The representation here basically says each observation in a data set is a sum of products of some Zs and loadings. By Zs, I mean the component scores. Loadings are the weights given to the individual features in a particular principal component.
So, at first, we obtain component scores by multiplying loadings with their respective feature value.
But, as the attached image says, each observation can be approximated using the sum of products of component scores and loadings. My question is shouldn't individual observations be component scores divided by respective loading.
Aren't the component scores themselves obtained by multiplying Xs and loadings?
So is it: component score = loading multiplied by Xs
OR X = loading multiplied by component score? (X represents i,j th element in an observation matrix)
PS: apologies for the bad formatting. This is my first post here and copy-paste is not working as expected so I'm typing everything in,