Ron et al. (1998) introduced a rich family of models for discrete longitudinal data called acyclic probabilistic finite automata. These may be represented as directed graphs that embody context-specific conditional independence relations. Here, the approach is developed from a statistical perspective. It is shown here that likelihood ratio tests may be constructed using standard contingency table methods, a model selection procedure that minimizes a penalized likelihood criterion is described, and a way to extend the models to incorporate covariates is proposed. The methods are applied to a small-scale dataset. Finally, it is shown that the models generalize certain subclasses of conventional undirected and directed graphical models.
BishopYMFienbergSEHollandPW (2007) Discrete multivariate analysis: Theory and practice. New York: Springer.
6.
BoutilierCFriedmanNGoldszmidtMKollerD (1996) Context-specific independence in Bayesian networks. Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence, 115–23. Los Altos: Morgan Kaufmann Publishers Inc.
7.
BrowningBBrowningS (2007) Efficient multilocus association testing for whole genome association studies using localized haplotype clustering. Genetic Epidemiology, 31, 365–75.
8.
CawleySLPachterL (2003) HMM sampling and applications to gene finding and alternative splicing. Bioinformatics, 19, ii36–ii41.
DigglePHeagertyPLiangK-YZegerS (2013) Analysis of Longitudinal Data. Oxford, UK: Oxford University Press.
12.
DupontPAmengualJ-C (2000) Smoothing probabilistic automata: An error-correcting approach. In Oliveira A, ed., Grammatical inference: Algorithms and applications, vol. 1891 of Lecture Notes in Computer Science, 255–56. Springer:Berlin/Heidelberg. http://dx.doi.org/10.1007/978-3-540-45257-75
13.
EdwardsD (2000) Introduction to graphical modelling. New York: Springer.
14.
EkholmASmithPWMcDonaldJW (1995) Marginal regression analysis of a multivariate binary response. Biometrika, 82, 847–54.
15.
EriksenPS (1999) Context specific interaction models. Technical Report R-99-2018, Department of Mathematical Sciences, Aalborg University.
16.
EriksenPS (2005) Decomposable log-linear models. Technical report, Department of Mathematical Sciences, Aalborg University.
17.
FitzmauriceGMLairdNM (1993) A likelihood-based method for analysing longitudinal binary responses. Biometrika, 80, 141–51.
18.
FreemanGSmithJQ (2011) Bayesian MAP model selection of chain event graphs. Journal of Multivariate Analysis, 102, 1152–65.
19.
HaraHSeiTTakemuraA (2012) Hierarchical subspace models for contingency tables. Journal of Multivariate Analysis, 103, 19–34.
20.
HøjsgaardSEdwardsDLauritzenS (2012) Graphical models with R. New York: Springer.
21.
HøjsgaardS (2003) Split models for contingency tables. Computational statistics and data analysis, 42, 621–45.
22.
HøjsgaardS (2004) Statistical inference in context specific interaction models for contingency tables. Scandinavian Journal of Statistics, 31, 143–58.
23.
JaegerM (2004) Probabilistic decision graphs Combining verification and AI techniques for probabilistic inference. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 12, 19–42.
RiccomagnoESmithJQ (2009). The geometry of causal probability trees that are algebraically constrained. Optimal Design and Related Areas in Optimization and Statistics, pp 133–54. New York: Springer.
28.
RonDSingerYTishbyN (1998) On the learnability and usage of acyclic finite automata. Journal of Computer and System Sciences, 56, 133–52.
29.
SchwarzG (1978) Estimating the dimension of a model. The annals of statistics, 6, 461–64.
30.
SilanderTLeongT-Y (2013) A dynamic programming algorithm for learning chain event graphs. Discovery Science, pp201–16. Berlin: Springer.
ThwaitesPSmithJQCowellRG (2008) Propagation using chain event graphs. Proceedings of 24th Conference on Uncertainty in Artificial Intelligence, pp. 554–61. http://uai.sis.pitt.edu/papers/08/p546-thwaites.pdf.
VidalEThollardFDeLaHigueraCCasacubertaFCarrascoR (2005a) Probabilistic finite-state machines-part i. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 27, 1013–25.
37.
VidalEThollardFDeLaHigueraCCasacubertaFCarrascoR (2005b) Probabilistic finite-state machines-part iiPattern Analysis and Machine Intelligence, IEEE Transactions on, 27, 1026–39.
38.
WareJDockeryDSpiroASpeizerFFerrisB Jr (1984) Passive smoking, gas cooking, and respiratory health of children living in six cities. Am. Rev. Respir. Dis., 129, 366–74.
