HP 3000 Manuals

HP RXForecast Users Manual for MPE Systems

Linear Example 

Suppose you generate the following Stats report from a linear forecast on
the Transactions Rate metric:


            

Notice that the second or "model" information block gives the formula
used to calculate this forecast:

FC = INT + SLOPE * TIME + DOW + WOM + MOQ + QOY

The formula tells you that you need to know the intercept, slope, and the
number of time periods since the start of the forecast, as well as
seasonality.

Question 

What is the forecasted Transactions Rate (X1000) for 1 June 1988?  That
is, how many terminal transactions can be expected per hour on that day?

Answer 

Most of the numbers you need (intercept, slope, seasonality) are given in
the Stats report.  Use a calendar to calculate TIME. Insert these numbers
into the formula, as follows:

Forecast  = 0.086992 + (0.00066047 * 92) + 0.0098705

          = 0.086992 + 0.06076324 + 0.0098705

          = 0.157626 transactions (X1000) per hour.

These numbers were derived as follows:

   1.  Calculate TIME, the number of days from the start date (1 March
       1988) through 1 June.

       This number is inclusive, so it is 13 weeks plus 1 day, or 92
       days.

       _________________________________________________________________ 

       NOTE  When the Ignore Weekends option is OFF, the forecast
             includes weekends.  Thus weekend days should be included in
             TIME.

       _________________________________________________________________ 

   2.  Multiply TIME, 92, by the SLOPE (0.00066047).

       Note that 6.6047e-004 is read as 6.6047 times 10 raised to the
       power -4.  Simply move the decimal point to the left 4 places.

   3.  Add the INTERCEPT (0.086992).

       Again, the intercept is 8.6992e-002.  So move the decimal point to
       the left 2 places.

   4.  Add the SEASONALITY factor for the particular day.

       1 June 1988 is a Wednesday.  Thus the seasonality factor is
       0.0098705.

MPE/iX 5.0 Documentation