Federico Belotti

Spatial Panel Data Models Using Stata

xsmle is a new command for spatial analysis using Stata. We consider the quasi-maximum likelihood estimation of a wide set of both fixed- and random- effects spatial models for balanced panel data. Of special note is that xsmle allows to handle unbalanced panels thanks to its full compatibility with the mi suite of commands, to use spatial weight matrices in the form of both Stata matrices and spmat objects, to compute direct, indirect and total effects according to the procedure outlined in LeSage and Pace (2009), and to exploit a wide range of postestimation features, extending to the panel data case the predictors proposed by Kelejian and Prucha (2007). This paper describes the command and all its functionalities using both simulated and real data.

Consistent Estimation of the 'True' Fixed-Effects Stochastic Frontier Model

The classic stochastic frontier panel data models provide no mechanism to disentangle individual time invariant unobserved heterogeneity from inefficiency. Greene (2005a,b) proposed a fixed-effects model specification that distinguishes these two latent components and allows a time varying inefficiency distribution. However, the maximum likelihood estimator proposed by Greene leads to biased inefficiency estimates due to the incidental parameters problem. In this paper, we propose two alternative estimation procedures that, by relying on a first difference data transformation, achieve consistency for n goes to infinity with fixed T. Evidence from Monte Carlo simulations shows good finite sample performances of both approaches even in presence of small samples.

Cost-Containment Policies and Hospital Efficiency: Evidence from a Panel of Italian Hospitals

The main objective of this article is to evaluate to which extent the set of national and regional cost control policies implemented in recent years in Italy have affected hospital activity. Our contribution is mainly empirical as we focus our attention on the impact that policies like hospital mergers and regional bailout plans had on inefficiency. We use a rich longitudinal sample of Italian hospitals over the period 1999-2007 and perform a Bayesian analysis of the random-effects stochastic frontier model proposed by Greene (2005), allowing for a one-step estimation of both production frontier parameters and inefficiency effects. Results show that hospital inefficiency has changed over time and that part of this change could be ascribed to the mentioned policies.

Disentangling True Determinants of Drug Therapy Effectiveness: A Double Fixed Effects Approach

Understanding the role that drug adherence has on health outcomes in everyday clinical practice is central for the policy maker. This is particularly true when patients suffer from asymptomatic chronic conditions (i.e., hypertension, hypercholesterolemia, and diabetes). By exploiting a unique longitudinal dataset at patient and physician level in Italy, we show that patients and physicians (observed and unobserved) characteristics play an important role in determining health status, at least as important as drug adherence. Most importantly, we show that physicians can have an important role in determining patient health status, far beyond the standard determinants of health status that clinical and health economic literature have discussed and analysed.

Against All Odds: The Contribution of the Healthcare Sector to Productivity. Evidence from Italy and UK from 2004 to 2011

We assess the productivity growth of the English and Italian healthcare systems over the period from 2004 to 2011. The English (NHS) and the Italian (SSN) healthcare systems share many similar features, facilitating comparison: basic founding principles, financing, organization, management, and size. We measure productivity growth as the rate of change in outputs over the rate of change in inputs. We find that the overall NHS productivity growth index increased by 10% over the whole period, at an average of 1.39% per year, while SSN productivity increased overall by 5%, at an average of 0.73% per year. Differential growth reflects different policy objectives. In England, the NHS focused on increasing activity, reducing waiting times and improving quality. Italy focused more on cost containment and rationalized provision, in the hope that this would reduce unjustified and inappropriate provision of services.

Consistent Inference in Fixed-Effects Stochastic Frontier Models

The classical stochastic frontier panel data models provide no mechanism for disentangling individual time-invariant unobserved heterogeneity from inefficiency. Greene (2005a, b) proposed the ‘true’ fixed-effects specification, which distinguishes these two latent components while allowing for time-variant inefficiency. However, due to the incidental parameters problem, the maximum likelihood estimator proposed by Greene may lead to biased variance estimates. We propose two alternative estimation procedures that, by relying on a first-difference data transformation, achieve consistency when n goes to infinity with fixed T. Furthermore, we extend the approach of Chen et al. (2014) by providing a computationally feasible solution for estimating models in which inefficiency can be heteroskedastic and may follow a first-order autoregressive process. We investigate the finite sample behavior of the proposed estimators through a set of Monte Carlo experiments. Our results show good finite sample properties, especially in small samples. We illustrate the usefulness of the new approach by applying it to the technical efficiency of hospitals.

The future of Long Term Care in Europe. An investigation using a dynamic microsimulation model

In this paper we investigate the evolution of public European LTC systems in the forthcoming decades, using the Europe Future Elderly Model (EuFEM), a dynamic microsimulation model which projects the health and socio-economic characteristics of the 50+ population of ten European countries, augmented with the explicit modelling of the eligibility rules of 5 countries. The use of SHARE data allows to have a better understanding of the trends in the demand for LTC differentiated by age groups, gender, and other demographic and social characteristics in order to better assess the distributional effects. We estimate the future potential coverage (or gap of coverage) of each national/regional public home-care system, and then disentangle the differences between countries in a population and a regulation effects. Our analysis offers new insights on how would the demand for LTC evolve over time, what would the distributional effects of different LTC policies be if no action is taken, and what could be potential impact of alternative care policies.

The “Double Expansion of Morbidity” Hypothesis: Evidence from Italy

The last few decades have been characterized by an increase in the number of years lived in bad health, lending support to the “Expansion of Morbidity” hypothesis. In this paper we propose the “Double Expansion of Morbidity” (DEM) hypothesis, arguing that not only life expectancy gains have been transformed into years lived in “bad health”, but also, due to an earlier onset of chronic diseases, the number of years spent in “good health” is actually reduced. Limited to the Italian case, we present and discuss a set of empirical evidence confirming the DEM hypothesis. In particular, we find that from 2004 to 2014 the average number of years spent with chronic conditions in Italy increased by 7.2 years 2.3 years of which are due to an increase in life expectancy and 4.9 years due to a reduction in the age of onset of chronic conditions. Compared with 2004, in 2014, this phenomenon generated extra public health expenditure of nearly 6.3 billion euros. We discuss the policy implications of these findings.

Modeling Public Health Care Expenditure Using Patient Level Data: Empirical Evidence from Italy

In this work we present some results obtained with a unique database of patient level data collected through GPs. The availability of such data opens new scenarios and paradigms for the planning and management of the health care system and for policy impact evaluation studies. The dataset, representative of the Italian population, contains detailed information on prescribed drugs, laboratory tests, outpatient visits and hospitalizations of more than 2 millions patients, managed by 900 GPs overtime. This pool of registers has produced a stock of information on about 25 millions of medical diagnosis, 100 millions of laboratory and diagnostic tests, 10 millions of blood pressure measurements and 50 millions of drug prescriptions. Using this novel dataset we analyze the expenditures of the Italian NHS over time, across age and geographical areas for the period from 2004 to 2011.