Time Series Tutorial
Selected Reading
- Time Series - Discussion
- Time Series - Useful Resources
- Time Series - Quick Guide
- Time Series - Further Scope
- Time Series - Applications
- Time Series - Error Metrics
- Time Series - LSTM Model
- Time Series - Prophet Model
- Time Series - Walk Forward Validation
- Time Series - Exponential Smoothing
- Time Series - Variations of ARIMA
- Time Series - ARIMA
- Time Series - Moving Average
- Time Series - Auto Regression
- Time Series - Naive Methods
- Time Series - Parameter Calibration
- Time Series - Modeling
- Data Processing & Visualization
- Time Series - Python Libraries
- Time Series - Programming Languages
- Time Series - Introduction
- Time Series - Home
Selected Reading
- Who is Who
- Computer Glossary
- HR Interview Questions
- Effective Resume Writing
- Questions and Answers
- UPSC IAS Exams Notes
Time Series - Error Metrics
Time Series - Error Metrics
It is important for us to quantify the performance of a model to use it as a feedback and comparison. In this tutorial we have used one of the most popular error metric root mean squared error. There are various other error metrics available. This chapter discusses them in brief.
Mean Square Error
It is the average of square of difference between the predicted values and true values. Sklearn provides it as a function. It has the same units as the true and predicted values squared and is always positive.
$$MSE = frac{1}{n} displaystylesumpmits_{t=1}^n lgroup y _{t}:-y_{t} group^{2}$$
Where $y _{t}$ is the predicted value,
$y_{t}$ is the actual value, and
n is the total number of values in test set.
It is clear from the equation that MSE is more penapzing for larger errors, or the outpers.
Root Mean Square Error
It is the square root of the mean square error. It is also always positive and is in the range of the data.
$$RMSE = sqrt{frac{1}{n} displaystylesumpmits_{t=1}^n lgroup y _{t}-y_{t} group ^2}$$
Where, $y _{t}$ is predicted value
$y_{t}$ is actual value, and
n is total number of values in test set.
It is in the power of unity and hence is more interpretable as compared to MSE. RMSE is also more penapzing for larger errors. We have used RMSE metric in our tutorial.
Mean Absolute Error
It is the average of absolute difference between predicted values and true values. It has the same units as predicted and true value and is always positive.
$$MAE = frac{1}{n}displaystylesumpmits_{t=1}^{t=n} | y {t}-y_{t}lvert$$
Where, $y _{t}$ is predicted value,
$y_{t}$ is actual value, and
n is total number of values in test set.
Mean Percentage Error
It is the percentage of average of absolute difference between predicted values and true values, spanided by the true value.
$$MAPE = frac{1}{n}displaystylesumpmits_{t=1}^nfrac{y _{t}-y_{t}}{y_{t}}*100: \%$$
Where, $y _{t}$ is predicted value,
$y_{t}$ is actual value and n is total number of values in test set.
However, the disadvantage of using this error is that the positive error and negative errors can offset each other. Hence mean absolute percentage error is used.
Mean Absolute Percentage Error
It is the percentage of average of absolute difference between predicted values and true values, spanided by the true value.
$$MAPE = frac{1}{n}displaystylesumpmits_{t=1}^nfrac{|y _{t}-y_{t}lvert}{y_{t}}*100: \%$$
Where $y _{t}$ is predicted value
$y_{t}$ is actual value, and
n is total number of values in test set.
Advertisements