Low-income households | Middle-income households | High-income households | All households | |||||
Conditional demand (intensity) elasticity (Deaton model) | ||||||||
Price | −0.424*** | (0.049) | −0.339*** | (0.067) | −0.258** | (0.142) | −0.359*** | (0.044) |
Income | 0.174** | (0.085) | 0.241** | (0.128) | 0.276 | 0.057 | 0.205*** | (0.050) |
Variables | Unit value | Budget share | Unit value | Budget share | Unit value | Budget share | Unit value | Budget share |
Total expenditure (ln) | 0.148*** | −0.034*** | 0.208*** | −0.025*** | 0.237*** | −0.021*** | 0.191*** | −0.029*** |
(0.024) | (0.003) | (0.049) | (0.006) | (0.025) | (0.003) | (0.016) | (0.002) | |
Household size (ln) | −0.077*** | 0.005 | −0.119** | −0.004 | −0.129*** | 0.000 | −0.098*** | 0.003* |
(0.026) | (0.004) | (0.049) | (0.006) | (0.022) | (0.002) | (0.016) | (0.002) | |
Male ratio | −0.077** | 0.009** | −0.012 | 0.018*** | −0.033 | 0.013*** | −0.032** | 0.014*** |
(0.034) | (0.005) | (0.030) | (0.003) | (0.021) | (0.002) | (0.015) | (0.002) | |
Adult ratio | −0.108*** | 0.008* | −0.152*** | 0.004 | −0.168*** | 0.012** | −0.133*** | 0.009*** |
(0.034) | (0.005) | (0.038) | (0.004) | (0.051) | (0.005) | (0.022) | (0.003) | |
Maximum education: more than secondary complete | ||||||||
No education | −0.144* | 0.073*** | −0.107 | 0.002 | −0.068 | 0.013* | −0.097** | 0.029*** |
(0.079) | (0.011) | (0.082) | (0.009) | (0.069) | (0.007) | (0.044) | (0.005) | |
Primary complete | −0.066*** | 0.006* | −0.092*** | 0.000 | −0.110*** | −0.001 | −0.091*** | 0.001 |
(0.024) | (0.003) | (0.025) | (0.003) | (0.025) | (0.003) | (0.014) | (0.002) | |
Secondary complete | −0.034* | 0.003 | −0.025 | 0.002 | −0.073*** | 0.001 | −0.049*** | 0.001 |
(0.019) | (0.003) | (0.016) | (0.002) | (0.016) | (0.002) | (0.010) | (0.002) | |
HH activity: employed | ||||||||
Unemployed | −0.025 | −0.002 | −0.076* | 0.004 | −0.111* | −0.009 | −0.046** | 0.000 |
(0.027) | (0.004) | (0.043) | (0.005) | (0.064) | (0.006) | (0.021) | (0.003) | |
Pensioners | −0.074*** | 0.001 | −0.061*** | −0.007*** | −0.113*** | −0.007*** | −0.085*** | −0.005*** |
(0.020) | (0.003) | (0.020) | (0.002) | (0.018) | (0.002) | (0.011) | (0.001) | |
Constant | −0.815*** | 0.240*** | −1.136*** | 0.198*** | −1.217*** | 0.167*** | −1.020*** | 0.214*** |
(0.132) | (0.018) | (0.272) | (0.031) | (0.170) | (0.017) | (0.096) | (0.011) | |
Number of clusters | 169 | 169 | 175 | 175 | 172 | 172 | 518 | 518 |
Cluster effect F1 | 12.967*** | 2.321** | 12.161*** | 3.147*** | 9.906*** | 3.509*** | 11.735*** | 2.938*** |
Observations | 1869 | 1869 | 2017 | 2017 | 1907 | 1907 | 5793 | 5793 |
R-squared | 0.612 | 0.348 | 0.587 | 0.337 | 0.592 | 0.360 | 0.609 | 0.340 |
Source: Own calculation; ***p<0.01, **p<0.05, *p<0.1.
Cluster fixed effects confirm the existence of time and spatial variation (Deaton); SEs for both price and expenditure elasticity are calculated using bootstrap procedure of 1000 replications. Note: Tests showed the absence of statistically significant difference between price elasticities among all income groups: low-income and middle-income groups (χ2(1)=1.39, prob >χ2=0.2379); low-income and high-income groups (χ2(1)=1.48, prob >χ2=0.2239); middle-income and high-income groups (χ2(1)=0.40, prob >χ2=0.5276). Also, test showed the absence of statistically significant difference between income elasticities among all income groups: low-income and middle-income groups (χ2(1)=0.21, prob >χ2=0.6502); low-income and high-income groups (χ2(1)=1.04, prob >χ2=0.3078); middle-income and high-income groups (χ2(1)=0.07, prob >χ2=0.7935).