|
Sample Exam Questions
(from Past Tests)
Note: The correct answer is followed by **. The code [i - j] refer to which section of the text the question is designed to address.
1. What factors do the five data smoothing techniques presented in Chapter Three have in common?
A) They all use only past observations of the data.
B) They all fail to forecast cyclical reversals in the data.
C) They all smooth short-term noise by averaging data.
D) They all product serially correlated forecasts.
E) All the above are correct. **
[3-1]
2. A simple-centered 3-point moving average of the time-series variable Xt is given by:
A) (Xt-1 + Xt-2 + Xt-3)/3.
B) (Xt + Xt-1 + Xt-1)/3.
C) (Xt+1 + Xt + Xt-1)/3. **
D) None of the above are correct.
[3-2]
3. Moving-average smoothing may lead to misleading inference when applied to
A) stationary data.
B) forecasting trend reversal in the stock market. **
C) small and limited data sets.
D) large and plentiful data sets.
E) None of the above are correct.
[3-2]
4. Which of the following is not correct concerning choosing the appropriate size of the smoothing constant (a) in the simple exponential smoothing model?
A) Select values close to zero if the series has a great deal of random variation.
B) Select values close to one if you wish the forecast values to depend strongly on recent changes in the actual values.
C) Select a value that minimizes RMSE.
D) Select a value that maximizes mean-squared error. **
E) All the above are correct.
[3-3]
5. The smoothing constant (a) of the simple exponential smoothing model
A) should have a value close to one if the underlying data is relatively erratic.
B) should have a value close to zero if the underlying data is relatively smooth.
C) is closer to zero, the greater the revision in the current forecast given the current forecast error.
D) is closer to one, the greater the revision in the current forecast given the current forecast error. **
[3-3]
6. The least squares procedure minimizes the
A) sum of the residuals.
B) square of the maximum error.
C) sum of absolute errors.
D) sum of squared residuals. **
E) None of the above are correct.
[4-1]
7. A residual is
A) the difference between the mean of Y conditional on X and the unconditional mean.
B) the difference between the mean of Y and its actual value.
C) the difference between the regression prediction of Y and its actual value. **
D) the difference between the sum of squared errors before and after X is used to predict Y.
E) None of the above are correct.
[4-1]
8 Regression model disturbances (forecast errors)
A) are assumed to follow a normal probability distribution.
B) are assumed to be independent over time.
C) are assumed to average to zero.
D) can be estimated by OLS residuals.
E) All of the above are correct. **
[4-1]
9. Seasonal indices of sales for the Black Lab Ski Resort are for January 1.20; and December .80. If December sales for 1998 were $5,000, a reasonable estimate of sales for January 1999 is:
A) $4,800.
B) $6,000.
C) $7,500. **
D) $10,000.
E) None of the above are correct.
[4-5]
10. Which of the following techniques are not used to solve the problem of autocorrelation?
A) Autoregressive models.
B) Improving the model specification.
C) Moving average smoothing. **
D) First differencing the data.
E) Regression using percentage changes.
[4-6]
11. Which of the following is not a consequence of serial correlation?
A) The OLS slope estimates are now unbiased.
B) The OLS prediction intervals are biased.
C) The R-squared is less than .5. **
D) Point estimates are unbiased.
E) None of the above are correct.
[4-6]
12. Autocorrelation leads to or causes:
A) Heteroscedasticity.
B) Serial correlation.
C) Spurious regression. **
D) Nonlinear regression.
E) All the above are correct.
[4-6]
13. Exact prediction intervals for the dependent variable
A) are bow-shaped around the estimated regression line. **
B) Are linear around the estimated regression line.
C) do not take the variability of Y around the sample regression into account.
D) do not take the randomness of the sample into account.
E) None of the above are correct.
[4-6]
Short Problem Example
14. A bivariate linear regression model relating domestic travel expenditures (DTE) as a function of income per capita (IPC) was estimated as:
DTE = -9589.67 + .953538 (IPC)
Forecast DTE under the assumption that IPC will be $14,750. Make the appropriate point and approximate 95 percent interval estimates, assuming that the estimated regression error variance was 2,077,230.38.
ANSWER:
The point estimate of DTE is:
DTE = -9589.67 + .953538 (14,750) = 4,475.02.
The standard error of the regression is 1441.26, and the approximate 95% confidence interval is:
4,475.02 ± (2)(1441.26)
4,475.02 ± 2882.52
P[1592.50 < DTE < 7357.54] = .95.
b) Given that actual DTE turned out to be $7,754 (million), calculate the percentage error in your forecast.
ANSWER:
If the actual value of DTE is $7,754, the percentage error in the forecast, based on the point estimate of $4475.02, is 42.3%.
[(7754 - 4475.02)/7754] = .423.
15 If it is found that the forecast errors from a ARIMA-type model exhibit serial correlation, such model
A) is not an adequate forecasting model. **
B) is a candidate for adding another explanatory variable.
C) almost surely contains seasonality.
D) is a candidate for Cochrane-Orcutt regression.
E) All of the above are correct.
[7-2]
16. Moving-average models are best described as
A) simple averages.
B) non-weighted averages.
C) weighted averages of white noise series. **
D) weighted averages of non-normal random variates.
E) None of the above are correct.
[7-3]
17. Which of the following patterns of the partial autocorrelation function correlogram is inconsistent with an underlying autoregressive data process?
A) Exponentially declining to zero.
B) Cyclically declining to zero.
C) Positive at first, then negative and increasing to zero.
D) Negative at first, then positive and declining to zero.
E) All of the above are correct. **
[7-4]
18 The autocorrelation function of a time series shows coefficients significantly different from zero at lags 1 through 4. The partial autocorrelation function shows one spike and monotonically increases to zero as lags length increases. Such a series can be modeled as a _____ model.
A) ARMA(1, 4). **
B) ARMA(2, 4).
C) MA(3).
D) ARMA(4, 1).
E) None of the above are correct.
[7-5]
19. Which of the following is not a first-step in the ARIMA model selection process?
A) Examine the autocorrelation function of the raw series.
B) Examine the partial autocorrelation function of the raw series.
C) Test the data for stationarity.
D) Estimate an ARIMA(1,1,1) model for reference purposes. **
E) All of the above are correct.
[7-7]
20 What is the null hypothesis being tested using the Box-Pierce statistic?
A) The set of autocorrelations is jointly equal to zero. **
B) The set of autocorrelations are jointly not equal to zero.
C) The set of autocorrelations are jointly equal to one.
D) The set of autocorrelations are jointly not equal to one.
E) All of the above are incorrect.
[7-7]
21. The main purpose of combining forecasts is to reduce
A) bias.
B) mean forecasting bias.
C) mean squared forecasting error. **
D) mean absolute forecasting error.
E) All the above are correct.
[8-2]
22. Which of the following is an advantage to using the adaptive approach to estimate the optimal weights in the forecast combination process?
A) The weights change from period to period. **
B) A test of the combined forecast model bias can be performed.
C) The covariance between error variances is utilized.
D) Weights are chosen so as to maximize regression error variance.
E) All of the above are correct.
[8-6]
|
