Joseph Hirschberg

Cluster analysis for measuring welfare and quality of life across countries

Abstract The dream of a multiattribute approach to empirical welfare analysis is coming closer to reality because of significant advances in both theoretical and measurement areas. In this paper we propose statistical cluster analysis methods to explore different ways and levels for clustering of 23 diverse attributes such as political rights, civil liberties, life expectancy, literacy, real domestic product, etc. Several key attribute categories are identified which should be very helpful in dealing with the problem of ‘double counting’ in multidimensional analyses. Aggregate measures of welfare are computed for many countries, and the sensitivity of several key inequality measures with respect to clustering and degrees of aggregation is studied.

Fiscal stress and the production of public safety: A distance function approach

Abstract Faced with increasing crime rates, but nonincreasing budgets, local governments are seeking cost saving means of providing public safety. This paper investigates a bureaucracys response to fiscal stress as well as its ability to efficiently substitute civilian for uniformed personnel. Exploiting duality theory, a distance function is used to model technology, retrieve information concerning substitutability and shadow prices of personnel, and test for cost minimization. Morishima elasticities are adopted to allow for asymmetry in substitution between types of personnel. It is found that the more adverse the public safety environment and budgetary condition, the more efficiently resources are allocated.

Occupational segregation in the multidimensional case Decomposition and tests of significance

A new multidimensional version of the G-segregation index is developed and applied to the study of occupational segregation. U.S. Current Population Survey data are used to measure the difference in occupational segregation between races as well as the change between time periods. Decomposition of the difference (change) into ‘occupation mix’ and ‘gender composition’ components indicates the contribution of each factor. Because these inequality measures are computed from sample data, distributional information required to test hypotheses is lacking. Two computer-intensive methods for estimating the distributional properties are demonstrated. The approximate randomization and bootstrap methodologies are used to test for statistically significant differences in segregation between races and for changes over time. In addition, the components of the decomposition are examined for statistical significance.

Bootstrapping Confidence Intervals for Linear Programming Efficiency Scores: With an Illustration Using Italian Banking Data

This article suggests a method for introducing a stochastic element into Farrell measures of technical efficiency as calculated via linear programming techniques. Specifically, a bootstrap of the original efficiency scores is performed to derive confidence intervals and a measure of bias for the scores. The bootstrap generates these measures of statistical precision for the “nonstochastic” efficiency measures by using computational power to derive empirical distributions for the efficiency measures.

Systematic Influences on Teaching Evaluations: The Case for Caution

In this paper, we examine eight years of Quality of Teaching (QOT) responses from an Economics Department in an Australian University. This is done to determine what factors, besides the instructor, have an impact on the raw average student evaluation scores. Most of the previous research on student ratings has been conducted in the US. One significant difference between US and Australian tertiary education is that, on average, the number of foreign undergraduate students in Australia is ten times the number in US institutions. We find that cultural background significantly affects student evaluations. Other factors that have an influence on the average QOT score include: year level; enrolment size; the quantitative nature of the subject; the gender of the student; fee-paying status by gender; course of study; the differences between the course mark and previous marks; the quality of workbooks; the quality of textbooks; and the QOT score relative to those in other subjects taught at the same time. In addition, average QOT scores for instructors who have taught in a mix of subjects are similar to those based on scores adjusted to account for subject and student characteristics.

An analysis of bilateral intra-industry trade in the food processing sector

This paper analyses determinants of intra-industry trade in food processing for a 30-country sample over the period 1964–85. Previous studies have tested the hypothesis that imperfect competition is a major determinant of intra-industry trade (IIT) in the durable goods manufacturing sectors. This study is distinguised from the earlier studies of IIT by; the examination of the processed food sector (SIC=20), the use of a panel data set for 22 years and 30 countries available at the four-digit SIC level, the use of purchasing power parity measures of GDP, and the use of a weighted tobit model with fixed effects to account for the censored cross-section time-series nature of the date. The results indicate that ITI in food processing is a positive function of a countrys GDP per capita and equality if GDP per capita between countries. In addition, it is also found that such trade is strongly influenced by distance between trading partners, membership in customs unions and free trade blocs, and also exchange r...

Alcohol consumption, smoking and wages

The good health of an individual is a combination of uncontrollable factors that includes genetics and random events and controllable factors through the regulation of activities such as smoking and drinking. Since the work of Grossman in the 1970s, a significant relationship between health and earnings has been predicted. In this present paper the 1995 Australian National Health Survey is used to examine simultaneously the effects of drinking and smoking on wages. To model the interaction of smoking with alcohol consumption separate models are fitted for smokers and nonsmokers. These models account for potential selectivity bias resulting from the decision to smoke, and endogeneity arising from a potential causal relationship between earnings and alcohol consumption.

Computer knowledge and earnings: evidence for Australia

This paper uses data on wage and salary workers in Australia in 1993 to examine the relation between computer knowledge and earnings. A unique feature of the data set that is used is detailed information on the types and levels of computer skills possessed by individual workers. The main objectives of the study are to contribute to understanding the magnitude and sources of the relation between computer knowledge and earnings. Similar to existing research it is found that there is a large and significant return to computer knowledge, but that the magnitude of the return is substantially reduced in regressions that include detailed occupation controls. Using the detailed information on workers’ computer skills the main finding is that earnings are significantly positively related to the number of types of skills and average level of skills possessed by a worker.

Inferences for the Extremum of Quadratic Regression Models

Quadratic functions are often used in regression to infer the existence of an extremum in a relationship although tests of the location of the extremum are rarely performed. We investigate the construction of the following confidence intervals: Delta, Fieller, estimated first derivative, bootstrapping, Bayesian and likelihood ratio. We propose interpretations for the unbounded intervals that may be generated by some of these methods. The coverage of the confidence intervals is assessed by Monte Carlo; the Delta and studentized bootstrap can perform quite poorly. Of all the methods, the first derivative method is easiest to implement.

Alcohol Consumption and Human Capital: A Retrospective Study of the Literature

Grossman proposed an individuals health can be viewed as one aspect of their human capital. Following this line of thought a number of recent papers have reported a positive impact of alcohol consumption on earnings. The rationale for the existence of such a relationship is the positive impact of alcohol on physical and mental health. We conduct a meta-analysis to determine whether such factors as: the estimation technique, the presence of ex-drinkers in the sample, possible sample selection bias and publication bias may all contribute to these findings. An additional suggestion for the positive relationship between alcohol and wages is the presence of a common set of personality traits that determines drinking behaviour and also leads to higher earnings. We examine this relationship by reviewing the literature that investigates if the personality influencing aspects of alcohol consumption influences measures of human capital. We also survey the significant body of research that has examined how alcohol consumption has been found to influence educational outcomes and the work force participation of problem drinkers.