Mean Absolute Percentage Error in R

  • Context: Undergrad 
  • Thread starter Thread starter Darth Frodo
  • Start date Start date
  • Tags Tags
    Absolute Error Mean
Click For Summary

Discussion Overview

The discussion centers around the calculation of Mean Absolute Percentage Error (M.A.P.E.) using the accuracy() function in the SDMtools package in R. Participants are exploring the interpretation of the output value and its units, particularly whether an output of 10.69 represents 10.69% or 1069%.

Discussion Character

  • Exploratory, Technical explanation, Debate/contested

Main Points Raised

  • One participant reports an output of 10.69 from the accuracy() function and questions its interpretation as a percentage.
  • Another participant notes the difficulty in responding without additional context regarding the output.
  • A different participant assumes that the output should be objective since observed and predicted values are required inputs.
  • One participant emphasizes the importance of having a description of the units for the input and output of the SDMtools package to understand the meaning of the output.
  • Another participant recalls that the accuracy() function does not return MAPE, suggesting that the Forecast package might be the correct one for obtaining MAPE, which would be expressed as a percentage.
  • A later reply acknowledges the previous participant's suggestion regarding the Forecast package.

Areas of Agreement / Disagreement

Participants express uncertainty regarding the interpretation of the output value and whether the accuracy() function is appropriate for calculating MAPE. There is no consensus on the correct interpretation or the appropriate package to use.

Contextual Notes

Participants highlight the need for clarity on the units of measurement and the specific function used, indicating potential limitations in understanding the output without proper documentation.

Darth Frodo
Messages
211
Reaction score
1
Hi all,

I'm trying to calculate the M.A.P.E. using the accuracy() function in SDMtools.

I have an output of 10.69. I'm not sure if this is 10.69% or 1069% as previously in a different model I had gotten an output of 0.34.

If anyone is familiar with this, I would appreciate any help.

Thanks.
 
Physics news on Phys.org
Without context, it is very hard to respond.
 
Well I assumed the answer would be objective given that you are always required to enter the observed and predicted values.

Regardless, what context would you like?
 
You are using something called SDMtools. I would hope that there would be a description of the units, etc. of its input and output. Without such a description, 10.69 has no meaning.
 
I thought about this for a day, and it's been a long time since I've used R. However, using accuracy() does not return a MAPE. However, the package for time series and linear modeling, (I think it's simply called Forecast package, been awhile) does return a MAPE and if you are using that then your answer would be in a percentage.
 
Yeah MarneMath, I think you're right. Thanks!
 

Similar threads

  • · Replies 4 ·
Replies
4
Views
3K
  • · Replies 31 ·
2
Replies
31
Views
3K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 8 ·
Replies
8
Views
3K
  • · Replies 8 ·
Replies
8
Views
2K
  • · Replies 26 ·
Replies
26
Views
4K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 4 ·
Replies
4
Views
3K
  • · Replies 9 ·
Replies
9
Views
5K
  • · Replies 5 ·
Replies
5
Views
6K