Causal Inference and Observational Research: The Utility of Twins

被引:410
作者
McGue, Matt [1 ,2 ]
Osler, Merete [2 ,3 ]
Christensen, Kaare [4 ,5 ]
机构
[1] Univ Minnesota, Dept Psychol, Minneapolis, MN 55455 USA
[2] Univ So Denmark, Inst Publ Hlth, Odense, Denmark
[3] Glostrup Cty Hosp, Res Ctr Prevent & Hlth, Glostrup, Denmark
[4] Univ So Denmark, Danish Twin Registry, Odense, Denmark
[5] Univ So Denmark, Danish Aging Res Ctr, Inst Publ Hlth, Odense, Denmark
关键词
discordant-twin design; causal inference; twin research; lifestyle influences in aging; MODERATE ALCOHOL-CONSUMPTION; PHYSICAL-ACTIVITY; DEPRESSIVE SYMPTOMS; ALZHEIMERS-DISEASE; COGNITIVE FUNCTION; LIFE-STYLE; FOLLOW-UP; DRUG-USE; RISK; MORTALITY;
D O I
10.1177/1745691610383511
中图分类号
B84 [心理学];
学科分类号
04 ; 0402 ;
摘要
Valid causal inference is central to progress in theoretical and applied psychology. Although the randomized experiment is widely considered the gold standard for determining whether a given exposure increases the likelihood of some specified outcome, experiments are not always feasible and in some cases can result in biased estimates of causal effects. Alternatively, standard observational approaches are limited by the possibility of confounding, reverse causation, and the nonrandom distribution of exposure (i.e., selection). We describe the counterfactual model of causation and apply it to the challenges of causal inference in observational research, with a particular focus on aging. We argue that the study of twin pairs discordant on exposure, and in particular discordant monozygotic twins, provides a useful analog to the idealized counterfactual design. A review of discordant-twin studies in aging reveals that they are consistent with, but do not unambiguously establish, a causal effect of lifestyle factors on important late-life outcomes. Nonetheless, the existing studies are few in number and have clear limitations that have not always been considered in interpreting their results. It is concluded that twin researchers could make greater use of the discordant-twin design as one approach to strengthen causal inferences in observational research.
引用
收藏
页码:546 / 556
页数:11
相关论文
共 85 条
[1]   Complexity of work and risk of Alzheimer's disease: A population-based study of Swedish twins [J].
Andel, R ;
Crowe, M ;
Pedersen, NL ;
Mortimer, J ;
Crimmins, E ;
Johansson, B ;
Gatz, M .
JOURNALS OF GERONTOLOGY SERIES B-PSYCHOLOGICAL SCIENCES AND SOCIAL SCIENCES, 2005, 60 (05) :P251-P258
[2]   Physical exercise at midlife and risk of dementia three decades later: A population-based study of Swedish twins [J].
Andel, Ross ;
Crowe, Michael ;
Pedersen, Nancy L. ;
Fratiglioni, Laura ;
Johansson, Boo ;
Gatz, Margaret .
JOURNALS OF GERONTOLOGY SERIES A-BIOLOGICAL SCIENCES AND MEDICAL SCIENCES, 2008, 63 (01) :62-66
[3]   STRUCTURAL EQUATION MODELING IN PRACTICE - A REVIEW AND RECOMMENDED 2-STEP APPROACH [J].
ANDERSON, JC ;
GERBING, DW .
PSYCHOLOGICAL BULLETIN, 1988, 103 (03) :411-423
[4]   The health benefits of moderate consumption called into question [J].
Andreasson, Sven .
ADDICTION RESEARCH & THEORY, 2007, 15 (01) :3-5
[5]  
[Anonymous], 2002, EXPT QUASIEXPERIMENT
[6]  
[Anonymous], 1990, STAT SCI
[7]  
ASHENFELTER O, 1994, AM ECON REV, V84, P1157
[8]   Separation of individual-level and cluster-level covariate effects in regression analysis of correlated data [J].
Begg, MD ;
Parides, MK .
STATISTICS IN MEDICINE, 2003, 22 (16) :2591-2602
[9]  
Bentler P.M., 1985, THEORY IMPLEMENTATIO
[10]   Socioeconomic status and social support following illicit drug use: Causal pathways or common liability? [J].
Bergen, Sarah E. ;
Gardner, Charles O. ;
Aggen, Steven H. ;
Kendler, Kenneth S. .
TWIN RESEARCH AND HUMAN GENETICS, 2008, 11 (03) :266-274