AF Measure Analysis Issues III: Decompositions by dimension and regional and ethnic groups, and policy implications
 
|
|
Watch the video (includes video guide)
Alkire, S., Foster, J.E., 2011. Counting and Multidimensional Poverty Measurement. Journal of Public Economics (Link to OPHI website)
Apart from the lectures introduction to decomposition this note is useful Technical Guide on the Alkire Foster method (from Summer School)
MPI: Alkire, S., Roche, J. M., and Suman, S. (2011). Sub-national Disparities and Inter-temporal Evolution of Multidimensional Poverty across Developing Countries. OPHI Working Paper 32a
Bangladesh: Alkire, S. and Roche, J.M. (2011). Beyond Headcount: Measures that Reflect the Breadth and Components of Child Poverty. OPHI Working Paper 45
Time Decompositions of the Alkire Foster Method
Guide to the video
Part 1: The Calculation of Decomposition and Contribution
00:00 Introduction population subgroup decomposition in the AF method.
06:21 Shows subgroup decomposition calculations.
08:33 Dimensional decompositions, or the censored headcount for each dimensions. M1 and M2 have the same decomposition properties and calculations are similar.
17:10 Contribution of dimensional subgroup.
19:38 Using unequal weights when calculating the contribution of each dimension
Part 2: Empirical Examples of MPI and Child Poverty in Bangladesh
25:14 Empirical analyses of subgroup and dimensional decomposition and contributions.
27:00 Example of global MPI and the contributions of intensity and incidence to the overall adjusted headcount (see Alkire and Santos (2010))
29:24 Decomposition of MPI, the example of India and Kenya; large variations
33:08 Global MPI, dimensional composition at the regional level
35:17 Global MPI, the composition of poverty, three country examples
38:21 Global MPI, the composition of poverty, same level different composition, a way to understand poverty.
39:27 Global MPI, poverty structures, typologies of poverty
41:13 Example of Child Poverty in Bangladesh using a different measure than the global MPI (Alkire and Roche (2011)). Apart from decompositions and dimensional contributions, the presentation goes through time comparisons, k cut-off robustness, dominance analysis, regional changes over time, k cut-off sensitivity at a regional level.
53:25 Changes over time in the censored headcount, the average deprivation score and the adjusted headcount – observing these changes could influence poverty (see lecture on Time Decomposition of the Alkire Foster method)
This paper based exercise introduces the decomposability of measures in the Alkire Foster family, both by subgroup and indicators. You will learn how to compute the subgroup MPI and each indicator’s censored headcounts, as well as the contribution from each indicator and subgroup to the overall adjusted headcount
Exercise sheet
Audio clip: Adobe Flash Player (version 9 or above) is required to play this audio clip. Download the latest version here. You also need to have JavaScript enabled in your browser.
For supplementary reading on this topic view
