1
$\begingroup$

The tag on feature scaling says:

Popular feature scaling types include scaling the data to have zero mean and unit variance, and scaling the data between a given minimum and maximum value.

Are there any details that help us to generate zero mean and unit variance?

$\endgroup$
1
$\begingroup$

To generate zero mean and unit variance, you are looking at standardization. Where a feature $x$ becomes scaled feature $z$ like this:

$$z = \frac{x - \mu}{\sigma}$$

Where $\mu$ is the mean of that feature and $\sigma$ the standard deviation.

$\endgroup$
2
  • 2
    $\begingroup$ I am sorry but I don't quite understand what is unclear about my answer. This is a very simple formula and the link I provided has plenty of additional information. I felt that it was better to keep the answer concise and leave the link as extra material for those that are interested to read further $\endgroup$ May 27 '20 at 20:46
  • $\begingroup$ scaled feature z like this: whether it indicates standard-score or z/t-statistics. $\endgroup$ May 29 '20 at 11:55

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.