TY - CONF
T1 - Comparison of two bootstrap procedures in the case of hidden Markovian model clustering
Y1 - 2016
A1 - Taushanov, Zhivko
A1 - Berchtold, André
KW - bootstrap
KW - clustering
KW - hidden Markov model
KW - mixture models
AB - The clustering of longitudinal data sequences is considered using a latent Markovian model (HMTD) combining Gaussian distributions and covariates. The main objective is to evaluate the significance of the estimated parameters. At first, different model specifications are optimized and the one providing the best clustering in terms of BIC is selected. Two different bootstrap procedures are then applied and compared in order to investigate the significance of the parameters of this optimal solution. First, a standard bootstrap procedure is applied using the full original sample and the optimal model with multiple components (clusters) is computed at each iteration. That leads to solutions with different degrees of similarity with the optimal solution and the well-known label-switching problem may occur. An alternative procedure is proposed that consists in applying separate bootstrap procedures on each subsample defined by the optimal clustering. In this case, a single component model is estimated from each bootstrap iteration and for each cluster separately. This method also provides a confidence interval for each parameter and avoids the label-switching problem. The pros and cons of each approach are described and examples based on real data are provided.
PB - European Regional Section of the IASC
CY - Oviedo, Spain
UR - http://www.compstat2016.org/
ER -
TY - CHAP
T1 - A discussion on hidden Markov models for life course data
T2 - Proceedings of the International Conference on Sequence Analysis and Related Methods (LaCOSA II)
Y1 - 2016
A1 - Bolano, Danilo
A1 - Berchtold, André
A1 - Ritschard, Gilbert
KW - hidden Markov model
KW - Life course approach
KW - sequence analysis
AB - This is an introduction on discrete-time Hidden Markov models (HMM) for longitudinal data analysis in population and life course studies. In the Markovian perspective, life trajectories are considered as the result of a stochastic process in which the probability of occurrence of a particular state or event depends on the sequence of states observed so far. Markovian models are used to analyze the transition process between successive states. Starting from the traditional formulation of a first-order discrete-time Markov chain where each state is liked to the next one, we present the hidden Markov models where the current response is driven by a latent variable that follows a Markov process. The paper presents also a simple way of handling categorical covariates to capture the effect of external factors on the transition probabilities and existing software are briefly overviewed. Empirical illustrations using data on self reported health demonstrate the relevance of the different extensions for life course analysis.
JA - Proceedings of the International Conference on Sequence Analysis and Related Methods (LaCOSA II)
PB - NCCR LIVES
CY - Lausanne, Switzerland
UR - https://lacosa.lives-nccr.ch/sites/lacosa.lives-nccr.ch/files/lacosa2-proceedings.pdf
ER -
TY - JOUR
T1 - General framework and model building in the class of Hidden Mixture Transition Distribution models
JF - Computational Statistics & Data Analysis
Y1 - 2016
A1 - Bolano, Danilo
A1 - Berchtold, André
KW - BIC
KW - hidden Markov model
KW - mixture model
KW - mixture transition distribution model
KW - model selection
KW - panel data
AB - Modeling time series that present non-Gaussian features plays as central role in many fields, including finance, seismology, psychological, and life course studies. The Hidden Mixture Transition Distribution model is an answer to the complexity of such series. The observed heterogeneity can be induced by one or several latent factors, and each level of these factors is related to a different component of the observed process. The time series is then treated as a mixture and the relation between the components is governed by a Markovian latent transition process. This framework generalizes several specifications that appear separately in related literature. Both the expectation and the standard deviation of each component are allowed to be functions of the past of the process. The latent process can be of any order, and can be modeled using a discrete Mixture Transition Distribution. The effects of covariates at the visible and hidden levels are also investigated. One of the main difficulties lies in correctly specifying the structure of the model. Therefore, we propose a hierarchical model selection procedure that exploits the multilevel structure of our approach. Finally, we illustrate the model and the model selection procedure through a real application in social science.
VL - 93
Y1 - 01/2016
PY - 10.1016/j.csda.2014.09.011
ER -