Non-causality in Bivariate Binary Panel Data



or, in compact vectorial form:

Y* = Bx + ε = V + ε

Y = [⅛∙>o}]

where Y*,Y,υ and ε are (n × 1) vectors of elements Yj*,Yj, βjX and ej∙, whereas
B = [β1, ∙ ∙ ∙ , βn'. Notice that no loss of generality is involved in assuming that
the same vector
x enters all equations, since some of the coefficients in B may
be zero.

The probability of Yj can be easily calculated by adapting the results of the
previous section:

Pr (yj = Уз I <≈) = Φ ((2 ∙ yj - 1) ∙ βjχ∙, 0, σ2)

i.e., the marginal distribution of Yj is a simple univariate probit model; this
result can be very useful in applications, since it shows that the distribution of
Yj depends only on the parameters of the corresponding latent regression Y.*.

However, in this case, it is more interesting to express the probability of a
vector
у = [τ∕ι,... ,yn]' whose elements are only O’s or l’s; in order to do so,
define the diagonal matrix
Dy

Dy = 2 ∙ diag (y) - In

Then the probability of у is

Pr (У = у I x) = Pr (Dy (Bx + ɛ) > 0)

= Pr (DyBx + Dyε > 0)

= Pr (—Dyε < DyBx)

Now suppose that ε is a random Gaussian vector, so that

ε ~ N (0, Σ)

Then -Dyε is itself a random Gaussian vector

-Dyε ~ N (θ,DyΣD'y)

and the probability of observing у is:

Pr (У = у I x) = Φn (pyBx; 0, DyΣD'y)

This formula allows to express the probability of у in compact form, involving
only an «-dimensional integral parameterized as a function of
y. Here, DyYD1y
is a positive definite matrix: in fact, consider dy, a column vector equal to the
main diagonal of
Dy; then, by Equation (2.11) in Styan (1973)

DyVD1y = (dyd!y) * Σ
30



More intriguing information

1. Behavior-Based Early Language Development on a Humanoid Robot
2. The name is absent
3. Getting the practical teaching element right: A guide for literacy, numeracy and ESOL teacher educators
4. Cross-Country Evidence on the Link between the Level of Infrastructure and Capital Inflows
5. The name is absent
6. The Environmental Kuznets Curve Under a New framework: Role of Social Capital in Water Pollution
7. The Role of Trait Emotional Intelligence (El) in the Workplace.
8. The urban sprawl dynamics: does a neural network understand the spatial logic better than a cellular automata?
9. The name is absent
10. Density Estimation and Combination under Model Ambiguity
11. Credit Markets and the Propagation of Monetary Policy Shocks
12. The name is absent
13. The name is absent
14. The name is absent
15. THE AUTONOMOUS SYSTEMS LABORATORY
16. Policy Formulation, Implementation and Feedback in EU Merger Control
17. 101 Proposals to reform the Stability and Growth Pact. Why so many? A Survey
18. Bidding for Envy-Freeness: A Procedural Approach to n-Player Fair Division Problems
19. Studying How E-Markets Evaluation Can Enhance Trust in Virtual Business Communities
20. Individual tradable permit market and traffic congestion: An experimental study