FORECAST.ETS.STAT Function

Excel Functions › Statistical

Excel 2016+ Statistical

The Excel FORECAST.ETS.STAT function returns a chosen statistic about the exponential-smoothing (ETS) model behind a forecast — such as a smoothing coefficient or an error measure — selected by a numeric statistic_type.


Quick answer:
=FORECAST.ETS.STAT(values, timeline, 3) the alpha smoothing coefficient of the ETS model

Syntax

=FORECAST.ETS.STAT(values, timeline, statistic_type, [seasonality], [data_completion], [aggregation])
ArgumentDescription
valuesRequiredThe historical data range to model (e.g. B2:B40).
timelineRequiredThe matching, evenly spaced date/number range (e.g. A2:A40), the same size as values.
statistic_typeRequiredA number 1–8 selecting which statistic to return (see the how-to below).
seasonalityOptional0 = none, 1 = auto-detect (default), or a fixed season length.
data_completionOptional1 (default) interpolates missing points; 0 treats gaps as zeros.
aggregationOptionalHow duplicate timeline entries are combined (1 = AVERAGE, the default).

How to use it

FORECAST.ETS.STAT exposes the internals of the forecasting model so you can judge its quality. The third argument picks which number you want:

typestatistic returned
1Alpha — base (level) smoothing
2Beta — trend smoothing
3Gamma — seasonal smoothing
4MASE (mean absolute scaled error)
5SMAPE (symmetric mean absolute percentage error)
6MAE (mean absolute error)
7RMSE (root mean square error)
8Detected step size of the timeline
=FORECAST.ETS.STAT(B2:B40, A2:A40, 1) // alpha, a level-smoothing weight 0-1
=FORECAST.ETS.STAT(B2:B40, A2:A40, 7) // RMSE - lower is a tighter fit

Tip: the error stats (types 4–7) are the quickest way to compare model fit. A smaller SMAPE or RMSE means the ETS model tracks your history more closely — useful before you trust the forecast.

Try it: interactive demo

Live demo

Pick a FORECAST.ETS.STAT example to see the formula and its result.

Result:

Practice workbook

📊
Download the free FORECAST.ETS.STAT practice workbook
Every example on this page, ready to open in Excel — plus practice challenges with answers on a separate tab. No sign-up required.

Frequently asked questions

What do the statistic_type numbers mean?
1–3 return the smoothing coefficients alpha, beta and gamma; 4–7 return error measures MASE, SMAPE, MAE and RMSE; 8 returns the detected timeline step size.
Which statistic tells me if the forecast is any good?
Use the error measures (types 4–7). Lower SMAPE, MAE or RMSE means the model fits the history more tightly. RMSE (type 7) is the most familiar overall accuracy measure.
What are alpha, beta and gamma?
They are the smoothing weights of the ETS model: alpha for the level, beta for the trend, gamma for the seasonal component. Each runs 0–1; higher values let the model react faster to recent data.
Which Excel versions support it?
FORECAST.ETS.STAT was introduced in Excel 2016 and is in Microsoft 365. It is not available in Excel 2013 or earlier.

Master functions like this in one day

This page covers one function. Our Excel Formulas and Functions class covers the 30 that matter most — live, hands-on, taught by professionals in Dallas–Fort Worth, Houston, Austin, Oklahoma City, Denver, or online.

See the Formulas & Functions Class

Related functions: FORECAST.ETS.CONFINT · FORECAST.ETS.SEASONALITY · FORECAST.LINEAR · STEYX · RSQ