Poverty Comparisons With Absolute Poverty Lines Estimated From Survey Data

Abstract

The objective of measuring poverty is usually to make comparisons over time or between two or more groups. Common statistical inference methods are used to determine whether an apparent difference in measured poverty is statistically significant. Studies of relative poverty have long recognized that when the poverty line is calculated from sample survey data, both the variance of the poverty line and the variance of the welfare metric contribute to the variance of the poverty estimate. In contrast, studies using absolute poverty lines have ignored the poverty line variance, even when the poverty lines are estimated from sample survey data. Including the poverty line variance could either reduce or increase the precision of poverty estimates, depending on the specific characteristics of the data. This paper presents a general procedure for estimating the standard error of poverty measures when the poverty line is estimated from survey data. Based on bootstrap methods, the approach can be used for a wide range of poverty measures and methods for estimating poverty lines. The method is applied to recent household survey data from Mozambique. When the sampling variance of the poverty line is taken into account, the estimated standard errors of Foster-Greer-Thorbecke and Watts poverty measures increase by 15-30 percent at the national level, with considerable variability at lower levels of aggregation. Copyright 2007 The Authors; Journal compilation International Association for Research in Income and Wealth 2007.

Consistent poverty comparisons and inference

“…Given this complexity, analytical solutions to estimate Var( z ), and therefore Var( P ), are intractable. Simler and Arndt (2007) present a general approach to estimating Var( P ) using bootstrapping (Efron, 1979; Efron and Tibshirani, 1993). The primary assumption of the bootstrap procedure is that the distribution of the observed sample is a good approximation of the distribution of the population.…”

“…The third column shows postbootstrap processing, which is simply the calculation of the standard deviations of the poverty measures over the bootstrap replications. Further details on the bootstrap procedure can be found in Simler and Arndt (2007).…”

“…The focus in this section is on the intuition behind the need for methodological improvement and the logic of the proposed changes. Separate papers describe the application of each new method in detail (Arndt and Simler, 2005; Simler and Arndt, 2007).…”

Using a community-based definition of poverty for targeting poor households for premium subsidies in the context of a community health insurance in Burkina Faso

“…In most developing countries, poverty issues are mainly addressed with regard to the implementation of national strategic plans for poverty alleviation [5-9]. In the 1970s, definitions of poverty focused mainly on income [10-14] and were often based on a comparison of individuals’ income and consumption with some defined thresholds, below which individuals were considered poor [15,16]. New layers of complexity in the definition of poverty were added in the 1980s, including some non-monetary aspects [17-21].…”

Poverty, Informality and the Optimal General Income Tax Policy

“…Absolute poverty measures consider exclusively the well-being of those who are defined as poor, thereby suggesting that only the condition of the poor and their deprivation is important, not the overall society (Ravallion (1994); Simler and Arndt (2007)). On the other hand, relative poverty measures define the segment of the population that is poor in comparison with the consumption (or income) of the general population.…”