ECO 550 Chapter 5—Business and Economic Forecasting

Chapter 5—Business and Economic Forecasting

MULTIPLE CHOICE

    1.    Time-series forecasting models:
a.    are useful whenever changes occur rapidly and wildly
b.    are more effective in making long-run forecasts than short-run forecasts
c.    are based solely on historical observations of the values of the variable being forecasted
d.    attempt to explain the underlying causal relationships which produce the observed outcome
e.    none of the above

    2.    The forecasting technique which attempts to forecast short-run changes and makes use of economic indicators known as leading, coincident or lagging indicators is known as:
a.    econometric technique
b.    time-series forecasting
c.    opinion polling
d.    barometric technique
e.    judgment forecasting

    3.    The use of quarterly data to develop the forecasting model Yt = a +bYt1 is an example of which forecasting technique?
a.    Barometric forecasting
b.    Time-series forecasting
c.    Survey and opinion
d.    Econometric methods based on an understanding of the underlying economic variables involved
e.    Input-output analysis

    4.    Variations in a time-series forecast can be caused by:
a.    cyclical variations
b.    secular trends
c.    seasonal effects
d.    a and b only
e.    a, b, and c

5.    The variation in an economic time-series which is caused by major expansions or contractions usually 
of greater than a year in duration is known as:
a.    secular trend
b.    cyclical variation
c.    seasonal effect
d.    unpredictable random factor
e.    none of the above

    6.    The type of economic indicator that can best be used for business forecasting is the:
a.    leading indicator
b.    coincident indicator
c.    lagging indicator
d.    current business inventory indicator
e.    optimism/pessimism indicator

    7.    Consumer expenditure plans is an example of a forecasting method. Which of the general categories best described this example?
a.    time-series forecasting techniques
b.    barometric techniques
c.    survey techniques and opinion polling
d.    econometric techniques
e.    input-output analysis

    8.    In the first-order exponential smoothing model, the new forecast is equal to a weighted average of the old forecast and the actual value in the most recent period.
a.    true
b.    false

    9.    Simplified trend models are generally appropriate for predicting the turning points in an economic time series.
a.    true
b.    false

    10.    Smoothing techniques are a form of ____ techniques which assume that there is an underlying pattern to be found in the historical values of a variable that is being forecast.
a.    opinion polling
b.    barometric forecasting
c.    econometric forecasting
d.    time-series forecasting
e.    none of the above

    11.    Seasonal variations can be incorporated into a time-series model in a number of different ways, including:
a.    ratio-to-trend method
b.    use of dummy variables
c.    root mean squared error method
d.    a and b only
e.    a, b, and c

12.    For studying demand relationships for a proposed new product that no one has ever used before, what would be the best method to use?
a.    ordinary least squares regression on historical data
b.    market experiments, where the price is set differently in two markets
c.    consumer surveys, where potential customers hear about the product and are asked their opinions
d.    double log functional form regression model
e.    all of the above are equally useful in this case

13.    Which of the following barometric indicators would be the most helpful for forecasting future sales for an industry?
    a.    lagging economic indicators.
    b.    leading economic indicators.
    c.    coincident economic indicators.
    d.    wishful thinking
    e.    none of the above

14.    An example of a time series data set is one for which the:
    a.    data would be collected for a given firm for several consecutive periods (e.g., months).
    b.    data would be collected for several different firms at a single point in time.
    c.    regression analysis comes from data randomly taken from different points in time.
    d.    data is created from a random number generation program.
    d.    use of regression analysis would impossible in time series.

15.    Examine the plot of data.  
    Sales

                                 
                                                                  
                            

                                 Time    
It is likely that the best forecasting method for this plot would be:
a.    a two-period moving average
b.    a secular trend upward
c.    a seasonal pattern that can be modeled using dummy variables or seasonal adjustments
d.    a semi-log regression model
e.    a cubic functional form

16. Emma uses a linear model to forecast quarterly same-store sales at the local Garden Center.  The results of her multiple regression is:

Sales = 2,800 + 200•T - 350•D

    where T goes from 1 to 16 for each quarter of the year from the first quarter of 2006 (‘06I) through the fourth quarter of 2009 (‘09 IV).  D is a dummy variable which is 1 if sales are in the cold and dreary first quarter, and zero otherwise, because the months of January, February, and March generate few sales at the Garden Center.  Use this model to estimate sales in a store for the first quarter of 2010 in the 17th month; that is: {2010 I}. Emma’s forecast should be:  
a.    5,950
b.    6,200
c.    6,350
d.    6,000
e.    5,850

17.     Select the correct statement.
    a.    Qualitative forecasts give the direction of change.
    b.    Quantitative forecasts give the exact amount or exact percentage change.
    c.    Diffusion forecasts use the proportion of the forecasts that are positive to forecast up or down.
    d.    Surveys are a form of qualitative forecasting.
    e.    all of the above are correct.

18.     If two alternative economic models are offered, other things equal, we would
    a.    tend to pick the one with the lowest R2.
    b.    select the model that is the most expensive to estimate.
    c.     pick the model that was the most complex.
    d.    select the model that gave the most accurate forecasts
    e.    all of the above

19.    Mr. Geppetto uses exponential smoothing to predict revenue in his wood carving business. He uses a weight of  = .4 for the naïve forecast and (1-) = .6 for the past forecast.  What revenue did he predict for March using the data below?  Select closet answer.
        MONTH   REVENUE        FORECAST
    Nov    100            100
    Dec     90            100
    Jan        115            ----
Feb        110            ----
    MARCH     ?            ?
a.    106.2
b.    104.7
c.    103.2
d.    102.1
e.    101.7

20.    Suppose a plot of sales data over time appears to follow an S-shape as illustrated below.

    Sales                                                •
                                              •
                         
                            •
                           •                 
                       •    •                  
 
                                Time

Which of the following is likely that the best forecasting functional form to use for sales data above?
a.    A linear trend, Sales = a + b T
b.    A quadratic shape in T, using T-squared as another variable, Sales = a + b T + cT2.
c.    A semi-log form as sales appear to be growing at a constant percentage rate, Ln Sales = a + bT
d.    A cubic shape in T, using T-squared and T-cubed as variables, Sales = a + b T + cT2 + d T3. 
e.    A quadratic shape in T and T-squared as variables, Sales = a + b T + cT2 

PROBLEM

    1.    The Accuweather Corporation manufactures barometers and thermometers for weather forecasters. In an attempt to forecast its future needs for mercury, Accuweather's chief economist estimated average monthly mercury needs as:

          N = 500 + 10X

where N = monthly mercury needs (units) and X = time period in months (January 2008= 0). The following monthly seasonal adjustment factors have been estimated using data from the past five years:

Month    Adjustment Factor
January      15%
April      10%
July    20%
September        5%
December    10%

(a)    Forecast Accuweather's mercury needs for January, April, July, September, and December of 2010.
(b)    The following actual and forecast values of mercury needs in the month of November have been recorded:
    
    Year    Actual    Forecast    
    2008    456    480    
    2009    324    360    
    2007    240    240    

What seasonal adjustment factor should the firm use for November?

    2.    Milner Brewing Company experienced the following monthly sales (in thousands of barrels) during 2010:

Jan.    Feb.    Mar.    Apr.    May    June
100    92    112    108    116    116

(a)    Develop 2-month moving average forecasts for March through July.
(b)    Develop 4-month moving average forecasts for May through July.
(c)    Develop forecasts for February through July using the exponential smoothing method (with w = .5). Begin by assuming  .