Final Exam Review Flashcards Preview

Introduction to Econometrics > Final Exam Review > Flashcards

Flashcards in Final Exam Review Deck (50)
Loading flashcards...
1
Q

steps to calculating a basic regression equation

A
  1. calculate E(x) and E(y)
  2. calculate actual minus expected for each variable, each observation
  3. square “actual minus expected” for only X
  4. for y, take (actual(x) - expected(x))*(actual(y)-expected(y))
  5. take the sums of 3 and 4
  6. take ratio of these sums with XY on top
    this is your estimator

intercept = E(y) -E(x)*slope

2
Q

interpret:

selling price = 150 + .027(square footage)

A

for every increase of 1 square foot, we can expect to see the selling price of the house increase by .027

3
Q

Total sum of squares

A

total actual variation in Y

sum of (Actual Y - expected Y)^2

4
Q

Explained sum of squares

A

the modeled variation in Y

sum of (estimated y - expected Y)^2

5
Q

steps for an R^2

A
  1. take the actual values of Y, get E(y)
  2. take (ACTy - EXPy), square it, add it up
  3. thats the actual variation in Y
  4. use the results of regression to calculate predicted values of Y for every X
  5. take (PREDICTEDy-EXPECTEDy); square it; add it up
  6. take the ratio of 5 over 3 (ESS/TSS)
6
Q

r^2

A

how much of the variance in our data is explained by the regression model

7
Q

Standard Error of OBservations

A

the standard deviation of the error term

-how far are the actual values from our fitted line

8
Q

What does a t-stat of 1.96 actually mean?

A

this means you could create an interval of a certain width (1.96 SE above and below our hypothesized mean) and if you repeated your sampling 100 times, 95/100 times that interval would contain the true population mean

9
Q

standard error of the beta hat

A

remember beta is a random variable

  • therefore, it has an expected value and distribution
  • that distribution, the sampling distribution, has a spread, measured by the variance and the SD
  • the standard error of beta hat is the SD of the sampling distribution…it measures the spread
10
Q

heteroskedastic

A

variance of the error term changes

11
Q

homoskedastic

A

variance of the error term is constant

12
Q

why does a smaller standard error of the beta hat usually correlate with a larger t stat?

A

because as SE decreases, the width of the distribution gets smaller and smaller…decreasing our chances of having an insignificant value…spread is TIGHT

13
Q

F-statistic

A

-used to test a joint hypothesis that ALL of our betas are really zero

14
Q

formula for an f-statistic

A

(1-R^2)/(n-k-1)

k is # of IVs

15
Q

whats the formula for testing a subset of variables?

A

(RSSrestricted-RSSunrestricted)/q
______________________________
RSSunrestricted/n-k-1

16
Q

after running a simple p and q demanded regression, how do we find the elasticity of a product at a certain point?
ex: q = 1147 - 7.93*p, p = 70

A

(p/q)*coefficient = elasticity at that point

70*-7.93 = 555
1147-555=592

-7.93*(70/592)

17
Q

what’s the most basic way to estimate a curvilinear regression?

A

convert the data to natural logs, dummy

18
Q

how do we convert an equation BACK from a log?

A
  1. take the exponential of your intercept term
  2. take your coefficient (elasticity) and raise your P to it
  3. multiply these things

ex: Q demanded = 23,156*p^(-.873)

19
Q

log-log (def and interpretation)

A
  • take the log of both the variables
  • changes interpretation to percentages
    ex: a certain % change in X is associated with a certain % change in Y
20
Q

log-linear (def and interpretations)

A
  • convert the DV to logs
  • leave IVs just as they are
  • changes to the DV are interpreted as percentages, NOT units
21
Q

interpret: Ln(selling price) = 6.21 - .08*(age)

A

log linear, so:

a one year increase in age of the house translates to an 8% increase in the selling price of the house

22
Q

can you compare the R^2 of a linear regression and a log linear regression?

A

NO, the DV’s are two very different thigns

23
Q

linear-log (def and interpretation)

A

convert the IVs to logs

-changes in the IV are interpreted as percentages, not units

24
Q

interpret: # of dining out experiences = -37.9 + 11.33*(LnIncome)

A

a 1% increase in income translates to a .11 increase in dining out experiences per month
-OR a 9% increase in income translates to a 1 time increase in dining out per month

25
Q

panel data

A

combination of cross sectional AND time series

-data varies across entities and across time

26
Q

fixed effects regression (time and entity)

A
  • holding constant the effects of different locations or places or times
  • done using thing specific binary variables and dummy coding
27
Q

how to test for significant of time fixed effect and entity fixed effect

A

(RSSrestricted-RSSunrestricted)/q
______________________________
RSSunrestricted/n-k-1

28
Q

how do we write in fixed effects on STATA?

A

xi: regress y x1 x2 x3 i.x4 i.x5

- stata will then create dummy variables for all but one of the state or time categories

29
Q

if you ran a regression with a binary variable and your coefficient is -.00377, how do you interpret this?

A

in states and years where the legal drinking age was 21, the data shows that seat belt usage was, on average, .37% lower than in states and years where the legal drinking age was not 21

30
Q

probit

A

in a probit model, the model plays the role of z in a cumulative standard normal distribution
-estimated beta is the change in the z value associated with a unit change in X

it spits out the chance that something is or isn’t occurring

31
Q

how does a pro bit work?

A

when state runs a pro bit, it is choosing values for the parameters that maximize a function
-this function is called a likelihood function

the likelihood we speak of is the likelihood that we observe the given Y values basked on our given X values

32
Q

time series

A

used for forecasting, data varies across time periods…not markets or person

33
Q

static or contemporaneous time series variables

A

an IV that is a statistic from the same time…such as Real GDP and Unemployment for each respective year

34
Q

dynamic time series variable

A

a statistic from the previous year…ex: REAL GDP and GDP from previous year

35
Q

path order Autoregressive Model

A

uses Y(T-1) to forecast Yt

  • there is no rule that says you can only use one lag
  • you can run a regression where IVs are Yt-1, Yt-2, Tt-3…so on
36
Q

how do you decide on how many lags to include?

A

Bayes Information Criterion Test

-need RSS, total number of time periods, number of lags

37
Q

BIC method

A
  1. take ln(RSS/periods)
  2. take number of (lags + 1)*(Ln(periods)/periods)
  3. add both numbers of that
    - the smallest BIC value is the one you use!
38
Q

why do we want BIC to be the smallest?

A
  1. the BIC has two parts, one part is a function of RSS
  2. we know this gets smaller as you add more variables
  3. the second part is a function of lags
  4. if you add a lag, the second part gets bigger and IF additional lag doesn’t do much to reduce RSS, the RSS only gets a little smaller…so overall BIC gets bigger
  5. but if you add a lag and it does a lot to make RSS smaller, then the first part gets a lot smaller, the second part gets a little bigger but the overall bic went down
  6. lower is better; the benefit you get from adding another lag outweighs the addition of the lag
39
Q

autoregressive distributed lag model

A

adding an additional variable

  • ex: past changes in GDP PLUS, say, unemployment
  • written like: ADL(p,q)
40
Q

BIC for an ADL(p,q) model

A

ln(RSS(k))/T) + (k)*(Ln(t)/t)

where k is the total number of coefficients across all RHS variables

41
Q

granger causality

A
  • a test to see whether an entire series of a RHS variable has useful predictive content
  • tests whether the estimated coefficients are all distinguishable from zero
42
Q

granger causality formula

A

RSSunrestricted/(n-k-1)

43
Q

how to interpret a LOGIT

A

e^(result)/(1+e^result)

result is a z-score that you can use to find out the likelihood of something occurring

44
Q

what are probits and logits interpreted as?

A

model is interpreted as probabilities that something occurred!

  • used for prediction/identification: based on certain factors, what is the probability that a person/observation falls into this group or that
    ex: the higher a person’s income, the greater likelihood he/she owns a car and drives themselves to work
45
Q

what does your beta coefficient represent in a pro bit regression?

A
  • estimated beta is the change in the z-value associated with a unit change in x
  • -if b is positive, a higher level of X is associated with a higher level of the z-value, therefore associated with a higher prob that y = 1
  • -if b is negative, a higher level of X is associated with a lower level of the z-value, and associated with a lower probablitliy that y = 1
46
Q

does STATA use a linear model when coming up with a regression equation for the data?

A

NO, it uses a maximum likelihood estimation

-likelihood that we observe the given Y values baed on our given X values

47
Q

the impact of a change in x on the z score is linear, but what about the impact on the probability?

A

IT IS NOT LINEAR.

-marginal effects will tell us the average, but this is misleading

48
Q

why is marginal effects of a probit misleading?

A

the average change in probability if a variable changed by x units is your MFX…however, this is not representative of the whole group
-the increase in probability is drastically effected by the spotting of the change

49
Q

what two different functions do a pro bit and a logit use?

A

probit: standard normal cumulative density function
logit: logistic cumulative density function

50
Q

do probits and log its have R^2?

A

they have pseudo R^2

-no sums of squares, can’t have R^2