How to find the row wise linear regression coefficients?

I have 3 matrices Y, x1, and x2 each having 3420 rows and 29 columns. I want the row wise linear regression coefficients of Y on x1, x2, and the interaction between x1 and x2 for their corresponding rows such that the regression coefficient term for each of them is of 3420 rows and 1 column.

I tried the following code:

y=rand([3420,28]);
x1=rand([3420,28]);
x2=rand([3420,28]);
n = 3420;
b = zeros(n,4);
X=zeros(n,4);
for i=1:n
X(i,4)=[ones([28,1]) x1(i,:)' x2(i,:)' (x1(i,:).*x2(i,:))'];
b(i,4)=(regress(y(i,:)',X(i,4)))';
end

But it is not giving the desired result.

How to get the linear regression coefficients of Y on x1, x2, and interaction between x1, x2 as a 3420 rows and 1 column array?

Answer 1

[Ive J]

nsample = 29;
nvar = 3420;

% sample data 
y = rand(nsample, nvar);
x1 = rand(nsample, nvar);
x2 = rand(nsample, nvar);
xInt = x1.*x2;
intercept = ones(nsample, 1);

beta = zeros(nvar, 4);
for i = 1:nvar
    desMat = [intercept, x1(:, i), x2(:, i), xInt(:, i)];
    beta(i, :) = regress(y(:, i), desMat);
end

size(beta)

ans = 1×2

3420 4

Each row of beta contains coefficients for each variables in nvar.

[Abhishek Chakraborty]

Thanks a lot Ive J.