Table 5

Panel regression estimates for expenditures on the old age function as an independent variable

Model 13Model 14Model 15Model 16
Dependent variablelnFIEBinTElnFIEBinFElnFIECinTEllFIECinFE
constant−0.275 (1.225)1.477 (1.058)−1.854 (1.484)−0.524 (1.258)
Independent variable
lnOA1.472*** (0.153)1.156*** (0.132)1.570*** (0.184)1.146*** (0.156)
Control variables
lnGini0.866** (0.327)0.519 (0.281)1.023* (0.418)0.818* (0.354)
lnGE−1.109*** (0.194)−0.791*** (0.166)−0.954*** (0.212)−0.592*** (0.180)
lnFU−0.272*** (0.050)−0.242*** (0.043)−0.321*** (0.061)−0.277*** (0.052)
Fit statistics of models
Breusch-Pagan testχ2 (1) = 1320.95 p = 0χ2 (1) = 1391.97 p = 0χ2 (1) = 1040.81 p = 0χ2 (1) = 1068.24 p = 0
Hausman testχ2 (4) = 6.832 p = 0.145χ2 (4) = 5.380 p = 0.250χ2 (4) = 19.986 p = 0.001χ2 (4) = 18.297 p = 0.001
EffectsrandomrandomFixedfixed
No. of countries24242121
No. of observations362362294294
F  F(4,269) = 21.344 p = 0.000F(4, 269) = 17.035 p = 0.000
χ2χ2(4) = 102.219 p = 0.000χ2(4) = 86.906 p = 0.000  
LSDV R2  0.9130.935
Within R2  0.2410.202
“Between” variance0.7850.832  
“Within” variance0.0590.043  

Note(s): Standard errors in parentheses, ***p < 0.001; **p < 0.01; *p < 0.05

Source(s): Authors’ own work

or Create an Account

Close subscription notice
Close access options