![]() ![]() E.g., calling the function like this inside another function will allow inplace operations: function some_functionĪ = perms_of_(A) % save the result of the call in a variable If you don't use specific inplace operation syntax in the caller then a deep copy will be returned to the caller. This syntax of using the same variable name for input and output can sometimes result in inplace operations depending on how the function is called. =size(A) % number of rows and columnsįor j = 1:d % permute the elements of column j Perms = perms_of_(A) % save the result of the call in a variableįunction A = perms_of_(A) % declare the return variable to be A That is, you calculate a new A inside your function but you don't return it to the caller via the perms variable. ![]() Let's look at an example.You are not returning the result in your function. The SSCP matrix is part of the "normal equations" that are used to obtain least-squares estimates for regression parameters. If you have computed the SSCP matrix in one order, you can obtain it for any order without recomputing it. Fortunately, if you have computed the sum of squares and crossproducts matrix (SSCP) for the variables in the original order, it is trivial to permute the matrix to accommodate any other ordering of the variables. The order of variables is also used in regression techniques such as variable selection methods. For some statistics (for example, the Type I sequential sum of squares), the order of the variables in the model are important. Suppose you read in a design matrix where the columns of the matrix are in a specified order. Another application is the order of columns in a design matrix for linear regression models. In my previous article, I used a correlation matrix to demonstrate why it is useful to know how to permute rows and columns of a matrix. You don't have to remember which side of A to put the permutation matrix, nor whether to use a transpose operation.Īn application: Order of effects in a regression model The second syntax specifies the order of the rows. If you multiply A on the left (Q`*A), you permute the rows, as shown:Ī = shape ( 1: 25, 5, 5 ) /*, the first syntax means, "copy the columns in the order, 3, 5, 2, 4, and 1." I think this definition is easier to use.) If you multiply A on the right (A*Q), you permute the columns. (The permutation matrix is the transpose of the matrix that I used in the previous article. The following example defines a 5 x 5 matrix, A, with integer entries and a function that creates a permutation matrix. If you use matrix multiplication to permute columns of a matrix, you might not remember whether to multiply the permutation matrix on the left or on the right, but if you use subscripts, it is easy to remember the syntax. Subscripts enable you to permute rows and columns efficiently and intuitively. I ended the article by noting that "there is an easy alternative way" to permute rows and columns: use subscript notation. A previous article shows how to create a permutation matrix and how to use it to permute the order of rows and columns in a matrix. ![]() Permutation matrices have many uses, but their primary use in statistics is to rearrange the order of rows or columns in a matrix. Instead, use elementwise multiplication of rows and columns. That article recommends that you never multiply with a large diagonal matrix. Which discusses an efficient way to use diagonal matrices in matrix computations. The advice is similar to the tip in the article, "Never multiply with a large diagonal matrix," This article explains why it is not necessary to multiply by a permutation matrix in a matrix language. Never multiply with a large permutation matrix! Instead, use subscripts to permute rows and columns. Do you ever use a permutation matrix to change the order of rows or columns in a matrix? Did you know that there is a more efficient way in matrix-oriented languages such as SAS/IML, MATLAB, and R? ![]()
0 Comments
Leave a Reply. |