Triangular systems for symmetric binary variables
Nanny Wermuth, Giovanni M. Marchetti, and D.R. Cox
Source: Electron. J. Statist. Volume 3 (2009), 932-955.
Abstract
We introduce and study distributions of sets of binary variables that are symmetric, that is each has equally probable levels. The joint distribution of these special types of binary variables, if generated by a recursive process of linear main effects is essentially parametrized in terms of marginal correlations. This contrasts with the log-linear formulation of joint probabilities in which parameters measure conditional associations given all remaining variables. The new formulation permits useful comparisons of different types of graphical Markov models and leads to a close approximation of Gaussian orthant probabilities.
Primary Subjects: 62E10
Secondary Subjects: 62H17, 62H20
Keywords: Graphical Markov models; linear in probability models; log-linear models; recursive generating processes
Full-text: Open access
Links and Identifiers
Permanent link to this document: http://projecteuclid.org/euclid.ejs/1253195940
Digital Object Identifier: doi:10.1214/09-EJS439
References
Bahadur, R.R. (1961). A representation of the distribution of joint responses to n dichotomous items. In: Studies in item analysis and prediction. H. Solomon (ed.) 158–176. Stanford University Press.
Bartlett, M.S. (1935). Contingency table interactions. Suppl. J. Roy. Statist. Soc., 2, 248–252.
Bergsma, W., Croon, M. & Hagenaars, J.A. (2009) Marginal Models. Springer, New York.
Birch, M.W. (1963). Maximum likelihood in three-way contingency tables. J. Roy. Statist. Soc. B 25, 220–233.
Cheng, M.C. (1969). The orthant probabilities of four Gaussian variates. Ann. Math. Statist. 40, 152–161.
Cochran, W.G. (1938). The omission or addition of an independent variate in multiple linear regression. Suppl. J. Roy. Statist. Soc. 5, 171–176.
Cox, D.R. (2006). Principles of Statistical Inference. Cambridge University Press.
Cox, D.R. (2007). On a generalization of a result of W.G. Cochran. Biometrika, 94, 400–410.
Cox, D.R. & Wermuth, N. (1994). A note on the quadratic exponential binary distribution. Biometrika, 81, 403–408.
Cox, D.R. & Wermuth, N. (1996). Multivariate Dependencies – Models, Analysis and Interpretation. London: Chapman & Hall.
Cox, D.R. & Wermuth, N. (2003). A general condition for avoiding effect reversal after marginalization. J. Roy. Statist. Soc. B, 65, 937–941.
Cramèr, H. (1946). Mathematical methods of statistics. Princeton University Press.
Darroch, J.N. & Ratcliff, D. (1972) Generalized iterative scaling for log-linear models. Ann. Math. Statist. , 43, 1470–1480.
Darroch, J.N., Lauritzen, S.L. & Speed, T.P. (1980). Markov fields and log-linear models for contingency tables. Ann. Statist. 8, 522–539.
Dempster, A. P. (1972). Covariance selection. Biometrics 28, 157–175.
Drton, M. (2009). Discrete chain graph models. Bernoulli. to appear.
Fienberg, S. (2007). The analysis of cross-classified categorical data. Springer (2007), New York.
Frydenberg, M. (1990). The chain graph Markov property. Scan. J. Statist. 17, 333–353.
Glonek, G.J.N. & McCullagh, P. (1995). Multivariate logistic models. J. Roy. Statist. Soc. B, 57, 533–546.
Goldberger, A.S. (1964). Econometric Theory. Wiley, New York.
Good, I. J. (1958). The interaction algorithm and practical Fourier analysis. J. Roy. Statist. Soc. B 20, 361–372.
Goodman, L.A. (1973). The analysis of multidimensional contingency tables when some variables are posterior to others: a modified path analysis approach. Biometrika, 60, 179–192.
Green, P.J., Hjort, N. & Richardson, S. (eds.) (2003). Models for highly structured stochastic systems. Oxford University Press.
Holland, P.W. & Rosenbaum, P. (1986). Conditional association and unidimensionality in monotone latent variable models. Ann. Statist., 14, 1523–1543.
Johnson, N.L., Kotz, S. & Balakrishnan, N. (1995). Distributions in statistics. Continuous univariate distributions, Vol. 2, 2nd edn., Wiley, New York.
Lancaster, H.O. (1969). The Chi-Squared Distribution. Wiley, New York.
Lazarsfeld, P.F. (1961). The algebra of dichotomous systems. In: Studies in item analysis and prediction. H. Solomon (ed.) 111-157. Stanford University Press.
Ma, Z.M., Xie, X.C. & Geng, Z. (2006). Collapsibility of distribution dependence. J. Roy. Statist. Soc. B, 68, 127–133.
Marchetti G.M. & Lupparelli, M. (2009). Chain graph models of multivariate regression type for categorical data. Submitted.
Marchetti, G.M. & Wermuth, N. (2009). Matrix representations and independencies in directed acyclic graphs. Ann. Statist., 37, 961–978.
McFadden, J.A. (1955). Urn models of correlation and a comparison with the multivariate normal integral. Ann. Math. Statist. 26, 478–489.
McFadden, J.A. (1956). An approximation for the symmetric quadrivariate normal integral. Biometrika 43, 206–207.
Moran, P.A.P. (1956). The numerical evaluation of a class of integrals. Proc. Cambridge Philos. Soc., Statist. 52, 230–233.
Pearl, J. & Wermuth, N. (1994). When can association graphs admit a causal interpretation? In: Models and Data, Artificial Intelligence and Statistics IV. 205–214. P. Cheeseman and W. Oldford (eds.). New York: Springer.
Schläfli, L. (1858). On the multiple integral. Quart. J. Math., 2, 269–301, 3 54-68, 97–108.
Sheppard, W.F. (1898). On the geometrical treatment of the ’normal curve’ of statistics, with special reference to correlation and to the theory of error. Proc. Roy. Soc. London, 62, 171–173.
Streitberg, B. (1990). Lancaster interactions revisited. Ann. Statist., 18, 1878–1885.
Streitberg, B. (1999). Exploring interactions in high-dimensional tables: a bootstrap alternative to log-linear models. Ann. Statist., 27, 405–413.
Wermuth, N. (1976). Analogies between multiplicative models for contingency tables and covariance selection. Biometrics, 32, 95–108.
Wermuth, N. (1980) Linear recursive equations, covariance selection, and path analysis. J. Amer. Statist. Assoc. 75 963–972.
Wermuth, N. (1998). Pairwise independence. Encyclopedia of Biostatistics. P. Armitage and T. Colton (eds). New York: Wiley, 3244-3246.
Wermuth, N. & Cox, D.R. (1998). On association models defined over independence graphs. Bernoulli, 4, 477–495.
Wermuth, N. & Cox, D.R. (2004). Joint response graphs and separation induced by triangular systems. J. Roy. Statist. Soc. B, 66, 687–717.
Wermuth, N., Cox, D.R. & Marchetti, G.M. (2006). Covariance chains. Bernoulli, 12, 841–862.
Wermuth, N., Wiedenbeck, M. & Cox, D.R. (2006). Partial inversion for linear systems and partial closure of independence graphs. BIT, Numerical Mathematics, 46, 883–901.
Wright, S. (1934). The method of path coefficients. Ann. Math. Statist., 5, 161–215.
Xie, X.C., Ma, Z.M. & Geng, Z. (2008). Some association measures and their collapsibility. Stat. Sinica. 1165–1183.
Yates, F. (1937). The Design and Analysis of Factorial Experiments. Harpenden: Imperial Bureau of Soil Science.
Zellner, A. (1962). An efficient method of estimating seemingly unrelated regressions and tests for aggregation bias. J. Amer. Statist. Assoc. 57, 348–368.
Electronic Journal of Statistics
