Title | Formula sheet - Econometrics notes |
---|---|
Course | literatura |
Institution | College SA |
Pages | 12 |
File Size | 1.2 MB |
File Type | |
Total Downloads | 85 |
Total Views | 149 |
Econometrics notes...
ECO 315: Econometrics Formula sheet Population and sample statistics Population
Sample _
E(X) = ∑Xf(x)
X
MEAN
X
i
/n _
2
2
( X X) 2 S i n 1 2 x
σ x = ∑(X-μ) f(x)
VARIANCE
σx
STANDARD DEVIATION
(X cov(X, Y)
cov(X,Y) = ∑∑(X-μx)(Y-μy)f(x,y)
COVARIANCE
ρ = cov(X,Y)/σxσy
CORRELATION COEFFICIENT
3
S = E(X-μx) / σ
3
x
4
2 2
K = E(X-μx) / [E(X-μx) ]
Sx _
i
_
X)(Yi Y) n 1
r = cov(X,Y)/SxyS _
X) 3
SKEWNESS
(X S
KURTOSIS
(X K
X)4
i
n 1 _
i
n 1
Normal distribution If Xi ~ N(μ,σ2), then Xi can be converted into Zi ~ N(0,1) using Zi = (Xi – μ)/σ OLS formulas: Simple regression _
_
b1 Y b 2 X _
b2
_
( X X )( Y Y ) (X X) i
i
_
2
i
_
var(b 1) X i2 2 /[n (X i X ) 2 ] _
2 var(b 2 ) 2 / (X i X )
se(b 1 ) var(b 1 ) se(b 2 ) var(b 2 )
^
Since σ2 is unknown, use 2 u i2 /( n 2)
Page 6 of 17
Hypothesis testing in simple regression
b1 1 ~ t df n 2 se(b 1 )
b 2 2 ~ t df n 2 se(b 2 )
Confidence intervals Limits:
b1 ± tαdf=n-2((se(b 1))
Limits:
b2 ± tαdf=n-2((se(b 2))
Analysis of variance TSS = ESS + RSS _
_
^
^
(Y Y) (Y Y) (Y Y ) 2
i
i
2
i
i
2
^
[Note that
(Y Y ) = u i
i
2
2 i ]
Coefficient of determination in context of simple regression ^
r
_
(Y Y ) (Y Y )
2
i
2
_
2
ESS TSS
i
Multiple regression t-ratios and confidence intervals are the same as in the simple regression case, but note that df = n-k, where k is the number of parameters. ^
^
ESS 2 yi x 2i 3 y ix 3i = 1 – (RSS/TSS) R TSS y i2 2
^
_
R
2
u /(n k ) 1 y /(n 1) 2 i
2 i
OLS formulas: Multiple regression ^
^
^
^
minu2i (Yi 1 2 X2i 3 X3i) 2 ^
_
^
_
^
_
1 Y 2 X 2 3 X3 ^
2
( yi x2 i )( x32i ) ( y ix 3i )( x 2i x 3i ) ( x22i )( x23i ) ( x 2ix 3i )2
Page 7 of 17
^
3
( yi x3i )( x 22i ) ( yi x 2 i )( x 2i x 3i ) ( x22i )( x23i ) ( x 2i x 3i ) 2
_ 2 1 X2 var( 1 ) n
^
x
^
var( 2 )
2 3i
( x )( x ) ( x 2 i x 3i ) 2 2i
2 3i
2
where 2
2 2i
( x )( x ) ( x 2 i x 3i ) 2 2i
2 3i
2 ^
x
^
var( 3 )
_ _ _ 2 x3 i X 23 x 22 i 2 X 2 X 3 x 2 i x 3 i 2 . x 22 i x 23i ( x 2i x 3i ) 2
2
^
u 2i
n3
2
Multiple regression: Hypothesis testing for overall significance ANOVA approach: F
In terms of R2: F
ESS /( k 1) RSS /( n k )
R2 /(k 1) (1 R2 ) /(n k )
Marginal contribution of an explanatory variable F test: F
(ESSnew - ESSold ) / number of new regres sors RSSnew / df ( n number of parameters in the new model)
Using R2: F
(R2new - R2old ) / number of new regres sors (1 - R2new ) / df ( n number of parameters in the new model)
Multiple regression: Hypothesis testing for equality of two coefficients ^
t
^
3 4 ^
^
^
^
var( 3 ) var( 4 ) 2 cov( 3 , 4 )
Page 8 of 17
Multiple regression: Hypothesis testing of linear equality restrictions ^
^
(2 3 ) (2 3 )
The t-test approach: t
^
^
^
^
var( 2 ) var(3 ) 2 cov(2 , 3)
F-test approach: F
( RSS R RSS UR ) / m RSS UR /( n k )
or in terms of R 2: F
(R 2UR R 2R ) / m (1 R2UR ) /(n k )
The Chow test
F
( RSS R RSS UR ) / k ~ F( k ,( n1 n2 2 k ) ( RSS UR ) /( n1 n 2 2 k )
Testing whether error variances of two sub-sample regressions are the same:
RSS1 And ^2 RSS 2 2 n1 k n2 k ^
2 1
^
Then: F
12 ^
2 2
Multicollinearity: Variance Inflation Factor: 1 VIF (1 r 223 ) ^
var( j)
2 VIF x2j
Auxiliary Regressions:
Fi
R2xi .x2 x3 ...xk /(k 2) (1 R 2xi .x2 x3 ...xk ) /(n k 1)
Heteroscedasticity: Spearman Rank Correlation Test:
d 2i rs 1 6 2 n ( n 1) t
rs n 2 1 rs2
Page 9 of 17
Goldfelt-Quandt test:
F
RSS2 / df RSS 1 / df
where df = [(n-c)/2] – k in the numerator and denominator
Breusch-Pagan-Godfrey test: ^ 2
~ 2
ui / n ^
~ 2
pi u i / 2
1 (ESS ) 2
Autocorrelation: Durbin-Watson statistic: t n
d
^
^
t n
^ 2 t
( u t u t 1 ) 2 t 2
u t 1
^
d 2 (1 ) Model Specification and Diagnostic Testing: Ramsey RESET test:
(R 2new - R 2old ) / number of new regressors F 2 (1 - Rnew ) / df ( n number of parameters in the new model)
Page 10 of 17
Page 11 of 17
Page 12 of 17
Page 13 of 17
Page 14 of 17
Page 15 of 17
Eco315 June 2019
Eco315 June 2019
Page 17 of 17...