I have the following questions:

Suppose we have the following chart, which represents the relationship between faculties and types of objects; for example CTE represents Computer Technologies, and the intersection between CTE and Wood says that at the CTE faculty there are 56 types of wood.

My question is: Can I use this table as a tool for PCA analysis?

Or can I represent these data in matrix form and perform a principal component analysis from this data table?

I need it for pattern recognition rate problems.

I know Matlab well and linear algebra as well; I just need advice.

enter image description here


migrated from math.stackexchange.com Mar 5 '13 at 14:07

This question came from our site for people studying math at any level and professionals in related fields.

  • $\begingroup$ What are you trying to do? $\endgroup$ – copper.hat Mar 5 '13 at 7:05
  • $\begingroup$ it is something like statistical analyse of different type of persons ,their characters and so on $\endgroup$ – dato datuashvili Mar 5 '13 at 7:12
  • $\begingroup$ Homework, in other words? $\endgroup$ – copper.hat Mar 5 '13 at 7:13
  • $\begingroup$ to be honestly i dont know what is meaning of homework in this case,but it is related with my article researching $\endgroup$ – dato datuashvili Mar 5 '13 at 7:14
  • $\begingroup$ I don't know what to say, you can use any table for PCA analysis, but whether it is meaningful or not depends on the data and what you are trying to do with it. The answers to your two questions are yes and yes, but these answers are somewhat meaningless. $\endgroup$ – copper.hat Mar 5 '13 at 7:30

You can use this table for PCA, but the data points would give you a more refined idea and use a covariance matrix since the data is on the same scale

Here is a video explaining PCA usage for finding patterns similar to your case


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.