Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
Is PCA and Factor Analysis same? Both are used for Data dimension reduction but theoretically I am not able to find the difference between them?
I did FA in SPSS to reduce number of variables in my data set. I think the same think can be done using PCA as well. Never did PCA so wanted to know exact difference between two techniques.
Principal components don't have to make sense, they are just artificial numbers, summarized data if you will, used e.g. for visualizations
With factor analysis you try to find a latent variable (an underlying mechanism) that explains the data. Factor analysis is often used in psychology, eg the personality trait extraversion (the factor) explains certain behaviours (eg certain behaviours reported in a questionnaire)
PCA explains the whole variability (as it reveals latent state-space due to dimensionality reduction). Factor analysys explains only that part of variability that is common for all units.
