Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 11

REGRESSION

WITH SINGLE REGRESSOR


Simple linear regression
Stock and Watson (Chapter 5)

HYPOTHESIS TESTING:STEP 1
Specify null hypothesis and alternative hypothesis
H0: the null hypothesis
H1: the alternative Hypothesis

Choose one of the three

HYPOTHESIS TESTING:STEP 2

Choose level of significance (denoted by


the Greek letter alpha). For example,
alpha=5% the most common.

The level of significance is the probability


of type I error (i.e. of rejecting the null
hypothesis when the null hypothesis is, in
fact, correct)

HYPOTHESIS TESTING:STEP 3

Compute the test statistic on a hypothesis about 1

t=
Where 1,0 is the value of 1 hypothesized under the
null. Since under null hypothesis 1 = 0, then 1,0 = 0
(like California Test Score example)
When

t is called the t-ratio which is reported


directly in the GRETL output.

HYPOTHESIS TESTING: STEP 4


Construct the t-statistic
t=
Reject at 5% significance level if |t| > 1.96
The p-value is p = Pr[|t| > |tact|] = probability in tails of normal
outside |tact|; you reject at the 5% significance level if the pvalue is < 5%.
This procedure relies on the large-n approximation that is
normally distributed; typically n = 50 is large enough for the
approximation to be excellent.

HYPOTHESIS TESTING: STEP 4


Hypothesis testing using p-values
Decision rules:

HYPOTHESIS TESTING
EXAMPLE (CALIFORNIA DATA)
R2 = 0.05
SER = 18.6
(9.46) (0.48)
Regression software reports the standard errors:
SE() = 0.48 and SE( ) = 9.46

t-statistic testing 1,0 = 0 is:


The 1% 2-sided significance level is 2.58, so we reject the null at
the 1% significance level.
The p-value based on the large-n standard normal approximation
to the t-statistic is 0.00001 (

BINARY/DUMMY
VARIABLES
Binary/dummy variables take only two
possible values (0 or 1)
Binary/dummy variables are used in simple
linear regression to test the difference
between two means

BINARY VARIABLE:
EXAMPLE
Suppose there are two groups (60 men and
40 women). Are their mean earnings
significantly different?
Solutions
Method 1: Test for the difference between
two means using the t test
Method 2: Specify a simple linear
regression with binary variable

SOLUTION:METHOD 1
Test for the differences between the two means using the t test
Men
Women
Number of observations
Sample Mean
Sample standard deviation
: =
: (assume a two-sided test)
t

Ys Yl
ss2
ns

sl2
nl

Ys Yl

SE(Ys Yl )

Reject if |t| > 1.96 ; otherwise fail to reject

SOLUTION: METHOD 2

You might also like