Skip to main content

Description


Computes a linear regression by fitting a straight line to the data and taking seasonality into account.

 

Syntax

SEASONAL_LINEAR_REGRESSION(Input Block, Seasonality Â, Ranking Dimension])

 

Arguments

Argument Type Dimensions Description

Input Block

(required)

 Number Any Dimensions This is the data source on which the seasonal linear regression is computed, and must be a Metric with data points as an expression of Integer or Number type. This Metric must include the same Dimension that is used in the Ranking Dimension argument. 

Seasonality

(required)

 Integer No Dimension or Dimensions of Text 1 Length of the seasonality. It must be greater than 1, for example, if you observe a quarterly on a Metric defined by month, the Seasonality length is 3. If you observe a yearly seasonality on a Metric defined by month, the Seasonality length is 12.

Ranking Dimension

(optional)

 Dimension Not applicable This is a Dimension applied to the time series taken in the Input Block. This is optional if it’s a datetime Dimension from the calendar. If this is not the case, then this is mandatory. It’s also mandatory if the Metric is defined on several time Dimensions.

 

Returns

Type Dimensions
Number Dimensions of Input Block

 

With N being the Seasonality length of the serie, the function returns:

  • Blank for value before the first non blank value.
  •  (A * x  + B ) * SeasonalityFactor(x) after the first non blank value

To compute SeasonalityFactor, A and B, we use the classical decomposition method, called multiplicative decomposition, over historical data.

 

Notes:

  • Blank observations (in the input Block) between the first non-blank value and the last non-blank values are considered as 0. 
  • The function requires 2 times the seasonality in terms of datapoint between the first non-blank value and the last non-blank values.

 

 

Examples

Formula Description
SEASONAL_LINEAR_REGRESSION(Actuals, 4, Quarter) Computes a yearly seasonality over a metric defined by quarter.
SEASONAL_LINEAR_REGRESSION( Actuals, 12, Month) Computes a yearly seasonality over a metric defined by month.
SEASONAL_LINEAR_REGRESSION( Actuals, 3, Month) Computes a quarterly seasonality over a metric defined by month.

 

Example using SEASONAL_LINEAR_REGRESSION(Actuals, 4): 

 

 

Using SEASONAL_LINEAR_REGRESSION as Forecasting Function

 

A common use case for using the SEASONAL_LINEAR_REGRESSION function is to prepare a forecast. It’s a good method when your observation series shows a linear trend and a seasonality.

 

See also

Related articles: FORECAST ETS , FORECAST_LINEAR

nReferences: Multiplicative decomposition , wikipedia]

Ask your question here!

Terms & ConditionsCookie settings