LogisticForecast

Syntax

LogisticForecast(Year1, Value1, Year2, Value2,... YearN, ValueN) or
LogisticForecast(XLRange(Filename, Rangename))

Description

Logistic forecasting is used to estimate future values based on a time series of historical data. The new values are predicted using an approximate fit of a logistic function by linear regression.

A logistic function takes the general form:

where the Y terms corresponds to the variable to be forecast and the X term is years. A, B, a, b are constants and e is the base of the natural logarithm (2.718&ldots;). A logistic forecast is most appropriate when a variable is expected to show an "S "shaped curve over time. This makes it useful for forecasting shares, populations and other variables that are expected to grow slowly at first, then rapidly and finally more slowly, approaching some final value (the "B" term in the above equation).

Use this function with caution. You may need to first use some other package to test the statistical validity of the forecast (i.e. test how well the regression "fits" the historical data).

Using the above two alternatives syntaxes the time-series data required by the function can either be entered explicitly in WEAP as year/value pairs or they can be specified as a range in an Excel spreadsheet. Use the yearly time-series wizard to input these values or to link to the Excel data. In either case, years do not need to be in any particular order, but duplicate years are not allowed, and must be in the range 1990-2200.

When linking to a range in Excel, you must specify the directory and filename of a valid Excel worksheet or spreadsheet (an XLS or XLW) file, followed by a valid Excel range. A range can be either a valid named range (e.g. "Import") or a range address (e.g. "Sheet1!A1:B5"). The Excel range must contain pairs of years and values in its cells arranged into 2 columns. Use the WEAP Yearly Time-series Wizard to select a worksheet, to choose among the valid named ranges in the worksheet, and to preview the data that will be imported.

NB: The result of this function will be overridden by any value calculated for the Current Accounts. In some cases this may lead to a marked "jump" from the Current Accounts value to the succeeding year's value. This may reflect the fact that the Current Accounts year you have chosen is not a good match of the long-term trends in your scenario, or it may reflect a poor fit between the regression and the historical data.

Tip

Use the Yearly Time-Series Wizard to enter the data for this function.

See Also

ExpForecast, Growth, GrowthAs, GrowthFrom, Interp, LinForecast, Smooth, Step