Chapter 4
Chapter 4
Chapter 4
MULTIPLE REGRESSION –
INFERENCE
Wooldridge: Introductory Econometrics:
A Modern Approach, 5e
Content
1
11/14/2021
1 -
2σ 2
0.4
f(x) = .e 0.35
σ 2π 0.3
0.2
Properties: 0.15
0.05
Var(X) = 2 -2 -1
0
0 1 2 3 4 5 6
• If random variables X1,…, Xn are independent (for any n) and X1 ~ N(1; 12);
X2 ~ N(2; 22);…; Xn ~ N(n; n2), then:
n n n
X
i=1
i = X1 +X 2 +...+X n ~ N( μ , σ
i=1
i
i=1
2
i )
X
i=1
i ~ N( nμ; nσ 2 )
• If X ~ N(; 2) and k is a non-zero constant, then: kX ~ N(k; k22)
Other distributions:
n
Chi-squared distribution: If Zi ~ N(0;1) (i = 1, n), then: Z i=1
2
i ~ χ 2 (n)
Z
Student’s t-distribution: If Z ~ N(0;1) and X ~ 2(m), then: ~ tm
X/m
X1 /m
Fisher distribution: If X1 ~ 2(m) and X2 ~ 2(n), then: ~ F(m, n)
X 2 /n
4
2
11/14/2021
3
11/14/2021
4
11/14/2021
Standard errors
Test H0: exper = 0 One would either expect a positive effect of experience on
Against H1: exper > 0 hourly wage or no effect at all.
t statistic
Degrees of freedom
Critical values for the 5% and the 1% significance level (these
are conventional significance levels). The null hypothesis is
rejected because the t-statistic exceeds the critical value.
„The effect of experience on hourly wage is statistically greater than zero at the 5%
(and even at the 1%) significance level.“
10
5
11/14/2021
11
ˆ j a j
– Step 1: Calculate t statistic: t
se( ˆ j )
– Step 2 :
12
6
11/14/2021
13
14
7
11/14/2021
3. Confidence intervals
• The confidence interval (CI) for a population parameter:
The 100(1-)% confidence interval (CI) for a population parameter j is:
j ˆ j t / 2 .se( ˆ j ); ˆ j t /2 .se( ˆ j )
• Interpretation of the confidence interval:
– The bounds of the interval are random.
– 100(1-)% is called the confidence level.
– In repeated samples, the interval that is constructed in the above way will cover
the population regression coefficient in 100(1-)% of the cases
• Relationship between confidence intervals and hypotheses tests
If aj Confidence interval then we reject H0: j = aj in favor of H1: j ≠ aj
16
8
11/14/2021
3. Confidence intervals
• Example: Model of firms‘ R&D expenditures
Spending on R&D Annual sales Profits as percentage of sales
log( rd ) 4.38 1.084 log( sales) 0.0217 profmarg
(0.47) (0.060) (0.0128)
n 32; R 2 0.918; df 32 2 1 29 t0.025 (29) 2.045
1.084 2.045 0.060 0.0217 2.045 0.0128
(0.961; 1.21) (0.0045; 0.0479)
17
18
9
11/14/2021
19
20
10
11/14/2021
21
( SSRR SSRUR ) / q
F ~ F (q,( n (k 1)))
SSRUR / (n ( k 1))
A F-distributed variable only takes on positive values.
This corresponds to the fact that the sum of squared
residuals can only increase if one moves from H1 to
H0.
Choose the critical value so that the null hypothesis
is rejected in, for example, 5% of the cases, although
it is true.
22
11
11/14/2021
23
24
12
11/14/2021
25
– Restricted regression
The restricted model is actually a regression of
[y-x1] on a constant
– Test statistic
H0 cannot be rejected.
26
13