Exam 15: Time-Series Forecasting and Index Numbers

The high and low values of the "ratios of actuals to moving average" are ignored when finalizing the seasonal index for a period (month or quarter)in time series decomposition.The rationale for this is to ___.

Because seasonal effects can confound trend analysis,it is important to make sure that the data is free of seasonality prior to using regression models to analyze trend.

Using 2008 as the base year,the 2007 value of the Laspeyres Price Index is ___.

Use of a smoothing constant value less than 0.5 in an exponential smoothing model gives more weight to ___.

In exponential smoothing models,the value of the smoothing constant may be any number between ___.

In an autoregressive forecasting model,the independent variable(s)is (are)___.

Mean error (ME)and mean absolute deviation (MAD)will have the same numerical value if all errors are positive.

Analysis of data for an autoregressive forecasting model produced the following tables: The actual values of this time series,y,were 228,54,and 191 for May,June,and July,respectively.The predicted (forecast)value for August is ___.

Time-series data are data gathered on a desired characteristic at a particular point in time.

Using a three-month moving average,the forecast value for November in the following time series is ___.

The following graph of a time-series data suggests a ___ trend.

Forecast error is the difference between the value of the response variable and those of the explanatory variables.

Differentiate among simple index numbers,unweighted aggregate price index numbers,weighted aggregate price index numbers,Laspeyres price index numbers,and Paasche price index numbers by defining and calculating each.

Jim Royo,manager of Billings Building Supply (BBS),wants to develop a model to forecast BBS's monthly sales (in $1,000's).He selects the dollar value of residential building permits (in $10,000)as the predictor variable.An analysis of the data yielded the following tables: Jim's calculated value for the Durbin-Watson statistic is 1.14.Using $\alpha$ = 0.05,the appropriate decision is: ___.

Using a three-month moving average (with weights of 5,3,and 1 for the most current value,next most current value and oldest value,respectively),the forecast value for November in the following time series would be ___.

A time series with forecast values and error terms is presented in the following table.The mean error (ME)for this forecast is ___.

Fitting a linear trend to 36 monthly data points (January 2000 = 1,February 2000 = 2,March 2000 = 3,etc. )produced the following tables: The projected trend value for January 2003 is ___.

Differentiate among various measurements of forecasting error,including mean absolute deviation and mean square error,in order to assess which forecasting method to use.

When constructing a weighted aggregate price index,the weights usually are ___.

Use of a smoothing constant value greater than 0.5 in an exponential smoothing model gives more weight to ___.