We examine the sensitivity of estimates and inequality indices to extreme values, in the sense of their robustness properties and of their statistical performance. We establish that these measures are very sensitive to the properties of the income distribution. Estimation and inference can be...

Using a simple axiomatic structure we characterise two classes ofinequality indices - absolute and relative - that take into account "envy"in the income distribution. The concept of envy incorporated hereconcerns the distance of each person's income from his or herimmediately richer neighbour....

The 'prediction approach' proposed by Dearden, Machin and Reed (DMR) consists in (1) regressing the observed incomes of the child and parent families on separate sets of predetermined variables, and (2) regressing the child's predicted income on that of the parents. Conceptually, this estimator...

In this paper we examine the concept of "vulnerability" within the context of incomemobility of the poor. We test for the dynamics of vulnerable households in the UKusing Waves 1 - 12 of the British Household Panel Study and find that, of threedifferent types of risks that we test for,...

Temkin (1986,1993) sets out a philosophical basis for the analysis of income inequality that provides an important alternative to the mainstream welfarist approach. We show that the Temkin principles can be characterised by a parsimonious axiomatic structure and we use this structure to derive a...

We examine the implications of three similar criteria that are commonly used in welfare economics and the analysis of inequality and poverty - income dominance, monotonicity and the Pareto principle - within the context of income-distribution comparisons. We show that whilst there is a simple...

Building on previous studies on perceptions of inequality, welfare and risk we investigate the structure of individuals' rankings of uncertain prospects in terms of risk and their relationship to individual preferences. We examine three interlinked propositions that are fundamental to the...

According to standard theory founded on Harsanyi (1953, 1955) a social welfarefunction can be appropriately based on the individual's approach to choice underuncertainty. We investigate whether people really do rank distributions according tothe same principles irrespective of whether the...

Distributional dominance criteria are commonly applied to draw welfare inferences about comparisons, but conclusions drawn from empirical implementations of dominance criteria may be influenced by data contamination. We examine a non-parametric approach to refining Lorenz-type comparisons and...

Inequality measures are powerful tools of applied welfare analysis. However, to use the tools effectively one has to take into account the characteristics of the data with which one usually has to work. These raise a number of common statistical problems which are addressed here for both...