Contents
0.200 0.220 0.240 0.260 0.280 0.300 0.320 0.340 0.360 0.380 0.400 1981-1984 1990-1994 1995-1998 1999-2004 2005-2009 2010-2014 Gi ni C oeffci ent Wave
Participation
ijw=β
0+ β
1(Income
ijw)+ β
2(Inequality
jw) +
β
3(Income
ijw*Inequality
jw) +ε
ijw(1)
β
2β
3β
3β
1β
2β
3β
2β
3β
1β
2β
1β
1β
2β
3∂y Participation
ijw∂x Inequality
jw= β
2+ β
3Income
ijw(2)
β
2Y
ij=b
0j+b
1jI
ij+ε
ijε
ij∼N(0,σ
2)
(3)
Yij=Outcome variable for ith individual in jthcountryb0j=Country specific intercept
b1j=Country specific effect of the individual leval variable
ε
ij)
σ
2b
0j&
b
1jb
0j& b
1jb
0j= γ
00+γ
01G
j+U
0jU
0j∼(0,τ
00)
(4)
b
1j=γ
10+γ
11G
j+U
1jU
1j∼N(0,τ
11)
(5)
cov(U
0j,U
1j)= τ
10 Gj=Country level variableγ00=Common intercept among countries
γ01=Effect of country level predictor on the group specific intercept
γ10= Common slope associated with the individual level variables across countries γ11=Effect of the country level predictor on the country specific slope
U
0jU
1j)
τ
00τ
11τ
10γ
00& γ
01γ
10& γ
11U
0jU
1jY
ij=
γ
00+γ
01G
j+γ
10I
ij+γ
11G
jI
ij+U
0jU
ij(6)
5. Methodology
Participationijw Incomeijw
Inequalityjw Incomeijw*GINIjw
Political scaleijw
Femaleijw Fulltimeijw Parttimeijw unemployedijw Marriedijw Singleijw Postcommunistj EU18j NonEU OEDCj
i
j
w
ε
0jwε
00j5.1. Ordinary Least Squares (OLS) regression
Participation
ijw= 𝛽
0+ 𝛽
1(𝐼𝑛𝑐𝑜𝑚𝑒
𝑖𝑗𝑤) + 𝛽
2(𝐺𝐼𝑁𝐼
𝑗𝑤) + 𝛽
3(𝐼𝑛𝑐𝑜𝑚𝑒
𝑖𝑗𝑤∗ 𝐺𝐼𝑁𝐼
𝑗𝑤)
+ 𝛽
4𝑃𝑜𝑙𝑖𝑡𝑖𝑐𝑎𝑙 𝑠𝑐𝑎𝑙𝑒
𝑖𝑗𝑤+ 𝛽
5𝐹𝑒𝑚𝑎𝑙𝑒
𝑖𝑗𝑤+ 𝛽
6𝐹𝑢𝑙𝑙𝑡𝑖𝑚𝑒
𝑖𝑗𝑤+ 𝛽
7𝑃𝑎𝑟𝑡𝑡𝑖𝑚𝑒
𝑖𝑗𝑤+ 𝛽
8𝑢𝑛𝑒𝑚𝑝𝑙𝑜𝑦𝑒𝑑
𝑖𝑗𝑤+ 𝛽
9𝑀𝑎𝑟𝑟𝑖𝑒𝑑
𝑖𝑗𝑤+ 𝛽
10𝑆𝑖𝑛𝑔𝑙𝑒
𝑖𝑗𝑤+ 𝛽
11𝑃𝑜𝑠𝑡𝑐𝑜𝑚𝑚𝑢𝑛𝑖𝑠𝑡
𝑗+ 𝛽
12𝐸𝑈18
𝑗+ 𝛽
13𝑁𝑜𝑛𝐸𝑈 𝑂𝐸𝐷𝐶
𝑗+ 𝜀
00𝑗+ 𝜀
0𝑗𝑤𝑌̂
5.2. Ordinal Logistic regression
𝑃 1−𝑃
6. Results
Standard errors in parentheses
* p < 0.10, ** p < 0.05, *** p < 0.01
0 0.03 0.06 0.09 0.12 0.15 0.18 0.21 0.24 0.27 0.3 0.33 0.36 0.39 0.42 0.45 Not at all interested Not very interested Somewhat interested Very interested P re di cte d proba bi liti es Political interest 0 0.03 0.06 0.09 0.12 0.15 0.18 0.21 0.24 0.27 0.3 0.33 0.36 0.39 0.42 0.45 0.48
Would never do Might do Have done
P re di cte d prob ab ili ti es Political Consumersim