To figure this out, we need to use the following regress:
sort hhid
regress mxtfood hhsizem if hhid~=hhid[_n-1]
You should come up with the following table:
Source | SS df MS Number of obs = 1060 ---------+------------------------------ F( 1, 1058) = 110.44 Model | 17540388.4 1 17540388.4 Prob > F = 0.0000 Residual | 168029694 1058 158818.237 R-squared = 0.0945 ---------+------------------------------ Adj R-squared = 0.0937 Total | 185570083 1059 175231.428 Root MSE = 398.52 ------------------------------------------------------------------------------ mxtfood | Coef. Std. Err. t P>|t| [95% Conf. Interval] ---------+-------------------------------------------------------------------- hhsizem | 43.44603 4.134097 10.509 0.000 35.33407 51.55799 _cons | 349.7945 22.4912 15.553 0.000 305.6621 393.927 ------------------------------------------------------------------------------
This gives you a regression equation of:
(xfoodhat)i = 349.79 + 43.45(hhsizem)iTherefore, for a every additonal member, a household can be expected, on average, to increase food expenditure by about 43.45 Rand per month.