Applied Health Economics

Andrew M. Jones, Nigel Rice, Teresa Bago d'Uva, Silvia Balia

• Publisher: Routledge
• Year: 2013
• ISBN:
  9781136239816
• Edition: 2
• Topic: Commerce
• Subtopic: Commerce Général

The first edition of Applied Health Economics did an expert job of showing how the availability of large scale data sets and the rapid advancement of advanced econometric techniques can help health economists and health professionals make sense of information better than ever before.

This second edition has been revised and updated throughout and includes a new chapter on the description and modelling of individual health care costs, thus broadening the book's readership to those working on risk adjustment and health technology appraisal. The text also fully reflects the very latest advances in the health economics field and the key journal literature.

Large-scale survey datasets, in particular complex survey designs such as panel data, provide a rich source of information for health economists. They offer the scope to control for individual heterogeneity and to model the dynamics of individual behaviour. However, the measures of outcome used in health economics are often qualitative or categorical. These create special problems for estimating econometric models. The dramatic growth in computing power over recent years has been accompanied by the development of methods that help to solve these problems. The purpose of this book is to provide a practical guide to the skills required to put these techniques into practice.

Practical applications of the methods are illustrated using data on health from the British Health and Lifestyle Survey (HALS), the British Household Panel Survey (BHPS), the European Community Household Panel (ECHP), the US Medical Expenditure Panel Survey (MEPS) and Survey of Health, Ageing and Retirement in Europe (SHARE). There is a strong emphasis on applied work, illustrating the use of relevant computer software with code provided for Stata. Familiarity with the basic syntax and structure of Stata is assumed. The Stata code and extracts from the statistical output are embedded directly in the main text and explained at regular intervals.

The book is built around empirical case studies, rather than general theory, and the emphasis is on learning by example. It presents a detailed dissection of methods and results of some recent research papers written by the authors and their colleagues. Relevant methods are presented alongside the Stata code that can be used to implement them and the empirical results are discussed at each stage.

This text brings together the theory and application of health economics and econometrics, and will be a valuable reference for applied economists and students of health economics and applied econometrics.

Part I
Describing and summarising data

1
Data and survey design

Synopsis

This chapter introduces each of the datasets that are used in the practical case studies throughout the book. It discusses some important features of survey design and focuses on the variables that are of particular interest for health economists.

1.1 The Health and Lifestyle Survey

The sample

The Health and Lifestyle Survey (HALS) is an example of a health interview survey. Aspects of the survey are used in Chapters 5 and 6. The HALS was designed as a representative survey of adults in Great Britain (see Cox et al., 1987, 1993). The population surveyed was individuals aged 18 and over living in private households. In principle, each individual should have an equal probability of being selected for the survey. This allows the data to be used to make inferences about the underlying population. HALS was designed originally as a cross-section survey with one measurement for each individual. It was carried out between the autumn of 1984 and the summer of 1985, and information was collected in three stages:

• a one-hour face-to-face interview, which collected information on experience and attitudes towards to health and lifestyle along with general socioeconomic information;
• a nurse visit to collect physiological measures and indicators of cognitive function, such as memory and reasoning;
• a self-completion postal questionnaire to measure psychiatric health and personality.

The HALS is an example of a clustered random sample. The intention was to build a representative random sample of this population but without the excessive costs of collecting a true random sample. Addresses were randomly selected from electoral registers using a three-stage design. First 198 electoral constituencies were selected with the probability of selection proportional to the population of each constituency. Then two electoral wards were selected for each constituency and, finally, 30 addresses per ward. Then individuals were randomly selected from households. This selection procedure gave a target of 12,672 interviews.

Some of the addresses from the electoral register proved to be inappropriate as they were in use as holiday homes, business premises or were derelict. This number was relatively small and only 418 addresses were excluded, leaving a total of 12,254 individuals to be interviewed. The response rate fell more dramatically when it came to success in completing these interviews: 9,003 interviews were completed. This is a response rate of 73.5 per cent. In other words, there was a 1 in 4 chance that an interview was not completed.

The overall response rate is fairly typical of general population surveys. Understandably, the response rate declines for the subsequent nurse visit and postal questionnaire. The overall response rate for those individuals who completed all three stages of the survey is only 53.7 per cent. To get a sense of how well the sample represents the population, it can be compared to external data sources. The most comprehensive of these is the population census which is collected every ten years. Comparison with the 1981 census suggests that the final sample under-represents those with lower incomes and lower levels of education. In general, it is important to bear this kind of unit non-response in mind when doing analysis with any survey data.

The longitudinal follow-up

The HALS was originally intended to be a one-off cross-section survey. However, HALS also provides an example of a longitudinal, or panel, dataset. In 1991/92, seven years on from the original survey, the HALS was repeated. This provides an example of repeated measurements, where the same individuals are re-interviewed. Panel data provide a powerful enhancement of cross-section surveys that allows a deeper analysis of heterogeneity across individuals and of changes in individual behaviour over time. However, because of the need to revisit and interview individuals repeatedly, the problems of unit non-response tend to be amplified. Of the original 9,003 individuals who were interviewed at the time of the first HALS survey, 808 (9 per cent) had died by the time of the second survey, 1,347 (14.9 per cent) could not be traced and 222 were traced but could not be inter viewed, either because they had moved overseas or they had moved to geographic areas that were out of the scope of the survey. These cases are examples of attrition – individuals who drop out of a longitudinal survey.

The deaths data

HALS provides an example of a cross-section survey (HALS1) and panel data (HALS1&2). Also it provides a longitudinal follow-up of subsequent mortality and cancer cases among the original respondents. These deaths data can be used for survival analysis. Most of the 9,003 individuals interviewed in HALS1 have been flagged on the NHS Central Register. In June 2005, the fifth deaths revision and the second cancer revision were completed. The flagging process was quite lengthy because it required several checks in order to be sure that the flagging registrations were related to the person previously interviewed. About 98 per cent of the sample had been flagged. Deaths account for some 27 per cent of the original sample. This information is used in Chapter 6 for a duration analysis of mortality rates.

1.2 The British Household Panel Survey

The sample

The British Household Panel Survey (BHPS) is a longitudinal survey of private households in Great Britain that provides rich information on socio-demographic and health variables. While HALS has only two waves of panel data, the BHPS has repeated annual measurements from 1991 to the present and is an ongoing survey, which has become part of the larger understanding society study. This provides more scope for longitudinal analysis. The BHPS is used in Chapters 2, and 7 to 10.

The BHPS was designed as an annual survey of each adult (16+) member of a nationally representative sample of more that 5,000 households, with a total of approximately 10,000 individual interviews. The first wave of the survey was conducted between 1 September 1990 and 30 April 1991. The initial selection of households for inclusion in the survey was performed using a two-stage clustered systematic sampling procedure designed to give each address an approximately equal probability of selection (Taylor et al., 1998). The same individuals are re-interviewed in successive waves and, if they split off from their original households are also re-interviewed along with all adult members of their new households.

Measures of health

One measure of health outcomes that is available in the BHPS, and many other general surveys, is self-assessed health (SAH), defined by a response to: ‘Please think back over the last 12 months about how your health has been. Compared to people of your own age, would you say that your health has on the whole been excellent/good...

Table of contents

• Cover
• Title
• Copyright
• Contents
• List of illustrations
• Preface
• Acknowledgements
• Introduction
• PART I Describing and summarising data
• PART II Categorical data
• PART III Duration data
• PART IV Panel data
• PART V Health care data
• Bibliography
• Index