21/9/2017 MAPE | Mean absolute percentage error | statistics of fit | reference manual | NumXL

NumXL for Microsoft Excel makes sense of time series analysis:

Have a Question?
Build, validate, rank models, and forecast right in Excel
Phone: +1 (888) 427-9486
Keep the data, analysis and models linked together
+1 (312) 257-3777
Make and track changes instantly Contact Us
Share your results by sending just one file
>>Read More
Search
| Free Trial

Home Products Tips & Support About Us Prices

Demos
Home >> Support >> Documentation >> NumXL >> Reference Manual >> Forecasting Performance >> MAPE

Try our full-featured product

MAPE free for 14 days

Calculates the mean absolute percentage error (Deviation) function for the forecast and the eventual outcomes.

Syntax
MAPEi(X, Y, Ret_type)

X is the original (eventual outcomes) time series sample data (a one dimensional array of cells (e.g. rows or columns)).

Y is the forecast time series data (a one dimensional array of cells (e.g. rows or columns)).

Ret_type is a switch to select the return output (1=MAPE (default), 2=Symmetric MAPE (SMAPI)). Help desk
Order Description Questions?
Request a feature?
1 MAPE (default) Report an issue?

2 SMAPE Go to your help desk

Remarks Or email us:

support@numxl.com
1. MAPE is also referred to as MAPD.

2. The time series is homogeneous or equally spaced.

3. For a plain MAPE calculation, in the event that an observation value (i.e. ) is equal to zero, the MAPE function skips that data point.

4. The mean absolute percentage error (MAPE), also known as mean absolute percentage deviation (MAPD), measures the accuracy of a
method for constructing fitted time series values in statistics. NumXL 1.65 (HAMMOCK) Est Aqu!
05/18/2017 - 21:31
5. The two time series must be identical in size.
NumXL 1.65 (HAMMOCK) is Here!
05/18/2017 - 21:14
6. The mean absolute percentage error (MAPE) is defined as follows:
NumXL 1.64 (TURRET) is here
12/25/2016 - 13:12

Where: ARIMA ARMA Forecast Getting Started

is the actual observations time series

goodness of fit LLF SARIMA
statistical test
scenario simulation
is the estimated or forecasted time series
tutorial user's guide
is the number of non-missing data points more tags

7. When calculating the average MAPE for a number of time series, you may encounter a problem: a few of the series that have a very high
MAPE might distort a comparison between the average MAPE of a time series fitted with one method compared to the average MAPE
when using another method.

8. In order to avoid this problem, other measures have been defined, for example the SMAPE (symmetrical MAPE), weighted absolute
percentage error (WAPE), real aggregated percentage error, and relative measure of accuracy (ROMA).

9. The symmetrical mean absolute percentage error (SMAPE) is defined as follows:

10. The SMAPE is easier to work with than MAPE, as it has a lower bound of 0% and an upper bound of 200%.

11. The SMAPE does not treat over-forecast and under-forecast equally.

12. For a SMAPE calculation, in the event the sum of the observation and forecast values (i.e. ) equals zero, the MAPE function
skips that data point.
Examples

http://www.spiderfinancial.com/support/documentation/numxl/reference-manual/forecasting-performance/mape 1/3
21/9/2017 MAPE | Mean absolute percentage error | statistics of fit | reference manual | NumXL
Example 1:

A B C
1 Date Series1 Series2
2 1/1/2008 #N/A -2.61
3 1/2/2008 -2.83 -0.28
4 1/3/2008 -0.95 -0.90
5 1/4/2008 -0.88 -1.72
6 1/5/2008 1.21 1.92
7 1/6/2008 -1.67 -0.17
8 1/7/2008 0.83 -0.04
9 1/8/2008 -0.27 1.63
10 1/9/2008 1.36 -0.12
11 1/10/2008 -0.34 0.14
12 1/11/2008 0.48 -1.96
13 1/12/2008 -2.83 1.30
14 1/13/2008 -0.95 -2.51
15 1/14/2008 -0.88 -0.93
16 1/15/2008 1.21 0.39
17 1/16/2008 -1.67 -0.06
18 1/17/2008 -2.99 -1.29
19 1/18/2008 1.24 1.41
20 1/19/2008 0.64 2.37

Formula Description (Result)

=MAPE($B$1:$B$19,$C$1:$C$19,1) MAPE (151.503)
=SMAPE($B$1:$B$19,$C$1:$C$19,2) SMAPE (500)

Files Examples

Iniciar sesin Registrarse

MAPE Descargar

Nombre

Ex1-MAPE.xlsx V3

References
Hamilton, J .D.; Time Series Analysis , Princeton University Press (1994), ISBN 0-691-04289-6

Tsay, Ruey S.; Analysis of Financial Time Series John Wiley & SONS. (2005), ISBN 0-471-690740
Related Links
Monash forecasting - SMAPE
Wikipedia - Mean absolute percentage error (MAPE)
Wikipedia - Symmetric mean absolute percentage error (sMAPE)

GRMSE up MdAPE

REFERENCE
SSE
SAE
RMSE
RMSD

Support Resources About Spider Follow Us

FAQ Order Help Contact Spider

http://www.spiderfinancial.com/support/documentation/numxl/reference-manual/forecasting-performance/mape 2/3
21/9/2017 MAPE | Mean absolute percentage error | statistics of fit | reference manual | NumXL
Demos & Tutorials Corporate Information
Documentation Legal Information
Help Desk Partners
Contact | Glossary | Sitemap | Blog | Links
2008-2017 Spider Financial | Disclaimer | Terms of Use | Privacy Policy | Trademarks & Copyrights

http://www.spiderfinancial.com/support/documentation/numxl/reference-manual/forecasting-performance/mape 3/3