MINITAB ASSIGNMENT ECO FORCASTING TEST

Question 1.1. What are at lest two diagnostic checks you should apply to a Box-Jenkins model to determine its reliability (excluding error measures such as MSE, RMSE, etc.)? (Points : 3.5)

    t-test of the coefficients and residual lag Chi-square values.
       constant term p-test and residual SSE
       Lag Chi-square value of the coefficients and standard error of the residuals
       None of the above determine reliability.

Question 2.2. The “I” in the ARIMA technique represents (Points : 3.5)

       the minimum error that is generated by the Moving Average process.
       the individual correlations for each lag period
       differencing to create a stationary data series.
       autoregressiveness of the appropriate model

Question 3.3. Given the following Chi-Square statistics from and ARIMA model at 95% confidence the residuals are not significantly autoregressive
Lag             12        24       36       48
Chi-Square 13.0     28.8    60.5     68.5
DF              10        22       34       46
P-Value   0.222     0.152   0.003   0.017 (Points : 3.5)

       only through the 12th lag.
       at least through the 24th lag.
       after the 24th lag.
       in none of the lags.

Question 4.4. The AR and MA and ARMA model forms can be applied to data with what major requirements? (Points : 3.5)

       Adequate time series data.
       Data that is stationary relative to trend and seasonality.
       Data that is non-linear.
       Data that has been deseasonalized (seasonal effects removed).
       Only 1 and 2 above.

Question 5.5. What two autoregressive statistics are used to determine the type of ARIMA model that may be appropriate? (Points : 3.5)

       standard deviation and variance
       data mean and residual variance
       autocorrelation and partial autocorrelation
       correlation coefficient and F value

Question 6.6. A second order MA model implies that (Points : 3.5)

       the autocorrelation function of the data has two significant early lags.
       there are two coefficients in the ARIMA model excluding the constant term.
       the partial autocorrelation function of the data has two significant lags.
       1. and 2. above
       none of the above.

Question 7.7. Given an ARIMA model of monthly data described by the menu (1,3,0)(2,2,0) how many data observations will be lost due to differencing to make the series stationary? (Points : 3.5)

       24
       5
       27
       25
       30

Question 8.8. Natural log data transformation is useful because it (Points : 3.5)

       enables ARIMA to be run with fewer observations.
       reduces the number of data differences required.
       can make curvilinear time series have linear characteristics.
       reduces the chance of type 1 error.

Question 9.9. A data series required one seasonal difference and two non seasonal differences to make it stationary. You have found two early spikes in the partial autocorrelation function after the non seasonal differences with converging autocorrelations. In addition you found one early lag spike in the autocorrelation function for the seasonal differenced data along with converging partial autocorrelations. Which is the appropriate ARIMA menu for the model? (Points : 3.5)

       (1,0, 1)(2,2,0)
       (2,2,0)(0,1,1)
       (2,2,1)(2,1,0)
       (1,2,0)(2,1,0)

Question 10.10. The major disadvantages of differencing to make data stationary include (Points : 3.5)

       Observations (degrees of freedom) will be lost and it requires a large amount of data.
       Lost observations have influence on the significance of the ARIMA model.
       Too many differences are taken the differenced data series becomes more autoregressively unstable.
       All of the above.
       None of the above since differencing does not influence the data characteristics or the model outcome.

Question 11.11. What is the rule of parsimony in ARIMA forecasting? (Points : 3.5)

       Better forecast results can be obtained from more complex ARIMA models
       Simpler models are preferred due to fewer data differences.
       The less complex the model given the same results the better..
       Everything being equal, ARIMA forecast accuracy is enhanced by adding more significant coefficients.

Question 12.12. Given the ARIMA menus below which will result in 4 model coefficients excluding a constant term? (Points : 3.5)

       (1,1,2)(2,1,0)
       (0,1,2)(1,2,1)
       (0,2,1)(1,2,0)
       (1,2,0)(1,2,0)

Question 13.13. In an ARIMA model with monthly data how many coefficients (excluding the constant term) are in the ARIMA model specified as (1,1,2)(0,1,1) and how many observations are 
lost due to differencing? (Points : 3.5)

       3 coefficients and 5 observations lost
       2 coefficients and 12 observations lost
       4 coefficients and 13 observations lost
       3 coefficients and 14 observations lost

Question 14.14. Which ARIMA model type is used to derive forecasts of a variable based only on a linear function of its past data values? (Points : 3.5)

       a moving average model
       a second order moving average model
       an ARMA model
       an autoregressive model

Question 15.15. The Chi-Square values in ARIMA results determine the (Points : 3.5)

       need for additional differencing.
       strength of the ARIMA model.
       autoregressiveness of the ARIMA residuals.
       normality of the residual distribution.

Question 16.16. Autocorrelations differ from partial autocorrelations in that (Points : 3.5)

       autocorrelation is the total effect correlation between lag values of a time series that could include previous lag autoregressive effects while partial autocorrelation is the direct correlation only between the specific lag value and the data observation.
       in autocorrelation other lag effects are allowed to vary while in partial autocorrelation the other lagged effects are held constant.
       partial autocorrelation is the indirect correlation only between the specific lag value of the variable and the variable observation while autocorrelation is the direct effect be observations and the lagged observations.
       partial autocorrelation is closer to true correlation since the significance can be measured by t values while autocorrelation cannot.
       only 1 and 2 above.

Question 17.17. You have a quarterly data series ACFs and the first four autocorrelation are significantly different from zero while the subsequent autocorrelations decreases slowly toward zero. In addition the autocorrelations for lag 8, 12 and 16 are significantly different from zero. What are your data autoregressive characteristics? (Points : 3.5)

       trend and cycle
       trend and seasonality
       only cycle
       only seasonality
       non linearity

Question 18.18. In the standard ARIMA menu notation what does P stand for? (Points : 3.5)

       The measure of the probability of residuals equal to zero
       For the observed non seasonal moving average (MA) tendencies
       For the observed seasonal autoregressive (AR) tendencies
       For the observed non seasonal autoregressive (AR) tendencies
       For the MA significant ACF spikes

Question 19.19. What is the value of the coefficient if the standard error of the coefficient is 1.25 and the t-value is 2.80? (Points : 3.5)

       3.5
       446
       2.24
       1.56

Question 20.20. Some ARIMA models do not require a constant term.  What determines the need for it? (Points : 3.5)

       The t-value of the coefficients.
       The LBQ values.
       The mean value of the residuals.
       The mean value of the last differenced data series.

Question 21.21. Given the data found in DocSharing under Exam 2 Data Problem 21 what is the first differenced value of the second seasonal difference of the sales data? (Take 2 seasonal differences) (Points : 6)

       110
       -15
       -143
       25
       21

Question 22.22. Given the following data for monthly pickup truck sales for a large Texas dealership. Determine the best ARIMA model to apply and select the menu for the model in (0,0,0)(0,0,0) form. (Remember that I will only accept this ARIMA model with non-significant residuals.)
Note that you must obtain the monthly truck data from Exam 2 Data, Problem 22 tab found in DocSharing. Do not take a hold out from this data.
(Points : 6)

       (0,1,0)(1,1,1) an Seasonal ARMA  model with one seasonal difference and a MA1 model with one non seasonal difference
       (0,1,1) (1,1,1) a seasonal ARMA model with one seasonal difference and an MA1 non seasonal model with one non seasonal difference
       (1,1,0)(0,0,0) an AR 1 model with one non seasonal difference
       (1,1,1)(1,1,0) a seasonal AR model with one seasonal difference and a non seasonal ARMA model with one non seasonal difference
       (1, 2, 0) (1,1,0) A seasonal AR model with one seasonal difference and a non seasonal AR model with two non seasonal differences.

Question 23.23. What are the significant coefficient(s) of the best ARIMA model found in the question above excluding the constant term? (Points : 6)

       .3833, .2930 and -.3209
       .7375 and .0394
       .9432
       -.4321, and .2839
       -.2836, .7280 and .8890

Question 24.24. What is the fit period MAPE of the best ARIMA model? (Points : 6)

       2.503
       4.320
       1.404
       -.3234

Question 25.25. What is the forecast value for the 6th month from the end of the data series? Develop a forecast with the best ARIMA model—then choose the value for the 6the month. (Points : 6)

       353.234
       432.365
       143.334
       135.147
       134.595

Time Remaining: