Showing papers by "Francesco Bartolucci published in 2019"
TL;DR: A shared-parameter approach for jointly modeling longitudinal and survival data allows for time-varying random effects that affect both the longitudinal and the survival processes.
Abstract: A shared-parameter approach for jointly modeling longitudinal and survival data is proposed. With respect to available approaches, it allows for time-varying random effects that affect both the longitudinal and the survival processes. The distribution of these random effects is modeled according to a continuous-time hidden Markov chain so that transitions may occur at any time point. For maximum likelihood estimation, we propose an algorithm based on a discretization of time until censoring in an arbitrary number of time windows. The observed information matrix is used to obtain standard errors. We illustrate the approach by simulation, even with respect to the effect of the number of time windows on the precision of the estimates, and by an application to data about patients suffering from mildly dilated cardiomyopathy.
17 citations
Posted Content•
TL;DR: In this paper, a causal inference approach is proposed to assess the effectiveness of remittances on the poverty level of recipient households, based on a longitudinal survey spanning the period 2009-2014 and where response variables are indicators of deprivation.
Abstract: To assess the effectiveness of remittances on the poverty level of recipient households, we propose a causal inference approach that may be applied with longitudinal data and time-varying treatments. The method relies on the integration of a propensity score based technique, the inverse propensity weighting, with a general Latent Markov (LM) framework. It is particularly useful when the interest is in an individual characteristic that is not directly observable and the analysis is focused on: (i) clustering individuals in a finite number of classes according to this latent characteristic and (ii) modelling its evolution across time depending on the received treatment. Parameter estimation is based on a two-step procedure in which individual weights are computed for each time period based on predetermined covariates and a weighted version of the standard LM model likelihood based on such weights is maximised by means of an expectation-maximisation algorithm. Finite-sample properties of the estimator are studied by simulation. The application is focused on the effect of remittances on the poverty status of Ugandan households, based on a longitudinal survey spanning the period 2009-2014 and where response variables are indicators of deprivation.
7 citations
TL;DR: This version of the self-administered, 36-item, Persian version of WHODAS 2.0 has acceptable reliability and validity in psychiatric patients, but a reformulation of problematic items and further validation tests would be required to produce a robust measurement instrument.
Abstract: The purpose of this study was to validate a self-administered 36-item Persian (Farsi) version of the World Health Organization (WHO) Disability Assessment Schedule II (now referred to as WHODAS 2.0) for assessment of psychiatric patients’ perceptions of their functioning and disability. WHODAS 2.0 items were analyzed using two approaches. Reliability, consistency, and factor structure were assessed using Cronbach’s α and factor analysis, and item response theory (IRT) was used to determine how well the WHODAS 2.0 items fitted the Rasch paradigm. Data were collected from 614 psychiatric outpatients in Tehran. The mean overall disability score for the sample was 37.57. The scale had excellent reliability (Cronbach’s α = 0.94). The IRT-based analysis showed that overall the set of items had a poor fit to the Rasch paradigm; the exceptions were items belonging to domains D1 (cognition), D2 (mobility), and D5 (life activities). There were several problematic items associated with dimensions D3 (self-ca...
5 citations
Posted Content•
TL;DR: In this article, a multiple step procedure was proposed to estimate the average partial effects in fixed-effects panel logit models with bias of O(T −2 ) as n → ∞ and performs well in finite sample, even when n is much larger than T.
Abstract: We propose a multiple step procedure to estimate Average Partial Effects (APE) in fixed-effects panel logit models. Because the incidental parameters problem plagues the APEs via both the inconsistent estimates of the slope and individual parameters, we reduce the bias by evaluating the APEs at a fixed-T consistent estimator for the slope coefficients and at a bias corrected estimator for the unobserved heterogeneity. The proposed estimator has bias of order O(T −2 ) as n → ∞ and performs well in finite sample, even when n is much larger than T . We provide a real data application based on the labor supply of married women.
5 citations
TL;DR: In this paper, a latent class mixture growth model with concomitant variables was proposed to study the time profiles of international remittances sent by first-generation migrants in Germany from 1996 to 2012.
Abstract: We propose a latent class mixture growth model with concomitant variables to study the time profiles of international remittances sent by first‐generation migrants in Germany from 1996 to 2012. The latent class approach enables us to identify homogeneous subgroups of migrants associated with different trajectories for their remitting behaviour, which can be interpreted in the light of the theoretical economic background. In addition, the inclusion of concomitant covariates allows us to uncover whether the assignment of migrants to a specific subgroup can be ascribed to their observable characteristics (e.g. their intention to return home), as conjectured by the theoretical models. The model proposed is easily estimated through an expectation–maximization algorithm. Results show that migrants can be clustered in three groups, two of which reflect the evolution of remittances predicted by economic theory.
5 citations
Posted Content•
TL;DR: In this article, the authors analyse the changing attitudes towards immigration in EU host countries in the last few years (2010-2016) on the basis of the European Social Survey data.
Abstract: We analyse the changing attitudes towards immigration in EU host countries
in the last few years (2010-2016) on the basis of the European Social Survey
data. These data are collected by the administration of a questionnaire made of
items concerning different aspects related to the immigration phenomenon. For this analysis we rely on a class of item response theory models that allow for: (i) multidimensionality; (ii) discreteness of the latent trait distribution; (iii) time-constant and time-varying covariates; and (iv) sample weights. Through these models we find latent classes of Europeans with similar levels of immigration acceptance, we study the effect of different socio-economic covariates on the probability of belonging to these classes, and we assess the item characteristics. In this way we show which countries tend to be more or less positive towards immigration and the temporal dynamics of the phenomenon under study.
2 citations
Posted Content•
01 Jan 2019
TL;DR: In this paper, a causal inference approach that may be applied with longitudinal data and time-varying treatments is proposed to assess the effectiveness of remittances on the poverty level of recipient households, based on the integration of a propensity score based technique, the inverse propensity weighting, with a general Latent Markov (LM) framework.
Abstract: To assess the effectiveness of remittances on the poverty level of recipient households, we propose a causal inference approach that may be applied with longitudinal data and time-varying treatments The method relies on the integration of a propensity score based technique, the inverse propensity weighting, with a general Latent Markov (LM) framework It is particularly useful when the interest is in an individual characteristic that is not directly observable and the analysis is focused on: (i) clustering individuals in a finite number of classes according to this latent characteristic and (ii) modelling its evolution across time depending on the received treatment Parameter estimation is based on a two-step procedure in which individual weights are computed for each time period based on predetermined covariates and a weighted version of the standard LM model likelihood based on such weights is maximised by means of an expectation-maximisation algorithm Finite-sample properties of the estimator are studied by simulation The application is focused on the effect of remittances on the poverty status of Ugandan households, based on a longitudinal survey spanning the period 2009-2014 and where response variables are indicators of deprivation
1 citations