Multivariate Analysis

Question 1

Ceteris paribus

Answer 1

holding all other variables constant, only way to isolate the effect of the variable of interest

Question 2

B0

Answer 2

predicted value of y when all x’s equal 0

Question 3

B1

Answer 3

predicted change in y when x increases by 1 unit, holding all other variables constant

Question 4

Multiple regression bias

Answer 4

1. random sample
2. linear in parameters
3. no perfect correlation between variables
4. cov(x,u) = 0

Question 5

Perfect correlation

Answer 5

Can’t have 2 variables that add up to each other OR can’t have the same variable in 2 units of measurement

Question 6

sample size & 𝜎̂^2

Answer 6

Sample size will not effect sigma squared because n is in the numerator and denominator

Question 7

sample size and total sum of squares (SST)

Answer 7

will increase SST because it contains the sum of i to n

Question 8

k

Answer 8

• no. / new regressors

- increasing k, decreases the variance b/c it’s in the denominator