Linear regression model using bayesian approach for energy performance of residential building

Syarifah Diana Permai, Heruna Tanty

Procedia Computer Science · 2018 · 85 citations · 9 references

DOIFull text

Open access

Concepts

Abstract

In the statistics there are two types of points of view, Frequentist and Bayesian. The difference between Frequentist and Bayesian is the point of view in terms of looking at a parameter. Bayesian views a parameter as a random variable, it means the value is not a single value. The modeling method that most commonly used by researchers is linear regression model. The Frequentist methods that are often used in linear regression are Ordinary Least Square (OLS) and Maximum Likelihood Estimation (MLE). However, along with the Bayesian development, several studies have shown better modeling results than the Frequentist method. On the other hand, Bayesian approach is also used when assumptions in linear regression model using OLS are not met. Therefore, this research performs linear regression modeling with Bayesian approach. The analysis showed that linear regression model using OLS does not met all assumptions. It means the model is not good enough. Then, Bayesian approach can be used as an alternative for the model. The comparison of Bayesian and Frequentist modeling results using several criteria such as RMSE, MAPE and MAD. The results showed that the linear regression method using Bayesian approach is better than Frequentist method using OLS.

References

9