Questions tagged [mae]

The Mean Absolute Error (MAE) is a point forecast accuracy measure. In the forecasting literature, Mean Absolute Deviation (MAD) is used interchangeably.

15 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4
votes
0answers
355 views

Regression models with comparable MAE but differing R²

I have trained two regression models on the same dataset. They perform with comparable mean absolut errors $MAE_{1,2} \approx 0.45$, but the coefficient of determination differs significantly with $R^...
2
votes
0answers
99 views

Why does the MAE of my estimation improve substantially when I divide it by 10 (in a very noisy dataset)?

I have an extremely noisy dataset, and I try to minimize the MAE. Apparently, when my linear regression makes its prediction - it has something like -1000 MAE (when compared to the MAE of an all-zero ...
1
vote
0answers
26 views

huge difference between RMSE and MAE in non-linear regressors

I am building non-linear regression models such as a Random Forest regressor , a KNN regressor or a SVM using a RBF kernel and I decided to use both RMSE and MAE as evaluation metrics. I know that a ...
1
vote
0answers
16 views

How should i compare this MAE results

I'm in need of help to correctly interpret these results. I am analyzing a time series of crime data. The series has 351,980 events. These are the results of the predictions using a regression model:...
1
vote
1answer
36 views

Scaling the MAE by the mean of non zero points for intermittent data

I am currently trying to find a way of scaling the MAE for my intermittent data. The data is always greater than 0 and is intermittent, with long periods of zeros. I have read a few papers that ...
1
vote
0answers
70 views

Error distribution for Huber Regression

For linear regression there's an assumption that error terms come from normal distribution. so that $Y = aX + b + \epsilon$, where $\epsilon$ has normal distribution with mean zero and certain ...
1
vote
1answer
92 views

a measure for MAE (of a regression)

I'm running a grid search, in order to fine-tune a NN hyper parameters. the question is: the MAE values I get from the trainings are too close. since I have the statistical attributes of the target ...
1
vote
0answers
148 views

Is there an analog for the coefficient of determination with absolute error?

Typically to measure the predictive power of a model, R^2 is more useful than RMSE because a RMSE score isn't very meaningful without a basis of comparison. If you are using mean absolute error (MAE) ...
1
vote
0answers
1k views

Relationship between $R^2$ and MAE in forecasting

I have the following linear model based on multivariate timeseries: ...
0
votes
0answers
18 views

Mean average error normalized by the standard deviation of the target

I'm working on a regression model, aiming at prediction age from structured data. I'm using the mean average error (MAE) as evaluation metric, and want to compare my performances with state-of-the-art ...
0
votes
0answers
20 views

RMSE vs. MAE for comparing HR between two measuring instruments

I am comparing a cheap measuring instrument to an expensive highly accurate measuring instrument. Both instruments measure heart rate in BPM. The cheap device is vulnerable to noise. I need to report ...
0
votes
1answer
37 views

What statistical test do I need for comparing forecasted data with actual data?

I’m currently completing my dissertation and need to compare forecasted wave height to the actual wave height. However I am unsure what statistical test to use. Thanks, Jess
0
votes
1answer
419 views

Relatively low MAE, but also low R-squared? Why

I am testing forecasts against against realized values with a number of observations of 4000. When I calculate the mean MAE, its relatively low. Around 10% deviation to the original variable. ...
0
votes
0answers
235 views

mape and mae from k-fold backtesting on time series

I performed a rolling window (i.e. do full sample, then next 4 observations until the last, and so on...) k-fold test for out of sample testing due to limited number of observations. From the MAPE ...
0
votes
1answer
103 views

Forecasting Prediction Accuracy

Out of 4 error paramters which one is best for evaluating prediction accuracy? Average error Mean absolute error Mean squared error Mean absolute % error why?