Econ 391 final exam

when the level of confidence decreases, the margin of error a. becomes smaller b. stays the same c. becomes larger d. becomes smaller or larger, depending on the sample size

a. becomes smaller

when the confidence interval level decreases, the margin of error ___ a. decreases b. increases c. remains the same d. not enough info

a. decreases

for a t - test as the test statistic becomes farther from zero, the chance of rejecting the null hypothesis a. increases b. decreases c. doesn't change d. increase or decreases depending on which test stat

a. increases

for a t-test, as the test statistic becomes farther from zero, the chance of rejecting the null hypothesis a. increases b. decreases c. doesn't change d. increases or decreases depending on which test statistic

a. increases

if SSE = 300 and SST = 625, compute R^2 a. 0.48 b. 0.52 c. 0.68 d. 0.32

0.52 R^2 = SSR/SST R^2= 1-(SSE/SST) 1-(300/625)=0.52

90 percent

1.64 p-value = 0.10

95 percent

1.96 p-value= 0.05

99 percent

2.57 p-value = 0.01

nonresponse bias

a systematic difference in preferences between respondents and non-respondents to a survey or a poll

selective bias

a systematic exclusion of certain groups from consideration for the sample. The sample is not representative of the population intended to be analyzed

in a regression analysis, if SSE = 200 and SSR = 300, the coefficient of determination is: a. 0.60 b. 1.50 c. 0.66 d. 0.40

a. 0.60

A random sample of 9 students selected from the student body had an average height of 70 inches. We want to determine if the height of all the students at the university is significantly different from 68 inches. Assume the distribution of height is normally distributed with a standard deviation of 5 inches. a. 1.2 b. 1.4 c. 1.6 d. 1.8

a. 1.2 z=(70-68)/(5/srt 9) = 1.2

a student receives a test score of 70%. The teacher announces to the class that each student will have their test score increased by 3%. How many percentage points will this increase the students test? a. 2.1 b. 73 c. 6.3 d. 73.6

a. 2.1

The following output is a regression for delivery times in minutes for Deliveroo. How would we interpret an r-squared value of 0.72? A. 72% of the variation in delivery times is explained by the X's B. 0.72% of the variation in delivery times is explained by the X's C. 72% of the variation in the X's is explained by delivery times D. 0.72% of the variation in the X's is explained by delivery times

a. 72% of the variation in delivery times is explained by the X's

in a regression analysis if R^2 =1 then a. RSS =TSS b. RSS = 1 c. ESS = RSS d. ESS = TSS

a. RSS = TSS

A random sample of 9 students selected from the student body of a large university had an average height of 70 inches. We want to determine if the height of all the students at the university is significantly different from 68. Assume the distribution of height is normally distributed with a standard deviation 5 inches At a .05 level of significance, it can be concluded that the mean height is _____. a. not significantly different from 68 b. significantly different from 68 c. significantly less than 68 d. none of the above

a. not significantly different from 68 The critical value for α =0.05 is 1.96 Since 1.96 > 1.2 We fail to reject the null. Alternatively, you could look at a Z-table

if we ran a simple linear regression with our dependent variable being ice cream sales and our dependent variable being temp, what sign would we expect the coefficient on temp to be? Y(sales) = Bo + B1(temp) a. pos b. neg c. zero d. not enough info to say

a. pos

in a simple linear regression, if we can reject the null hypothesis of an f-test, we can also be certain that our only independent variable is statistically significant a. true b. false

a. true

increasing the confidence interval will increase the width of a confidence interval, all else constant. a. true b. false

a. true

taking a sample of Lexington residents will likely result in biased estimates compared to the entire population of Kentucky a. true b. false

a. true

the adjusted R^2 will fall if you add an additional independent variable (explanatory variable) that is not statistically significant a. true b. false

a. true

the assumed null hypothesis for regression coefficients is that Ho: Bo (is not significantly significant) a. true b. false

a. true

the f - stat from a regression output is used to test the significance of the entire model a. true b. false

a. true

the f-statistic from a regression output is used to test the significance of the entire model a. true b. false

a. true

If we change a 95% confidence interval estimate to a 99% confidence interval estimate, we can expect a. width of the CI to increase b. width of CI to decrease c. width of CI to remain the same d. sample size to increase

a. with of the CI to increase

calculate the variance inflation factor (VIF) for 2 variables where R^2 x1x2= 0.89 are they likely collinear A. Yes, because the VIF is greater than 5.0 B. Yes, because the VIF is greater than 1 C. No, because the VIF is less than 5.0 D. No, because the VIF is greater than 1

a. yes, because the VIF is greater than 5.0 VIF = 1/ (1-R^2x1x2) = 1/(1-.89)= 9.1

if X has a normal distribution with a mean of 50 and a standard deviation of 5, the probability P(40<=X<=55) can be written as: a. P(-2<=Z<=2) b. P(-2<=Z<=1) c. P(-1<=Z<=2) d. P(-1<=Z<=1)

b. P(-2<=Z<=1)

Suppose we run a regression but can only get the following partial output from excel : MS regression is 587.08 and the MS residual is 14.74 which of the following is the F stat a. 0.14 b. 39.82 c. 4.56 d. 3

b 39.82 F= MSR/MSE 587.08/14.74 = 39.82

on a standard normal curve, the area to the right of what z-score is 95%? a. 1.645 b. -1.645 c. 1.96 d. -1.96

b. -1.645

Math scores on the SAT are normally distributed with mean at 500 points and a standard deviation of 100 points. If 1000 students take the SAT how many would be expected to have a math score above 700 points? a .125 b. 23 c. 50 d. 47

b. 23

id SSE = 300 and SST = 625, compute SSR a. -325 b. 325 c. 925 d. 625

b. 325 SST = SSE + SSR

The following output is a regression for delivery times in minutes for Deliveroo. If weekend is an indicator for whether it is a weekend or not, how long do you expect to wait if you place 2 orders, five miles away on a Monday? intercept : 15 distance : 3 number of orders : 5 weekend : 18 a. 58 mins b. 40 mins c. 53 mins d. 20 mins

b. 40 mins =15+3(5)+5(2)+18(0)=40

interpret the coefficient for mileage ln(price)=23,000-.037 mileage a. a 1% increase in mileage leads to a 3.7% decrease in price b. a 1 mile increase in mileage leads to a 3.7% decrease in price c. a 1 mile increase in mileage leads to a .037% decrease in price d. a 1% increase in mileage leads to a $0.037 decrease in price

b. a 1 mile increase in mileage leads to a 3.7% decrease in price

a regression model in which more than one independent variable is used to predict the dependent variable is called a. a simple linear regression model b. a multiple regression model c. an independent model d. none of the answers is correct

b. a multiple regression model

a z-value of -1.75 represents a. a x-value of 1.75 SD above the mean b. a x-value of 1.75 SD below the mean c. a x-value 1.75 times larger than the mean d. a x-value 1.75 times smaller than the mean

b. a x-value of 1.75 SD above the mean

which is a way to increase the value of R^2? a. drop a variable from the model which is not particularly useful in predicting the dependent variable b. add an independent variable to the model which is useful for predicting the dependent variable c. correct the heteroskedasticity d. reduce multicollinearity by dropping an independent variable

b. add an independent variable to the model which is useful for predicting the dependent variable

Accounting for heteroskedasticity causes the T-statistic to A. Increase B. Decrease C. Remain Unchanged D. Become zero

b. decrease

if we dropped every independent variable except one, what would we expect to happen to the value of R^2 a. increase b. decrease c. not change d. not enough info

b. decrease

as the sample size increases, the margin or error a. increases b. decreases c. stays the same d. none of the above

b. decreases

suppose you want to test the hypothesis at the 99% level that avg height is less than 70 in, what will you conclusion be and why? a. fail to reject - 70 in is outside the CI b. fail to reject - 70 in is inside the CI c. reject- 70 in is outside CI d. reject - 70 in is inside CI

b. fail to reject - 70 in is inside the CI

adding an independent variable, which has no predictive power, to a regression model will usually lower the value of R^2 a. true b. false

b. false

an assumption of the classic regression model ( ordinary least squares) is that there is no multicollinearity a. true b. false

b. false

for data with a heteroskedasticity problem, the estimated coefficient parameters will be wrong if we dont correct for the heteroskedasticity? a. true b. false

b. false

the nominal distribution is always symmetric and centered around zero a. true b. false

b. false

the sample variance can be positive or negative a. true b. false

b. false

for = .05 , we reject the null hypothesis for a p-value that is 0.08 a. true b. false

b. false if bigger, fail to reject

which of the following will increase the width of a confidence interval a. increasing sample size b. increasing the level of confidence c. decreasing the level of confidence d. none of the above

b. increasing the level fo confidence if we increase the level of confidence, we are multiplying the standard error by a larger number when computing the margin of error, thus increasing the widths of the confidence interval

suppose we run a simple linear regression with college GPA as the DV , and distance from campus as the IV. If the slope coeffiecent on distance from campus is negative, how could we interpret this? Y(GPA) = Bo + B1(distance) + E a. living closer to campus causes people to be better students and earn higher GPAS b. living farther from campus is associated with a lower GPA c. a students GPA will increase if they move closer to campus d. a students GPA will decrease if they move closer to campus

b. living farther from campus is associated with a lower GPA

data on income America tends to have a very long right-tail. Knowing this, which value will be larger, median household income or mean household income? a. median household income b. mean household income c. they will be equal d. it depends on how far out the right-tail goes

b. mean household income

in a multivariable regression, if we know that one of the coefficients is statistically significant, what can we say about the conclusion of an f-test? a. we can't make an conclusions without know more info b. we will reject the null hypothesis because at least one variable is statistically different from zero c. we will fail to reject the null hypothesis because at least one variable is statistically different than zero d. we can conclude that the model as a whole does not predict our dependent variable

b. we will reject the null hypothesis because at least one variable is statistically different from zero

for some uniform distribution, there is a 40% probability of drawing an observation between 0 and 3. Assuming the distribution begins at 0, where does the distribution end a. 10 b. 8 c. 7.5 d. 6

c. 7.5

if the seller is selling a non-luxury good and decides to make the item a luxury good and increase the price by $3, what is the expected change in number of units sold, holding any advertising spending constant a. 103 units b. -10.8 units c. 92.2 units d. 113.8 units

c. 92.2 units

a snacks company wants to produce bags of chips with exactly 8 ounces of chips inside. They dont want anymore or any less. Which of the following are the correct hypotheses a. Ho : μ > 8 , Ha : μ <= 8 b. Ho : μ = 8 , Ha : μ >= 8 c. Ho : μ = 8 , Ha : μ doesn't = 8 d. Ho : μ <= 8 , Ha : μ > 8

c. Ho : μ = 8 , Ha : μ doesn't = 8

Given a simple regression of Wages and Years of School Log (wages) =-2.426 + 0.154(Schooling) How do you interpret the coefficient on X? A. On average, a one percent increase in schooling increases wages by $0.154 B. On average, an additional year of school increases wages by $1.54 C. On average, an additional year of school increases wages by 15.4% D. On average, an additional year of school increases wages by 0.154%

c. On average, an additional year of school increases wages by 15.4%

If two variables are completely uncorrelated, they will have a Variance Inflation Factor (VIF) that is: A. Negative B. Between zero and one C. Equal to one D. Greater than one

c. equal to 1 VIF = 1/1-0=1

the difference between the observed value and the predicted value is called a. SD b. variance c. error d. laffer's constant

c. error

the difference between the observed variable and the predicted value is called a. sd b. variance c. error d. laffers constants

c. error

which of the following measures is least affected by a single extreme value a. range b. mean c. median d. none of the above , all affected

c. median

suppose we found out that there is a heteroskedasticity problem that was not corrected. Are we able to tell whether the coefficient for luxury is statistically significant without correcting the standard errors? a. yes, the p-value is zero before correcting the standard errors, so it should be even lower after correcting the standard errors b. yes, the p-value will increase, but not enough to make the coefficient insignificant c. no, we can't know how much the p-value will change without running the corrected regression d. no, the coefficient will now be insignificant after correcting the standard error

c. no, we can't know how much the p-value will change without running the corrected regression

The following output is a regression for delivery times in minutes for Deliveroo. How would you interpret the coefficient on weekends? intercept : 15 distance : 3 number of orders : 5 weekend : 18 A. On average, deliveries take 18 minutes longer on weekends. B. Deliveries take 18 minutes longer on weekdays. C. On average, deliveries take 18 minutes longer on weekends all else constant. D. Deliveries take 18 minutes less on weekends, all else constant.

c. on average, deliveries take 18 minutes longer on weekends all else constant

Regression analysis is a statistical procedure for developing a mathematical equation that describes how a. one independent and one or more dependent variables are related b. several independent and several dependent variables are related c. one dependent and one or more independent variables are related d. none of the answers are correct

c. one dependent and one ore more independent variables are related

what relationship does the following data have a. pos and linear b. neg and linear c. pos and non linear d. neg and non linear

c. pos and non linear

when we construct a confidence interval, what is our parameter of interest a. the variance b. the standard deviation c. the mean d. range

c. the mean

below is the estimated regression equation of car price on milage. which is the correct interpretation of the coefficient on mileage? a. the price of a car decreases by 23,000 for every mile a car is driven b. the price of a car decreases by 57 cents for every mile a car is driven c. the prices of a car decrease by 57 cents for every additional mile that car is driven, on average d. on average driving a car another mile will increase the value of that car by 57 cents

c. the prices of a car decrease by 57 cents for every additional mile that car is driven, on average

If coefficient estimates are not consistent, we expect A. The coefficient estimates to be unreliable. B. The t-statistics to be correct C. The standard errors to be unreliable D. The coefficient estimates to be biased.

c. the standard errors to be unreliable

t - statistic

coefficient divided by the standard error

if X has a normal distribution with a mean of 50 and a SD of 5, the probability P(40<=X<=55)is a. 0.14 b. 0.56 c. 0.95 d. 0.82

d. 0.82 = P(X<=55) - P(X<=40) = P(X<=1) - P(X<=-2) = 0.84 - 0.02275 = 0.82

a person wants to buy a laptop which costs $1000. when he purchases the laptop, he first applies a 20% discount and then uses a $15 off coupon. what percent of the cost of the laptop was removed by the discount and the coupon? a. 35% b. 24.5% c. 78.5% d. 21.5%

d. 21.5%

for a uniform distribution form 3 to 10, what is the probability of an observation being between 6 and 8 a. 20% b. 865 c. 43% d. 29%

d. 29%

You read in a Facebook post that unemployment has decreased by 2 percentage points. Previously, the unemployment rate was at 6%. This means the current unemployment rate is? A. 5.88% B. 2% C. 5.98% D. 4%

d. 4%

suppose you construct a 95% CI based on a sample of students' height and find a confidence interval of (67.3, 70.2). what is the point estimate for students' avg height a. 67.3 b. 70.2 c. 69.5 d. 68.75

d. 68.75

The following output is a regression for delivery times in minutes for Deliveroo (a food delivery app). Which of the following variables is statistically significant at the 5% level. a. # of order b. weekend c. intercept d. distance

d. distance distance p-value is .001 and .05>.001

which of the following will decrease the width of a confidence interval? a. increase the CI b. increase the sample mean c. increase the margin of error d. increase the sample mean

d. increase the sample mean

which of the following regarding the adjusted R^2 is false a. can be used to determine whether or not an independent variable should be added to a model or not b. it is a measure of how much variation in the dependent variable is explained by the independent variables c. it is generally preferred to the R^2 because it takes into account whether the variables you added to the regression equation are irrelevant or not d. it shows the direction of the relationship between the 2 variables being compared

d. it shows the direction of the relationship between the 2 variables being compared R^2 says nothing about the relationship of the direction of variables being compared, it is a tool to help compare which model better explains the variation in the data

which descriptive statistic doesn't give info about the spread of the data? a. range b. standard deviation c. variane d. mean

d. mean

when the mean decreases, the confidence interval ___ a. expands b. contracts c. remains the same d. none of the above

d. none of the above

given a simple regression between likes on your last post (Y in hundreds) and number of followers on instagram (X) : y = -2 + 0.04X How do you interpret the coefficient of X A. On average an additional like on your last post increase your followers by 0.04. B. On average an additional follower increases your likes on the last post by 0.04. C. On average an additional like on your last post increase your followers by 4. D. On average an additional follower increases your likes on the last post by 4.

d. on average an additional follower increases your likes on the last post by 4

for a simple linear regression of car price (Y) on mileage (X), what is the correct interpretation of Bo, the intercept? a. the price of a car for a car with avg mileage b. a one unit increase in X increases Y by Bo dollars c. the mileage of a car when the price is zero d. the avg price of a car with zero mileage

d. the average price of a car with zero mileage

which factor does not affect the size of the margin of error? a. the confidence interval b. the sample size c. the amount of variability in the population d. the sample mean

d. the population mean

if we run a simple linear regression and find an R^2 = 0.12, we can conclude which of the following a. there is a relationship between X and Y b. there is a strong relationship between X and Y c. there is a non-linear relationship between X and Y d. the variation in X explains 12 percent of the variation in Y

d. the variation in X explains 12 % of the variation in Y

which statement about homoscedasticity is not correct? a. a key assumption of the classic regression model (ols) is homoscedasticty b. homoscedasticity requires that the standard errors are constant across all x's c. coefficient estimates are correct under heteroskedasticity d. when heteroskedasticity is present, standard errors do not depend on any independent variable

d. when heteroskedasticity is present, standard errors do not depend on any independent variable