Professional Documents
Culture Documents
Dougherty
Introduction to Econometrics,
5th edition
Chapter heading
Chapter 3: Multiple Regression
Analysis
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
This sequence investigates the variances and standard errors of the slope coefficients in a
model with two explanatory variables.
1
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
The expression for the variance of ̂ 2 is shown above. The expression for the variance of̂ 3
is the same, with the subscripts 2 and 3 interchanged.
2
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
The first factor in the expression is identical to that for the variance of the slope coefficient
in a simple regression model.
3
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
The variance of ̂ 2 depends on the variance of the disturbance term, the number of
observations, and the mean square deviation of X2 for exactly the same reasons as in a
simple regression model.
4
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
5
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
The higher is the correlation between the explanatory variables, positive or negative, the
greater will be the variance.
6
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
This is easy to understand intuitively. The greater the correlation, the harder it is to
discriminate between the effects of the explanatory variables on Y, and the less accurate
will be the regression estimates.
7
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
Note that the variance expression above is valid only for a model with two explanatory
variables. When there are more than two, the expression becomes much more complex
and it is sensible to switch to matrix algebra.
8
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
u2 1
standard deviation of ˆ 2
X 2 i X 2 1 rX 2 , X 3
2 2
The standard deviation of the distribution of ̂ 2 is of course given by the square root of its
variance.
9
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
u2 1
standard deviation of ˆ 2
X 2 i X 2 1 rX 2 , X 3
2 2
With the exception of the variance of u, we can calculate the components of the standard
deviation from the sample data.
10
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
1 2 nk 2
E uˆ i u
n n
The variance of u has to be estimated. The mean square of the residuals provides a
consistent estimator, but it is biased downwards by a factor (n – k) / n , where k is the
number of parameters, in a finite sample.
11
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
1 2 nk 2 1
E uˆ i u ˆ
2
i
ˆ
u 2
n n u
nk
Obviously we can obtain an unbiased estimator by dividing the sum of the squares of the
residuals by n – k instead of n. We denote this unbiased estimator ˆ u .
2
12
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
u2 1 u2 1
2ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
1 2 nk 2 1
E uˆ i u ˆ
2
i
ˆ
u 2
n n u
nk
ˆ u2 1 ˆ u2 1
s.e. ˆ2
X 2i X 2
2
1 r 2
X2 ,X3 n MSD X 2 1 r 2
X2 ,X3
Thus the estimate of the standard deviation of the probability distribution of ̂ 2 , known as
the standard error of ̂ 2 for short, is given by the expression above.
13
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
We will use this expression to analyze why the standard error of S is larger for the union
subsample than for the non-union subsample in wage equation regressions using Data Set
21.
14
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
To select a subsample in Stata, you add an ‘if’ statement to a command. The COLLBARG
variable is equal to 1 for respondents whose rates of pay are determined by collective
bargaining, and it is 0 for the others.
15
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
Note that in tests for equality, Stata requires the = sign to be duplicated.
16
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
17
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
In the case of the non-union subsample, the standard error of S is 0.2439, less than half as
large.
18
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
ˆ u2 1 ˆ u2 1
s.e. ˆ2
X 2i X 2
2 2 2
1 rX2 ,X3 n MSD X 2 1 rX2 ,X3
We will explain the difference by looking at the components of the standard error. It is
convenient to start by rearranging the expression for the standard error as the product of
the four factors.
19
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Union 0.5365
Non-union 0.2439
Factor product
Union
Non-union
20
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1
ˆ u2 RSS
nk
21
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1
ˆ u2 RSS
nk
22
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1
ˆ u2 RSS
nk
RSS / (n – k) is equal to 108.908. To obtain ˆ u , we take the square root. This is 10.436.
23
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Non-union 0.2439
Factor product
Union
Non-union
24
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
Similarly, in the case of the non-union subsample, ˆ u is the square root of 123.325, which is
11.105. We also note that the number of observations in that subsample is 425.
25
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
Union
Non-union
26
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
Union
Non-union
We calculate the mean square deviation of S for the two subsamples from the sample data.
27
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
The correlation coefficients for S and EXP are –0.5866 and –0.5796 for the union and non-
union subsamples, respectively. (Note that "cor" is the Stata command for computing
correlations.)
28
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
Union
Non-union
These entries complete the top half of the table. We will now look at the impact of each
item on the standard error, using the mathematical expression at the top.
29
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
Union 10.436
Non-union 11.105
The ˆ u components need no modification. It is a little larger for the non-union subsample,
and so has an adverse effect on the standard error.
30
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
The number of observations is much larger for the non-union subsample, so the second
factor is much smaller than that for the union subsample.
31
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
Perhaps surprisingly, the variance in schooling is similar for the two subsamples.
32
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
The correlation between schooling and work experience is also similar for the two
subsamples. Note that the sign of the correlation makes no difference since it is squared.
33
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
Multiplying the four factors together, we obtain the standard errors. (The discrepancy in
the last digit of the union standard error has been caused by rounding error.)
34
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
We see that the reason that the standard error is smaller for the non-union subsample is
that there are far more observations than in the non-union subsample. Otherwise the
standard errors would have been about the same.
35
PRECISION OF THE MULTIPLE REGRESSION COEFFICIENTS
1 1 1
s.e. ˆ2 ˆ u
n MSD( X 2 ) 1 rX22 , X 3
Factor product
The goodness of fit, as measured by ˆ u , is slightly inferior for the non-union sample and
this has a marginal offsetting effect. The other two factors are very similar for the two
subsamples.
36
Copyright Christopher Dougherty 2016.
Individuals studying econometrics on their own who feel that they might benefit
from participation in a formal course should consider the London School of
Economics summer school course
EC212 Introduction to Econometrics
http://www2.lse.ac.uk/study/summerSchools/summerSchool/Home.aspx
or the University of London International Programmes distance learning course
EC2020 Elements of Econometrics
www.londoninternational.ac.uk/lse.
2016.04.29