Formula Sheet EC3303

Download as pdf or txt
Download as pdf or txt
You are on page 1of 1

Formula Sheet (EC3303)

h i
2 2
De…nition: X = V ar (X) = E (X X) ; Cov (X; Y ) = E [(X X ) (Y Y )] =
Cov(X;Y )
E (XY ) E (X) E (Y ) ; Corr (X; Y ) = X Y
; where X = E (X) :

If X and Y are two random variables, and a and b are two constants,

E (aX + bY ) = aE (X)+bE (Y ) ; V ar (aX + bY ) = a2 V ar (X)+b2 V ar (Y )+2abCov (X; Y ) :

P
Sample Covariance sXY = n 1 1 ni=1 Xi X Yi Y and the sample correlation coe¢ cient
q q
sXY 1 Pn 2 1 Pn 2
XY = sX sY ; where s X = n 1 i=1 Xi X and s Y = n 1 i=1 Yi Y are sample

standard deviation of X and Y respectively.

For simple linear regression, the OLS estimators b 0 and b 1 ;

Pn Pn
b i=1 Xi X Yi Y i=1 Xi Yi nX Y
1 = Pn 2 = P n 2
Xi X 2
i=1 i=1 Xi nX
b = Y b X
0 1

q Pn
b2i
u
Standard error of b 1 : b b = SE b 1 = qP SER
n 2
; where SER = i=1
n 2 :
i=1 (Xi X )
1

Pn 2 Pn 2 Pn
T SS = i=1 Yi Y = i=1 Ybi Y + b2i
i=1 u = ESS + SSR: R2 = ESS
T SS =1 SSR
T SS :

2 2
(Runrestricted Rrestricted )=q
Homoskedasticity-only F -statistic= restricted SSRunrestricted )=q
; or (SSRSSR unrestricted =(n k 1)
:
(1 Runrestricted )=(n k 1)
2

When the sample size is large, F -statistic Fq;1 : If the dependent variables are di¤erent for

the unrestriced and restricted regression models, two formulas are not equivalent. The latter

should be used.

You might also like