how can i do Factor analysis with 2 matrix

I have 2 Matrix, for example

Matrix A ={a1 b1 c1; a2 b2 c2; a3 b3 c3}

Matrix B={x1 y1 z1 m1 n1; x2 y2 z2 m2 n2; x3 y3 z3 m3 n3 }

there must some relationships zwischen Matrix A and B, linear or unlinear, but i don't yet.

i want to do the Factor analysis and this relationships to find.

how kann i do the Factor analysis by Matlab ?

which function should i use ?

Thankyou very very much for your time!

Answer 1

[Abdolkarim Mohammadi]

factoran function implements Factor Analysis (FA) in MATLAB. FA is a dimension reduction technique. It is not designed to find the relationship between two datasets. It can only summarize each of your datasets into factors separately. If you want to find the relationship between the factors obtained from your datasets, you should use Structural Equations Modeling (SEM), whom uses FA along other techniques.

[Zuyu An]

first of all, thankyou for your time!

so could you please tell me how kann i do this SEM by Matlab ?

[Abdolkarim Mohammadi]

SEM is a collection of methods, including factor analysis and linear regression. MATLAB do provide powerful tools for these two. However, SEM requires many other statistical tests and techniques, which might be inculded in MATLAB, but are not packed as a single tool. If you have multiple inputs and multiple outputs and a large dataset, maybe Artificial Neural Networks (ANN) are a good choice for you. Beware that ANNs do not produce explicit formula (unlike regression) between the two matrices.

[Zuyu An]

i want to do the factor analysis at first, could you please show me the code of factor analysis about 2 Matrix ?

thankyou very much for your time!

[Abdolkarim Mohammadi]

Principle components analysis (PCA) is one of the most popular methods for FA. You can refer to the MATLAB's documentation of the function pca(). There you can see that FA is implemented on not more than one matrix. I think you should first read about the basics of FA.