Demean vs normalization vs Standardization for PCA

Course Q&A Natural Language Processing NLP with Classification and Vector Spaces
1

In the lectures the course recommend to standardize the data before doing the PCA transformation. But in the assignment the suggest to just de-mean the data.
Why?
How the results will change if we use Demean vs normalization vs Standardization for PCA?
What’s the different ? which is better and why?

1 Like
2

Hi Nicolas1,

Whether or not you want to perform normalization depends on the meaning of the values and the variation in them. See this discussion.