How to Transform Data to Better Fit The Normal Distribution - MachineLearningMastery.com
A large portion of the field of statistics is concerned with methods that assume a Gaussian distribution: the familiar bell curve. If your data has a Gaussian distribution, the parametric methods are powerful and well understood. This gives some incentive to use them if possible. Even if your data does not have a Gaussian distribution. […]
By Jason Brownlee on August 8, 2019 in Statistics 64 Share Post Share A large portion of the field of statistics is concerned with methods that assume a Gaussian distribution: the familiar bell curve. If your data has a Gaussian distribution, the parametric methods are powerful and well understood. This gives some incentive to use them if possible. Even if your data does not have a Gaussian distribution. It is possible that your data does not look Gaussian or fails a normality test, but can be transformed to make it fit a Gaussian distribution. This is more likely if you are familiar with the
related reading
- Ever Wondered Why Normal Distribution Is So Important?medium.com
- Logs, Tails, Long Tails – Ryan Moulton's Articlesmoultano.wordpress.com
- Six (and a half) intuitions for KL divergence — LessWronglesswrong.com
- How much do you believe your results? — LessWronglesswrong.com
- Nonparametric statistics - Wikipediaen.wikipedia.org
- Normalizing flowsbehindml.com
- A Visual Exploration of Gaussian Processesdistill.pub
- normal distribution - Change of variables: Apply $\tanh$ to the Gaussian samples - Mathematics Stack Exchangemath.stackexchange.com
- A Maximum Entropy Intuition for Fundamental Statistical Distributions | long intuitionlongintuition.com
- Musings on typicality – Sander Dielemansander.ai
- The power of selectiontsvibt.blogspot.com
- Normalizing Flows for Probabilistic Modeling and Inferencealphaxiv.org