Hence, we obtain:
Var(ri I C)
Var(rj I C)
Var(r ) + ^7?Var(/)
(1 + δ) Var(r1)
Var(ri ) v72
(1 + è')Var(rJ) + (1 + £)(1 + χjφ7j
(A.6)
From (A.3), the correlation coefficient during the crisis period in the hypothesis
that only the variance of f and εj change, while the factor loadings remain
constant — which is our coefficient of interdependence φ — can be written as:
φ(λj,λf,δ,p) = 7i
7
1 Φ Var(ri I C) ∖ “1/2
1 + λf ∖Var(rj i c)J
Substituting (A.6) into (A.7), we finally obtain
φ^j,χf,δ,p)
(1 + ʌɑ)2 72 Var(ri) + 'dl + ʌɑ)2
(1 + 72iVar(r3) (1 + W + x3)
-, —1/2
(1 + ʌf)2 + ^(1 + Xj)(ɪ + ʌf)2 p
(1 + δ)(1 + Xjɔ2 p2 + (1 + δ)(1 + Xjɔ2 p2
ʃ(1 + χ )2 ■ [1+^(1 + χ')p2 ] 1
p( (1 + <5)(1 + Xjp ∫
which can be rearranged to give equation (2).
22
(A.7)
More intriguing information
1. Yield curve analysis2. Fiscal Policy Rules in Practice
3. The demand for urban transport: An application of discrete choice model for Cadiz
4. Comparative study of hatching rates of African catfish (Clarias gariepinus Burchell 1822) eggs on different substrates
5. Valuing Farm Financial Information
6. The economic value of food labels: A lab experiment on safer infant milk formula
7. GENE EXPRESSION AND ITS DISCONTENTS Developmental disorders as dysfunctions of epigenetic cognition
8. Financial Development and Sectoral Output Growth in 19th Century Germany
9. American trade policy towards Sub Saharan Africa –- a meta analysis of AGOA
10. Technological progress, organizational change and the size of the Human Resources Department