InGrid Summer School “Reaching out to hard-to-survey groups among the poor” HIVA-KU Leuven, Leuven - Belgium, 30 May -3 June 2016 Small Area Models for Linking Deprivation to Local Areas in Italy ( draft ) Gennaro PUNZO Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 1 Depart ment of Management and Quant it at ive St udies
AIM OF THE WORK Exploring the POVERTY PATTERNS and DIFFERENTIALS across Italian NUTS3 regions for the several dimensions of life-style deprivation STEPS JOI NT ANALYSI S OF MONETARY AND SUPPLEMENTARY DEPRI VATI ON ACCORDI NG TO A MULTI DI MENSI ONAL AND FUZZY APPROACH MANI FEST AND LATENT DEPRI VATI ON MEASURES (BETTI ET AL., 2006) BORROWI NG STRENGTH ACROSS BOTH SMALL AREAS AND TI ME: RAO – YU MODEL (1992, 1994) LOOKI NG I NTO THE POTENTI AL BACKGROUND DETERMI NANTS OF THE DI FFERENT FORMS OF POVERTY Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 2 Depart ment of Management and Quant it at ive St udies
CONSIDERING DEPRIVATION IN ITS MULTIPLE DIMENSIONS... FUZZY SET approach (Zadeh, 1965) TOTALLY FUZZY and RELATIVE and, in particular, method (Cheli-Lemmi, 1995) A NEW CLASS OF MONETARY AND SUPPLEMENTARY DEPRI VATI ON MEASURES TREATI NG POVERTY AS A MONETARY DEPRIVATION MATTER OF DEGREE, REPLACI NG THE TRADI TI ONAL DI CHOTOMI ZATI ON POOR/ NON POOR Basic Life-style Secondary Life-style FUZZY MONETARY FUZZY SUPPLEMENTARY Housing Facilities PROPENSITY TO PROPENSITY TO OVERALL NON- Housing Deterioration INCOME POVERTY Environmental Problems Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 3 Depart ment of Management and Quant it at ive St udies
TO COMBINE THE TWO MAIN POVERTY DIMENSIONS... ... investigating the extent to which the several dimensions of deprivation tend to OVERLAP for households across Italian provinces TARGET VARI ABLES. . . MANI FEST DEPRI VATI ON NON- MONETARY MANI FEST DEPRI VATI ON DEPRI VATI ON I NTERSECTI ON I NCOME POVERTY between the two f uzzy sets LATENT DEPRI VATI ON UNI ON MANI FEST denotes a higher degree of deprivation LATENT DEPRI VATI ON than the LATENT one Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 4 Depart ment of Management and Quant it at ive St udies
LATENT DEPRIVATION FUZZY SET L max( FM , FS ) i i i OPERATIONS (Betti et al., 2006) MANIFEST DEPRIVATION M min( FM , FS ) i i i FM FS FM FS HOUSEHOLDS BEI NG SUBJECT TO FUZZY MANI FEST I NCOME POVERTY AND, AT THE SAME TI ME, TO LI FE- STYLE DEPRI VATI ON PROPENSITY TO BOTH MONETARY AND NON-MONETARY POVERTY HOUSEHOLDS BEI NG SUBJECT TO AT FUZZY LATENT LEAST ONE OF THE TWO PREVI OUS FORMS OF DEPRI VATI ON PROPENSITY TO EITHER MONETARY OR NON-MONETARY POVERTY Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 5 Depart ment of Management and Quant it at ive St udies
A METHODOLOGICAL VIEW In order to assess the gain, in terms of efficiency, that could be achieved by borrowing strength across BOTH SMALL AREAS AND TIME... RAO AND YU MODEL (1992, 1994) as ext ension of t he basic Fay–Her r iot (1979) Survey data Auxiliary variables ECHP sample Istat Territorial (waves 1994 – 2001) Indicators DATA SOURCES DI RECT SYNTHETI C ESTI MATES ESTI MATES Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 6 Depart ment of Management and Quant it at ive St udies
A METHODOLOGICAL VIEW ˆ ' Fay – Her r iot , 1979 x z v e with i = 1, 2, ... , m i i i i i independent and identically distributed 2 random variables with mean 0 and variance v ˆ ' Rao – Yu, 1994 x z v u e with i = 1, 2, ... , m it it i i it it and t = 1, 2, ... , T model on the θ it ’s depends on both area-specific effects ( v i ) and the area-by-time specific effects ( u it ) which are correlated across time for each i u it ’s are assumed to follow a u u e 1 common first order Auto-Regressive , 1 it i t it process (AR1) for each i UNDER THI S MODEL, THE EBLUP COMPOSI TE ESTI MATOR I S OBTAI NED Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 7 Depart ment of Management and Quant it at ive St udies
REGRESSION COEFFICIENT ESTIMATES AND STANDARD ERRORS Territorial Indicators FUZZY FUZZY (independent variables) MANIFEST LATENT Intercept - 0.0149 (0.0518) 0.2297 (0.0125) Unemployment Rate 0.2698 (0.1222) 0.4606 (0.0978) Territorial Concentration Rate of the Resident Population - 0.1007 (0.0426) – Source: Our elaborations on ECHP data, Italian Section (1994-2001), and Istat OBVI OUSLY, RAO- YU MODELS HAVE ALSO BEEN ESTI MATED FOR: FUZZY Unemployment Rate, Resident Population MONETARY per 100 inhabitants, Marriage Rate FUZZY Unemployment Rate, Public SUPPLEMENTARY Hospitalization Rate, Crime Rate HEAD COUNT Unemployment Rate, Resident Population RATIO (traditional per 100 inhabitants, Growth Enterprises poverty measure) Rate, Activity Rate Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 8 Depart ment of Management and Quant it at ive St udies
I N ORDER TO EVALUATE THE PERFORMANCE OF THE ESTI MATI ON PROCESS THROUGH SMALL AREA MODELS. . . I T ALLOWS TO TEST THE EXTENT EBLUP Composite Estimate TO WHI CH THE MODELI NG Direct Estimate MODI FI ES THE DI RECT ESTI MATES I T MEASURES THE I MPROVEMENT Standard Error EBLUP Estimate I N THE ACCURACY LEVEL OF THE Standard Error Direct Estimate ESTI MATES BY MODELI NG Summary statistics on performance outcome measures EBLUP Estimate / Direct Estimate Mean CV Min Max FUZZY MANIFEST 1.0347 0.3670 0.0910 2.0702 FUZZY LATENT 1.0261 0.2190 0.3197 1.6853 SE (EBLUP Estimate) / SE (Direct Estimate) 1 – 0.5618 = 0.4382 FUZZY MANIFEST 0.5618 0.3720 0.0337 0.8827 FUZZY LATENT 0.5227 0.3940 0.0252 0.9429 Source: Our elaborations on ECHP data, Italian Section (1994-2001), and Istat Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 9 Depart ment of Management and Quant it at ive St udies
SOME DETERMI NANTS OF I NCOME AND LI FE- STYLE DEPRI VATI ON. . . UNEMPLOYMENT RATE VS HCR UNEMPLOYMENT RATE VS FM 0.5 0.3 0.4 0.2 0.3 NORTH- 0.2 WEST 0.1 0.1 0 0 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 NORTH- EAST UNEMPLOYMENT RATE VS FS UNEMPLOYMENT RATE VS MANI FEST 0.3 0.2 CENTRO 0.2 0.1 0.1 SOUTH 0 0 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 ISLANDS UNEMPLOYMENT RATE VS LATENT ACTI VI TY RATE VS HCR 0.5 0.5 0.4 0.4 0.3 0.3 0.2 0.2 0.1 0.1 0 0 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.3 0.35 0.4 0.45 0.5 0.55 0.6 Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 10 Depart ment of Management and Quant it at ive St udies
EXPLORI NG POVERTY PATTERNS AND DI FFERENTI ALS. . . Distribution of Italian NUTS3 regions by classes of poverty intensities Head Count Fuzzy Fuzzy Fuzzy Fuzzy Ratio Monetary Supplementary Manifest Latent < 0.05 6.45 0.00 0.00 36.56 0.00 0.05 |– 0.10 30.11 3.23 1.07 53.76 0.00 0.10 |– 0.15 26.88 44.09 41.94 9.68 0.00 0.15 |– 0.20 4.30 35.48 40.86 0.00 0.00 0.20 |– 0.25 3.23 12.90 16.13 0.00 36.56 0.25 |– 0.30 7.53 4.30 0.00 0.00 43.01 > 0.30 21.50 0.00 0.00 0.00 20.43 Source: Authors’ elaborations on ECHP data, Italian Section (1994-2001), and Istat Nearly 57% of I talian provinces shows an income poverty incidence (HCR) between 5% and 15% while a substantial share of provinces (32%), with a poverty incidence higher than 20%, is located in the South and I slands More than 92% of I talian provinces shows a FM between 10% and 25% while there isn’t any province with a FM higher than 30% or lower than 5% Almost the totality (98. 93%) of the I talian provinces shows a FS between 10% and 25%, denoting lower levels of territorial disparities Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 11 Depart ment of Management and Quant it at ive St udies
EXPLORI NG POVERTY PATTERNS AND DI FFERENTI ALS. . . TERRI TORI AL SERI ES OF POVERTY COMPOSI TE ESTI MATES AT A NUTS3 LEVEL HEAD COUNT RATI O (continuous line) FUZZY MONETARY (broken line) VS VS FUZZY MONETARY (broken line) FUZZY SUPPLEMENTARY (continuous line) 0.5 0.3 0.4 0.2 0.3 0.2 0.1 0.1 0 0 North-West North-East Center South Islands North-West North-East Center South Islands The territorial series of HCR, substantially stable across northern I talian provinces, rapidly increases as we move to the southern and insular ones The territorial series of FM is quite stable across northern provinces and it slightly tends to increase as we move to the southern and insular ones Supplementary deprivation increases across provinces with the increasing of the income poverty Universit y of Naples “Part henope” (I t aly) 2nd J une 2016 12 Depart ment of Management and Quant it at ive St udies
Recommend
More recommend
