A multilevel latent Markov model for the evaluation of nursing homes' performance

Montanari, Giorgio E. and Doretti, Marco and Bartolucci, Francesco (2017): A multilevel latent Markov model for the evaluation of nursing homes' performance.

Abstract

The periodic evaluation of health care services is a primary concern for many institutions. In this work, we focus on nursing home services with the aim to produce a ranking of a set of nursing homes based on their capability to improve - or at least to keep unchanged - the health status of the patients they host. As the overall health status is not directly observable, latent variable models represent a suitable approach. Moreover, given the longitudinal and multilevel structure of the available data, we rely on a multilevel latent Markov model where patients and nursing homes are the first and the second level units, respectively. The model includes individual covariates to account for the patient case-mix and the impact of nursing home membership is modeled through a pair of correlated random effects affecting the initial distribution and the transition probabilities between different levels of health status. Through the prediction of these random effects we obtain a ranking of the nursing homes. Furthermore, the proposed model is designed to address non-ignorable dropout, which typically occurs in these contexts because some elderly patients die before completing the survey. We apply our model to the Long Term Care Facilities dataset, a longitudinal dataset gathered from Regione Umbria (Italy). Our results are robust to the sensitivity parameter involved (the number of latent states) and show that differences in nursing homes' performances are statistically significant.

The authors certify that they have the right to deposit this contribution in its published format with MPRA.

• Item Type: MPRA Paper
• Language: English
• Keywords: clustered data, health status evaluation, non-ingorable dropout, random effects
• Subjects: C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C13 - Estimation: General

References

Altman, R. M. (2007). Mixed hidden Markov models: an extension of the hidden Markov model to the longitudinal data setting. Journal of the American Statistical Association 102 (477), 201-210.

Bacci, S., S. Pandolfi, and F. Pennoni (2014). A comparison of some criteria for states selection in the latent Markov model for longitudinal data. Advances in Data Analysis and Classification 8 (2), 125-145.

Bartolucci, F., A. Farcomeni, and F. Pennoni (2013). Latent Markov Models for Longitudinal Data. Statistics in the Social and Behavioural Sciences. Chapman & Hall/CRC.

Bartolucci, F. and M. Lupparelli (2016). Pairwise likelihood inference for nested hidden Markov chain models for multilevel longitudinal data. Journal of the American Statistical Association 111 (513), 216-228.

Bartolucci, F., M. Lupparelli, and G. E. Montanari (2009). Latent Markov model for longitudinal binary data: an application to the performance evaluation of nursing homes. The Annals of Applied Statistics 3 (2), 611-636.

Bartolucci, F., G. E. Montanari, and S. Pandolfi (2015). Three-step estimation of latent Markov models with covariates. Computational Statistics & Data Analysis 83, 287-301.

Bartolucci, F., F. Pennoni, and G. Vittadini (2011). Assessment of school performance through a multilevel latent Markov Rasch model. Journal of Educational and Behavioral Statistics 36 (4), 491 522.

Baum, L. E., T. Petrie, G. Soules, and N. Weiss (1970). A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. The Annals of Mathematical Statistics 41, 164-171.

Dempster, A. P., N. M. Laird, and D. B. Rubin (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B 39 (1), 1-38.

Fisher, R. A. (1915). Frequency distribution of the values of the correlation coefficient in samples from an indefinitely large population. Biometrika 10 (4), 507-521.

Fletcher, R. (1987). Practical methods of optimization (2nd ed.). New York: John Wiley & Sons.

Gnaldi, M., S. Bacci, and F. Bartolucci (2016). A multilevel finite mixture item response model to cluster examinees and schools. Advances in Data Analysis and Classification 10 (1), 53-70.

Goldstein, H. and M. J. R. Healy (1995). The graphical presentation of a collection of means. Journal of the Royal Statistical Society, Series A 158 (1), 175-177.

Goodman, L. A. (1974). Exploratory latent structure analysis using both identifiable and unidentifiable models. Biometrika 61 (2), 215-231.

Gray, A. (2009). Population aging and health care expenditure. China Labor Economics 1 (10), 105-114.

Henry, K. and B. Muthén (2010). Multilevel latent class analysis: An application of adolescent smoking typologies with individual and contextual predictors. Structural Equation Modeling 17 (2), 193-215.

Hirdes, J. P., G. Ljunggren, J. N. Morris, D. H. Frijters, H. Finne Soveri, L. Gray, M. Bjorkgren, and R. Gilgen (2008). Reliability of the interRAI suite of assessment instruments: a 12-country study of an integrated health information system. BMC Health Services Research 8 (1), 277.

Kim, H., Y.-I. Jung, M. Sung, J.-Y. Lee, J.-Y. Yoon, and J.-L. Yoon (2015). Reliability of the interRAI Long Term Care Facilities (LTCF) and interRAI Home Care (HC). Geriatrics & Gerontology International 15 (2), 220-228.

Kitagawa, E. M. (1964). Standardized comparisons in population research. Demography 1 (1), 296-315.

Koukounari, A., I. Moustaki, N. C. Grassly, I. M. Blake, M.-G. Basanez, M. Gambhir, D. C. Mabey, R. L. Bailey, M. J. Burton, A. W. Solomon, et al. (2013). Using a nonparametric multilevel latent Markov model to evaluate diagnostics for trachoma. American Journal of Epidemiology 177 (9), 913-922.

Little, R. J. and D. B. Rubin (2002). Statistical Analysis with Missing Data (2-nd ed.). Wiley.

Makai, P., W. B. Brouwer, M. A. Koopmanschap, E. A. Stolk, and A. P. Nieboer (2014). Quality of life instruments for economic evaluations in health and social care for older people: a systematic review. Social Science & Medicine 102, 83-93.

Maruotti, A. (2011). Mixed hidden Markov models for longitudinal data: an overview. International Statistical Review 79 (3), 427-454.

Maruotti, A. and R. Rocci (2012). A mixed nonhomogeneous hidden Markov model for categorical data, with application to alcohol consumption. Statistics in Medicine 31 (9), 871-886.

Montanari, G. E. and S. Pandolfi (2016). Evaluation of health care services through a latent Markov model with covariates. In SIS 2016 – 48-th Scientific Meeting of the Italian Statistical Society.

Montanari, G. E., M. G. Ranalli, and P. Eusebi (2010). Multilevel latent class models for evaluation of long-term care facilities. In Data Analysis and Classification, pp. 249-256. Springer.

Oehlert, G. W. (1992). A note on the delta method. The American Statistician 46 (1), 27-29.

Press, W. H., B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling (1989). Numerical recipes, Volume 3. Cambridge University Press, Cambridge.

Raffa, J. D. and J. A. Dubin (2015). Multivariate longitudinal data analysis with mixed effects hidden Markov models. Biometrics 71 (3), 821-831.

Schwarz, G. (1978). Estimating the dimension of a model. The Annals of Statistics 6 (2), 461-464.

Stephens, M. (2000). Dealing with label switching in mixture models. Journal of the Royal Statistical Society, Series B 62 (4), 795-809.

Vermunt, J. (2003). Multilevel latent class models. Sociological Methodology 33 (1), 213-239.

Vermunt, J. K., R. Langeheine, and U. Bockenholt (1999). Discrete-time discrete-state latent Markov models with time-constant and time-varying covariates. Journal of Educational and Behavioral Statistics 24 (2), 179-207.

Welch, L. R. (2003). Hidden Markov models and the Baum-Welch algorithm. IEEE Information Theory Society Newsletter 53, 1-13.

White, C. (2007). Health care spending growth: how different is the United States from the rest of the OECD? Health Affairs 26 (1), 154-161.

Wiggins, L. M. (1973). Panel analysis: Latent probability models for attitude and behavior processes. Jossey-Bass.