6.) Specification: Choosing the Independent Variables

Question 1

Specifying an econometric equation consists of three parts…

Answer 1

1. ) Choosing the correct independent variables
2. ) Choosing the correct functional form
3. ) Choosing the correct form of the stochastic error term

Question 2

A specification error results when…

Answer 2

any one of three parts of specifying an econometric equation made incorrectly

Question 3

The strength of researchers being able to pick the independent variables for regression equations is…

Answer 3

the equations can be formulated to fit individual needs

Question 4

The weakness of researchers being able to pick which independent variables to include is…

Answer 4

that researchers can estimate many different specifications until they find the one that “proves” their point

Question 5

The primary consideration in deciding whether an independent variable belongs in an equation is whether

Answer 5

the variable is essential the regression on the basis of theory

Question 6

The major consequence of omitting a relevant independent variable from..

Answer 6

an equation is to cause bias in the regression coefficients that remain in the equation

Question 7

Omitted Variable is defined as..

Answer 7

an important explanatory variable that has been left out of a regression equation

Question 8

The bias caused by leaving a variable out of an is called…

Answer 8

omitted variable bias

Question 9

In an equation with more than one independent variable, the coefficient beta K represents…

Answer 9

the change I the dependent variable Y caused by a one-unit increase in the independent variable Xk, holding constant the other independent variables in the equation

Question 10

If a variable is omitted, then …

Answer 10

it is not included as an independent variable, and it is not held constant for the calculation and interpretation of beta hat K.

Question 11

The major consequence of omitting a relevant independent variable from an equation is…

Answer 11

to cause bias in the regression coefficients that remain in the equation

Question 12

The term Bomf(rin,om) is …

Answer 12

the amount of specification bias introduced into the estimate of the coefficient of the included variable by leaving out the omitted variable.

Question 13

When a relevant variable is omitted than r squared barred is likely to…

Answer 13

drop

Question 14

What two factors are key to understand if a relevant variable is left out of a regression equation?

Answer 14

1. ) There is no longer an estimate of the coefficient of that variable in the equation.
2. ) The coefficients of the remaining variables are likely to be biased.

Question 15

Reasons that including omitted variable is easier said than done

Answer 15

1. ) Omitted variable bias is hard to detect
2. ) The problem of choosing which variable to add to an equation once you decide that it is suffering from omitted variable bias.

Question 16

Expected bias is…

Answer 16

the likely bias that omitting a particular variable would have caused in the estimated coefficient of one of the included variables.

Question 17

The best indicators of an omitted relevant variable are

Answer 17

the theoretical underpinnings of the model itself

Question 18

Irrelevant variables are..

Answer 18

the converse of omitted variables, it’s when you include a variable in an equation that doesn’t belong there.

Question 19

Although the irrelevant variables no bias…

Answer 19

it causes problems for the regression because it reduces the t-scores and the R squared barred

Question 20

In terms of bias and variance on coefficient estimates an omitted variable causes…

Answer 20

Bias and the variance decreases

Question 21

In terms of bias and variance on coefficient estimates an irrelevant variable causes

Answer 21

No bias but increases the variance

Question 22

4 part test to be worked through every time a variable is added

Answer 22

1. ) Theory: is the variable’s place in the equation unambiguous and theoretically sound?
2. ) t-Test: Is the variable’s estimated coefficient significant in the expected direction?
3. ) R squared bar: Does the overall fit of the equation (adjusted for degrees of freedom) improve when the variable is added to the equation?
4. ) Bias: Do other variables’ coefficients change significantly when the variable is added to the equation?

Question 23

If an irreleveant variable is included…

Answer 23

it will reduce r squared bar, have an insignificant t-score, and have little impact on the other variables’ coefficients.

Question 24

Since economic theory is the most important test for including a variable…

Answer 24

a variable need not be dropped from an equation simply because it has an insignificant t-score.

Question 25

Theoretical considerations should never be discarded…

Answer 25

even in the face of statistical insignificance

Question 26

Three prescriptions for best practices in specification searches…

Answer 26

1. ) rely on theory rather than statistical fit as much as possible when choosing variables, functional forms, and the like.
2. ) minimize the number of equations estimated
3. ) Reveal, in a footnote or appendix, all alternative specifications estimated.