Using NonNormal SEM to Resolve the ACDE Model in the Classical Twin Design
 Koken Ozaki,
 Hideki Toyoda,
 Norikazu Iwama,
 Saori Kubo,
 Juko Ando
 … show all 5 hide
Abstract
One of the biggest problems in classical twin studies is that it cannot estimate additive genetic (A), nonadditive genetic (D), shared environmental (C), and nonshared environmental (E) effects, simultaneously, because the model, referred to as the ACDE model, has negative degrees of freedom when using Structural Equation Modeling (SEM). Therefore, instead of the ACDE model, the ACE model or the ADE model is actually used. However, using the ACE or ADE models almost always leads to biased estimates. In the present paper, the univariate ACDE model is developed using nonnormal Structural Equation Modeling (nnSEM). In SEM, (1st and) 2ndorder moments, namely, (means and) covariances are used as information. However, nnSEM uses higherorder moments as well as (1st and) 2ndorder moments. nnSEM has a number of advantages over SEM. One of which is that nnSEM can specify models that cannot be specified using SEM because of the negative degrees of freedom. Simulation studies have shown that the proposed method can decrease the biases. There are other factors that have possible effects on phenotypes, such as higherorder epistasis. Since the proposed method cannot estimate these effects, further research on developing a more exhaustive model is needed.
 Bentler, PM (1983) Some contributions to efficient statistics in structural models: specification and estimation of moment structures. Psychometrika 48: pp. 493517 CrossRef
 Bollen, KA (1989) Structural equations with latent variables. Wiley, New York
 Browne MW (1982) Covariance structures. In: Hawkins DM (ed) Topics in applied multivariate analysis. Cambridge University Press, Cambridge, pp. 72–141
 Browne, MW (1984) Asymptotically distributionfree methods for the analysis of covariance structures. Br J Math Stat Psychol 9: pp. 665672
 Comon, P (1994) Independent component analysis—a new concept?. Signal Process 36: pp. 287314 CrossRef
 Coventry, WL, Keller, MC (2005) Estimating the extent of parameter bias in the classical twin design: a comparison of parameter estimates from extended twinfamily and classical twin designs. Twin Res Hum Genet 8: pp. 214223 CrossRef
 Eaves, JL, Erkanli, A (2003) Markov chain Monte Carlo approaches to analysis of genetic and environment components of human developmental change and G × E interaction. Behav Genet 33: pp. 279299 CrossRef
 Eaves, LJ, Last, KA, Martin, NG, Jinks, JL (1977) A progressive approach to nonadditivity and genotype–environmental covariance in the analysis of human differences. Br J Math Stat Psychol 30: pp. 142
 Eaves, LJ, Last, KA, Young, PA, Martin, NG (1978) Modelfitting approaches to the analysis of human behavior. Heredity 41: pp. 249320 CrossRef
 Eaves, LJ, Martin, NG, Eysenck, SBG (1978) An application of the analysis of covariance structures to the psychogenetical study of impulsiveness. Br J Math Stat Psychol 30: pp. 185197
 Eaves, LJ, Heath, AC, Martin, NG (1984) A note on the generalized effects of assortative mating. Behav Genet 14: pp. 371376 CrossRef
 Fisher, RA (1918) The correlation between relatives on the supposition of Mendelian inheritance. Trans R Soc Edinb 52: pp. 399433
 Grayson, DA (1989) Twins reared together: minimizing shared environmental effects. Behav Genet 19: pp. 593604 CrossRef
 Hoyer, PO, Shimizu, S, Kerminen, A, Palviainen, M (2008) Estimation of causal effects using linear nongaussian causal models with hidden variables. Int J Approx Reason 49: pp. 362378 CrossRef
 Ihaka R, Gentleman R (1996) R: a language for data analysis and graphics. J Comput Graph Stat 5:299–314. http://www.Rproject.org
 Kano Y, Shimizu S (2003) Causal inference using nonnormality. In: Proceedings of international symposium on science of modeling—the 30th Anniversary of the Information Criterion (AIC), pp 261–270
 Kathryn, ABB, Kirby, DD, Thalia, E, Jennifer, JF, Jim, S, Plomin, R (2004) A genetic analysis of individual differences in dissociative behaviors in childhood. J Child Psychol Psychiatry 45: pp. 522532 CrossRef
 Keller, MC, Coventry, WL (2005) Quantifying and addressing parameter indeterminancy in the classical twin design. Twin Res Hum Genet 8: pp. 201213 CrossRef
 Keller, MC, Coventry, WL, Heath, AC, Martin, NG (2005) Widespread evidence for nonadditive genetic variation in Cloninger’s and Eysenck’s personality dimensions using a twin plus sibling design. Behav Genet 35: pp. 707721 CrossRef
 Loelin, JC, DeFries, JC (1987) Genotype–environment correlation and IQ. Behav Genet 17: pp. 263277 CrossRef
 Mooijaart, A (1985) Factor analysis for nonnormal variables. Psychometrika 50: pp. 323342 CrossRef
 Neale, MC, Carldon, LR (1992) Methodology for genetic studies of twins and families. Kluwer, Dordrecht
 Neale, MC, Boker, SM, Xie, G, Maes, HH (2006) Mx: statistical modeling. Virginia Commonwealth University, Department of Psychiatry, Richmond, VA
 Ozaki, K, Ando, J (2009) Direction of causation between shared and nonshared environmental factors. Behav Genet 39: pp. 321336 CrossRef
 Plomin, R, DeFries, JC, Loehlin, JC (1977) Genotype–environment interaction and correlation in the analysis of human behavior. Psychol Bull 84: pp. 310322 CrossRef
 Purcell, S (2002) Variance components models for gene–environment interaction in twin analysis. Twin Res 5: pp. 554571 CrossRef
 Shimizu, S, Kano, Y (2008) Use of nonnormality in structural equation modeling: application to direction of causation. J Stat Plan Inference 138: pp. 34833491 CrossRef
 Shimizu, S, Hoyer, PO, Hyvärinen, A, Kerminen, A (2006) A linear nongaussian acyclic model for causal discovery. J Mach Learn Res 7: pp. 20032030
 Toyoda, H (2007) Theory of structural equation modeling. Asakurashoten, Tokyo
 Truett, KR, Eaves, LJ, Walters, EE, Heath, AC, Hewitt, JK, Meyer, JM, Siberg, J, Neale, MC, Martin, NG, Kendler, KS (1994) A model system for analysis of family resemblance in extended kinships of twins. Behav Genet 24: pp. 3549 CrossRef
 Title
 Using NonNormal SEM to Resolve the ACDE Model in the Classical Twin Design
 Open Access
 Available under Open Access This content is freely available online to anyone, anywhere at any time.
 Journal

Behavior Genetics
Volume 41, Issue 2 , pp 329339
 Cover Date
 20110301
 DOI
 10.1007/s1051901093865
 Print ISSN
 00018244
 Online ISSN
 15733297
 Publisher
 Springer US
 Additional Links
 Topics
 Keywords

 Biases in estimators
 Higherorder moments
 Model identification
 nnSEM
 Nonnormality
 Univariate ACDE model
 Authors

 Koken Ozaki ^{(1)}
 Hideki Toyoda ^{(2)}
 Norikazu Iwama ^{(2)} ^{(3)}
 Saori Kubo ^{(2)}
 Juko Ando ^{(4)}
 Author Affiliations

 1. Research Organization of Information and Systems, The Institute of Statistical Mathematics, 103 Midoricho, Tachikawa, Tokyo, 1908562, Japan
 2. Waseda University, Tokyo, Japan
 3. Japan Society for the Promotion of Science, Tokyo, Japan
 4. Keio University, Tokyo, Japan