Chapter 3: How to Interpret ADePT Results
mean ratio, computed as (90th percentile UPM – 10th percentile LPM) / 90th percentile UPM. The larger the 90/10 partial mean ratio, the larger is the gap between these two partial means. A lower partial mean is the average per capita expenditure of all people below a specific percentile cutoff. An upper partial mean is the mean per capita expenditure above a specific percentile. A partial mean ratio captures inequality between a lower partial mean and an upper partial mean. In table 3.5, we reported a distribution’s different quantile PCEs. For example, the quantile PCE at the 10th percentile of Georgia in 2003 was GEL 44.8, meaning that 10 percent of the Georgian population lives with per capita expenditure less than GEL 44.8. However, that does not tell us the average income of these people. Similarly, 10 percent of the Georgian population has per capita expenditure more than GEL 229.8, Georgia’s quantile PCE at the 90th percentile, but we do not know exactly how rich this group is. Partial means are useful for determining these values, and partial mean ratios tell us the difference in the average per capita expenditures between a poorer and a richer group. It is evident from table 3.13 that the average per capita expenditure of the poorest 20 percent of people in Ajara is only GEL 36.5 in 2003 [6,B], whereas the average income of the richest 20 percent of the population is GEL 222.4 [6,C]. The corresponding 80/20 partial mean ratio is 83.6 [6,F], meaning that the gap between the two partial means is 83.6 percent of the 80th upper partial mean. Stated another way, the mean per capita expenditure of the population’s richest 20 percent is 100 / (100 – 83.6) = 6.1 times larger than the mean per capita expenditure of the population’s poorest 20 percent. Likewise, in Shida Kartli, the mean per capita expenditure of the population’s richest 20 percent (GEL 263.3 [3,C]) is 7.1 times larger than the mean per capita expenditure of the population’s poorest 20 percent (GEL 37.1 [3,B]) in 2003. The corresponding 80/20 partial mean ratio is 85.9 [3,F]. Lessons for Policy Makers A larger inequality in terms of the quantile ratio does not necessarily translate into higher inequality in terms of the partial mean ratio. In table 3.12, we found that the 80/20 quantile ratio for Imereti (65.0) was larger than that of Ajara (63.7), but in table 3.13 Ajara’s 80/20 partial mean ratio (83.6 [3,F]) is slightly larger than Imereti’s (82.5 [9,F]).
179