Question 1

What is a static time-series model? Why might you prefer to estimate a more-advanced time-series model? Explain.

Accepted Answer

A static time-series model is one in whi

Question 2

Distributed lag models control for differences across time periods by

Accepted Answer

A) estimating the sample regression function by OLS. 
B) including lagged dependent variables in the estimated sample regression function. 
C) including lagged independent variables in the estimated sample regression function. 
D) including both lagged dependent and lagged independent variables in the estimated sample regression function. 
A) estimating the sample regression function by OLS. 
B) including lagged dependent variables in the estimated sample regression function. 
C) including lagged independent variables in the estimated sample regression function. 
D) including both lagged dependent and lagged independent variables in the estimated sample regression function.

Question 3

Suppose you estimate the following the degree to which HDTV sales (in millions of units)are related to price,consumer income,and a time-trend as (p-values in parentheses)

$$\begin{array} { lllll } 
HD\widehat {TV~ S}ales  _ { t } =& 15.43 -& 0.168   \text {Price} +& 0.247  \text {Income } +& 3.52  \text {Time Trend }\
& ( 0.023 )&  ( 0.102 ) &  ( 0.028 )& ( 0.046 ) \

\end{array}$$
You should conclude that the data do

Accepted Answer

A) not exhibit a time-trend because the estimated coefficient for Price is not statistically significant. 
B) exhibit a time-trend because the estimated coefficient for Income is positive and statistically significant. 
C) not exhibit a time-trend because the estimated coefficient for the Time Trend is positive. 
D) exhibit a time-trend because the estimated coefficient for the Time Trend is statistically significant. 
A) not exhibit a time-trend because the estimated coefficient for Price is not statistically significant. 
B) exhibit a time-trend because the estimated coefficient for Income is positive and statistically significant. 
C) not exhibit a time-trend because the estimated coefficient for the Time Trend is positive. 
D) exhibit a time-trend because the estimated coefficient for the Time Trend is statistically significant.

Question 4

How does time-series data differ from cross-section data? Why is this difference important? Explain.

Accepted Answer

Time-series data is data collected acros

Question 5

What does it mean for a time-series to be weakly dependent? Why is this desirable? Explain.

Accepted Answer

A time-series is weakly-dependent if the

Question 6

You can control for quarterly seasonality in your data by

Accepted Answer

A) de-trending your time-series data. 
B) including a time-trend in your regression. 
C) including binary dummy variables for all four quarters in your regression. 
D) including binary dummy variables for three of the four quarters in your regression. 
A) de-trending your time-series data. 
B) including a time-trend in your regression. 
C) including binary dummy variables for all four quarters in your regression. 
D) including binary dummy variables for three of the four quarters in your regression.

Question 7

A given time-series is said to have a time-trend if

Accepted Answer

A) an unexpected shift in time-series data. 
B) the data trend upward or downward over time. 
C) a number of outliers in cross-section data. 
D) an independent variable is correlated with the dependent variable but there is no theoretical justification for the relationship. 
A) an unexpected shift in time-series data. 
B) the data trend upward or downward over time. 
C) a number of outliers in cross-section data. 
D) an independent variable is correlated with the dependent variable but there is no theoretical justification for the relationship.

Question 8

Seasonality occurs when

Accepted Answer

A) time-series data move upward or downward over time. 
B) time-series data follows similar patterns during specific seasons of the year. 
C) an unexpected shift occurs in time-series data. 
D) an independent variable is correlated with the dependent variable but there is no theoretical justification for the relationship. 
A) time-series data move upward or downward over time. 
B) time-series data follows similar patterns during specific seasons of the year. 
C) an unexpected shift occurs in time-series data. 
D) an independent variable is correlated with the dependent variable but there is no theoretical justification for the relationship.

Question 9

You can control for a potential time-trend in your data by

Accepted Answer

A) not including spuriously correlated variables in your regression. 
B) including dummy variables for three of the four quarters in your regression. 
C) de-trending the data before performing OLS. 
D) performing weighted least squares by diving the initial data by the estimate coefficient on the time-trend variable. 
A) not including spuriously correlated variables in your regression. 
B) including dummy variables for three of the four quarters in your regression. 
C) de-trending the data before performing OLS. 
D) performing weighted least squares by diving the initial data by the estimate coefficient on the time-trend variable.

Question 10

You can perform out-of-sample prediction by estimating the sample regression function for

Accepted Answer

A) all of the data,using the results to predict outcomes for all of the data,and comparing the predicted outcomes to the actual outcomes. 
B) a subset of the data,using the results to predict outcomes for all of the data,and comparing the predicted outcomes to the actual outcomes. 
C) all of the data,using the results to predict outcomes for a subset of the data,and comparing the predicted outcomes to the actual outcomes. 
D) a subset of the data,using the results to predict outcomes for the subset not included in the regression,and comparing the predicted outcomes to the actual outcomes. 
A) all of the data,using the results to predict outcomes for all of the data,and comparing the predicted outcomes to the actual outcomes. 
B) a subset of the data,using the results to predict outcomes for all of the data,and comparing the predicted outcomes to the actual outcomes. 
C) all of the data,using the results to predict outcomes for a subset of the data,and comparing the predicted outcomes to the actual outcomes. 
D) a subset of the data,using the results to predict outcomes for the subset not included in the regression,and comparing the predicted outcomes to the actual outcomes.

Question 11

You can control for a potential time-trend in your data by including a _____ in your regression.

Accepted Answer

A) variable that increases by 1 for each successive time-period 
B) binary dummy variable indicating a time-trend 
C) lagged dependent variable 
D) variable indicating the current time-period 
A) variable that increases by 1 for each successive time-period 
B) binary dummy variable indicating a time-trend 
C) lagged dependent variable 
D) variable indicating the current time-period

Question 12

Suppose you wish to estimate the marginal effect that income has on consumption for in a time-series for a given country.The static time-series model would be specified as

Accepted Answer

A)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \beta _ { 2 } \text { Income } _ { i - 1 } + \varepsilon _ { t } \text {. }$ 
B)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \varepsilon _ { t } \text {. }$ 
C)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \varepsilon _ { i } \text {. }$ 
D)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \beta _ { 2 } \text { Income } _ { t - 1 } + \varepsilon _ { t } \text {. }$ 
A)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \beta _ { 2 } \text { Income } _ { i - 1 } + \varepsilon _ { t } \text {. }$ 
B)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \varepsilon _ { t } \text {. }$ 
C)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \varepsilon _ { i } \text {. }$ 
D)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \beta _ { 2 } \text { Income } _ { t - 1 } + \varepsilon _ { t } \text {. }$

Question 13

You can perform forecasting by

Accepted Answer

A) making an educated guess as to what the value of the dependent variable will be at some point in the future. 
B) regression future dependent variables of future independent variables. 
C) using the results of regression analysis to predict the value of the dependent variable will be at some point in the future. 
D) using the results of regression analysis to predict the value of the dependent variable in a past period and comparing the predicted value to the actual value. 
A) making an educated guess as to what the value of the dependent variable will be at some point in the future. 
B) regression future dependent variables of future independent variables. 
C) using the results of regression analysis to predict the value of the dependent variable will be at some point in the future. 
D) using the results of regression analysis to predict the value of the dependent variable in a past period and comparing the predicted value to the actual value.

Question 14

What is a distributed lag model? Why is it preferable to a static time-series model? Explain.

Accepted Answer

A distributed lag model is one that incl

Question 15

Suppose you wish to estimate the marginal effect that income has on consumption.The distributed lag model would be specified as

Accepted Answer

A)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \beta _ { 2 } \text { Income } _ { i - 1 } + \varepsilon _ { t } \text {. }$ 
B)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \varepsilon _ { t }$ 
C)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \varepsilon _ { i } \text {. }$ 
D)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \beta _ { 2 } \text { Income } _ { t - 1 } + \varepsilon _ { t } \text {. }$ 
A)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \beta _ { 2 } \text { Income } _ { i - 1 } + \varepsilon _ { t } \text {. }$ 
B)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \varepsilon _ { t }$ 
C)  $\text { Consumption } _ { i } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { i } + \varepsilon _ { i } \text {. }$ 
D)  $\text { Consumption } _ { t } = \beta _ { 0 } + \beta _ { 1 } \text { Income } _ { t } + \beta _ { 2 } \text { Income } _ { t - 1 } + \varepsilon _ { t } \text {. }$

Question 16

Suppose you include a time trend in your model of U.S.Personal Consumption Expenditures (billions)on U.S.Personal Income (billions)using quarterly data for the period 1969Q1-2013Q3 and you get $$\begin{array} { l } 
\text { Consumption } _ { t } = &- 69.616 + &0.877 \text { Income } _ { t } -& 4.427 \text { Time Trend } _ { t } \
&( 13.460 )& ( 0.007 )& ( 0.572 ) \
&&n = 179 \
&&R ^ { 2 } = .9995
\end{array}$$ 
a)Explain how to create the time trend variable.
b)Interpret the time trend variable and comment if it is statistically significant.
c)Explain how to detrend both the dependent and independent variable.

Accepted Answer

a)It is easy to create the time trend va

Question 17

What does it mean to de-trend your data? How can you do so? Explain.

Accepted Answer

"De-trending" the data refers to the pro

Question 18

Spurious regression occurs

Accepted Answer

A) an unexpected shift in time-series data. 
B) a number of outliers in cross-section data. 
C) a general upward trend over time in time-series data. 
D) an independent variable is correlated with the dependent variable but there is no theoretical justification for the relationship. 
A) an unexpected shift in time-series data. 
B) a number of outliers in cross-section data. 
C) a general upward trend over time in time-series data. 
D) an independent variable is correlated with the dependent variable but there is no theoretical justification for the relationship.

What is a static time-series model? Why might you prefer to estimate a more-advanced time-series model? Explain.

Distributed lag models control for differences across time periods by

Suppose you estimate the following the degree to which HDTV sales (in millions of units)are related to price,consumer income,and a time-trend as (p-values in parentheses) HDale= 15.43- 0.168 Price + 0.247 Income + 3.52 Time Trend (0.023) (0.102) (0.028) (0.046) You should conclude that the data do

How does time-series data differ from cross-section data? Why is this difference important? Explain.

What does it mean for a time-series to be weakly dependent? Why is this desirable? Explain.

You can control for quarterly seasonality in your data by

A given time-series is said to have a time-trend if

Seasonality occurs when

You can control for a potential time-trend in your data by

You can perform out-of-sample prediction by estimating the sample regression function for

You can control for a potential time-trend in your data by including a _____ in your regression.

Suppose you wish to estimate the marginal effect that income has on consumption for in a time-series for a given country.The static time-series model would be specified as

You can perform forecasting by

What is a distributed lag model? Why is it preferable to a static time-series model? Explain.

Suppose you wish to estimate the marginal effect that income has on consumption.The distributed lag model would be specified as

What does it mean to de-trend your data? How can you do so? Explain.

Spurious regression occurs

An Introduction to Econometrics and Statistical Inference

Collection and Management of Data

Summary Statistics

Simple Linear Regression

Hypothesis Testing in Linear Regression Analysis

Multiple Linear Regression Analysis

Qualitative Variables and Non-Linearities in Multiple Linear Regression Analysis

Model Selection in Multiple Linear Regression Analysis

Heteroskedasticity

Auto-Correlation

Limited Dependent Variables

Panel Data

Instrumental Variables for Simultaneous Equations, Endogenous Independent Variables, and Measurement Error

Quantile Regression, Count Data, Sample Selection Bias, and Quasi-Experimental Methods

Filters

Exam 10: Time Series Analysis

What is a static time-series model? Why might you prefer to estimate a more-advanced time-series model? Explain.

Distributed lag models control for differences across time periods by

Suppose you estimate the following the degree to which HDTV sales (in millions of units)are related to price,consumer income,and a time-trend as (p-values in parentheses) HDale= 15.43- 0.168 Price + 0.247 Income + 3.52 Time Trend (0.023) (0.102) (0.028) (0.046) You should conclude that the data do

How does time-series data differ from cross-section data? Why is this difference important? Explain.

What does it mean for a time-series to be weakly dependent? Why is this desirable? Explain.

You can control for quarterly seasonality in your data by

A given time-series is said to have a time-trend if

Seasonality occurs when

You can control for a potential time-trend in your data by

You can perform out-of-sample prediction by estimating the sample regression function for

You can control for a potential time-trend in your data by including a _____ in your regression.

Suppose you wish to estimate the marginal effect that income has on consumption for in a time-series for a given country.The static time-series model would be specified as

You can perform forecasting by

What is a distributed lag model? Why is it preferable to a static time-series model? Explain.

Suppose you wish to estimate the marginal effect that income has on consumption.The distributed lag model would be specified as

What does it mean to de-trend your data? How can you do so? Explain.

Spurious regression occurs

An Introduction to Econometrics and Statistical Inference

Collection and Management of Data

Summary Statistics

Simple Linear Regression

Hypothesis Testing in Linear Regression Analysis

Multiple Linear Regression Analysis

Qualitative Variables and Non-Linearities in Multiple Linear Regression Analysis

Model Selection in Multiple Linear Regression Analysis

Heteroskedasticity

Auto-Correlation

Limited Dependent Variables

Panel Data

Instrumental Variables for Simultaneous Equations, Endogenous Independent Variables, and Measurement Error

Quantile Regression, Count Data, Sample Selection Bias, and Quasi-Experimental Methods

Filters