Tom K. answered 12/04/20
Knowledgeable and Friendly Math and Statistics Tutor
The variance-covariance matrix is
3 1/2
1/2 1
The inverse is
4/11 -2/11
-2/11 12/11
Then, f(x,y) = 2/(11π) exp(-1/2 (4/11 x^2 + 4/11 xy +12/11y^2))
If 2x +3y = 1, y = (1 - 2x)/3
Then, f(x,y) = f(x, (1 - 2x)/3)
We substitute (1 - 2x)/3 for y. Then, we will be able to make use of symmetry to get the expected value.
Looking at the exponential term,
4/11 x^2 + 4/11 xy +12/11y^2 = 4/11 x^2 - 4/11 x(1 - 2x)/3 + 12/11 [(1 - 2x)/3]^2 =
4/11 x^2 - 4/33x + 8/33x^2 + 4/33 - 16/33x +16/33x^2 =
12/11x^2 -20/33x +4/33
We complete the square, but the constant is irrelevant, all we care about is the symmetry.
12/11(x-5/18)^2 + ...
The mean is 5/18