Children at High Risk for Adolescent Conduct Problems , 2002, Journal of abnormal child psychology.

[31]  Roderick J. A. Little,et al.  Statistical Analysis with Missing Data: Little/Statistical Analysis with Missing Data , 2002 .

[32]  T. Achenbach.  Manual for the child behavior checklist/4-18 and 1991 profile , 1991 .

[33]  J. Brian Gray,et al.  Applied Regression Including Computing and Graphics , 1999, Technometrics.

[34]  G. Molenberghs,et al.  Linear Mixed Models for Longitudinal Data , 2001 .

[35]  Nicole A. Lazar,et al.  Statistical Analysis With Missing Data , 2003, Technometrics.

[36]  Delbert S. Elliott,et al.  Explaining Delinquency and Drug Use , 1985 .

[37]  A. Scott,et al.  The Effect of Two-Stage Sampling on Ordinary Least Squares Methods , 1982 .

[38]  K. Dodge,et al.  Initial impact of the Fast Track prevention trial for conduct problems: II. Classroom effects. Conduct Problems Prevention Research Group. , 1999, Journal of consulting and clinical psychology.

[39]  J. MacKinnon,et al.  Estimation and inference in econometrics , 1994 .

[40]  John L.P. Thompson,et al.  Missing data , 2004, Amyotrophic lateral sclerosis and other motor neuron disorders : official publication of the World Federation of Neurology, Research Group on Motor Neuron Diseases.

[41]  J. Coie,et al.  A comparison of methods for defining sociometric status among children , 1991 .

[42]  Geert Molenberghs,et al.  Discussion of Diggle, P. and Kenward, M. G.: 'Informative drop-out in longitudinal data analysis' , 1994 .

[43]  D. Relles,et al.  Theory Testing in a World of Constrained Research Design , 1990 .

[44]  J. Heckman.  The Common Structure of Statistical Models of Truncation, Sample Selection and Limited Dependent Variables and a Simple Estimator for Such Models , 1976 .

[45]  E. M. Foster.  Using services data to adjust for attrition in outcome analyses: An application of multiple imputation , 2002 .

[46]  E. Foster,et al.  An Evaluator's Guide To Detecting Attrition Problems , 1996 .

[47]  Ana Ivelisse Avilés,et al.  Linear Mixed Models for Longitudinal Data , 2001, Technometrics.

[48]  J. Heckman.  Shadow prices, market wages, and labor supply , 1974 .

[49]  J. Graham.  Adding Missing-Data-Relevant Variables to FIML-Based Structural Equation Models , 2003 .