Suppose we have a variable y which is dependent on 2 variables say x1 and x2.
Then I can understand how we can compute Sum of squares due to x1 and x2. For instance we may have Type I Sum of squares where each variable is entered sequentially or Type III sum of squares where each variable is entered in the last.
My query is : How do we go from the Sum of Squares to the OLS coefficients?
Are the OLS coefficients different if we have unbalanced data and we use Type I vs Type III sum of squares ?
I am a self taught kind of person so please pardon my simple query.