Quiz 3

Front 1

Specify the 3 steps required to test the null hypothesis that the slope coefficient beta_1 equals zero.

Back 1

1. Compute the standard error of the estimated slope coefficient beta_1-hat^act

2. Compute the t-statistic

3. Compute the p-value

Front 2

Consider the eqn:

Testscore-hat = 698.9 - 2.28 = 698.9 -2.28STR

(10.4) (0.52)

R^2 = 0.051

SER = 18.6

t-statistic?

Back 2

4.38

Front 3

The regression R^2 is a measure of

Back 3

the goodness of fit of your regression line

Front 4

What is the difference between beta_1 and beta_1-hat?

Back 4

beta_1 is the true population parameter, the slope of the population regression line, while beta_1-hat is the OLS estimator of beta_1

Front 5

What is the difference between u and u-hat?

Back 5

u represents the deviations of observations from the population regression line, while u-hat is the difference between Y and Y-hat

Front 6

What is the difference between the OLS predicted value Y-hat and E(Y|X)?

Back 6

E(Y|X) is the expected value of Y given values of X, while Y-hat is the OLS predicted value of Y for given values of X.

Front 7

In the simple linear regression model Y_i = beta_0 + beta_1X_i + u_i, what does beta_0 + beta_1X_i represent?

Back 7

the population regression function

Front 8

To decide whether or not the slope coefficient is small or large you should

Back 8

analyze the economic importance of a given increase in X

Front 9

Consider the following regression line:

Testscore-hat = 698.9 - 2.28STR

slope coefficient t-stat = 4.38

What is the standard error of slope coefficient?

Back 9

0.52

Front 10

A binary variable is often called a

Back 10

dummy variable

Front 11

if

ahe-hat = 3.32 - 0.45Age, R^2 = 0.02, SER=8.66

(1.00) (0.04)

the 95% confidence interval for the effect of changing age by 5 years is approximately

Back 11

[1.96,2.54]

Front 12

The 95% confidence interval for the beta_0-hat is the interval

Back 12

(beta_0-hat - 1.96SE, beta_0-hat + 1.96SE)

Front 13

The OLS residuals, u_i-hat, are sample counterparts of the population

Back 13

error

Front 14

Binary variables

Back 14

can only take on two values

Front 15

In the simple linear regression model , the regression slope

Back 15

indicates by how many units Y increases given a one unit increase in X

Front 16

The t-statistic is calculated by dividing

Back 16

the estimator minus its hypothesized value by the standard error of the estimator

Front 17

the slope estimator, beta_1, has a smaller standard error, other things equal, if

Back 17

there is more variation in the explanatory variable, X

Front 18

The sample regression line estimated by OLS

Back 18

will always run through point (X-bar, Y-bar)

Front 19

The confidence interval for the sample regression function slope

Back 19

can be used to conduct a test about a hypothesized population regression function slope

Front 20

The regression R^2 is defined as follows

Back 20

(ESS / TSS)

Front 21

This question was too long to type--

Back 21

See question 6 for practice!