The eigenvalues of a matrix are not easy to compute. It is remarkable, therefore, that with relatively simple mental arithmetic, you can obtain bounds for the eigenvalues of a matrix of any size. The bounds are provided by using a marvelous mathematical result known as Gershgorin's Disc Theorem. For certain

## Tag: **Matrix Computations**

A quadratic form is a second-degree polynomial that does not have any linear or constant terms. For multivariate polynomials, you can quickly evaluate a quadratic form by using the matrix expression x` A x This computation is straightforward in a matrix language such as SAS/IML. However, some computations in statistics

In numerical linear algebra, there are often multiple ways to solve a problem, and each way is useful in various contexts. In fact, one of the challenges in matrix computations is choosing from among different algorithms, which often vary in their use of memory, data access, and speed. This article

In simulation studies, sometimes you need to simulate outliers. For example, in a simulation study of regression techniques, you might want to generate outliers in the explanatory variables to see how the technique handles high-leverage points. This article shows how to generate outliers in multivariate normal data that are a

I remember the first time I used PROC GLM in SAS to include a classification effect in a regression model. I thought I had done something wrong because the parameter estimates table was followed by a scary-looking note: Note: The X'X matrix has been found to be singular, and a

A data analyst asked how to compute parameter estimates in a linear regression model when the underlying data matrix is rank deficient. This situation can occur if one of the variables in the regression is a linear combination of other variables. It also occurs when you use the GLM parameterization

A SAS programmer asked how to rearrange elements of a matrix. The rearrangement he wanted was rather complicated: certain blocks of data needed to move relative to other blocks, but the values within each block were to remain unchanged. It turned out that the mathematical operation he needed is called

It is sometimes necessary for researchers to simulate data with thousands of variables. It is easy to simulate thousands of uncorrelated variables, but more difficult to simulate thousands of correlated variables. For that, you can generate a correlation matrix that has special properties, such as a Toeplitz matrix or a

Back in high school, you probably learned to find the intersection of two lines in the plane. The intersection requires solving a system of two linear equations. There are three cases: (1) the lines intersect in a unique point, (2) the lines are parallel and do not intersect, or (3)

The sweep operator performs elementary row operations on a system of linear equations. The sweep operator enables you to build regression models by "sweeping in" or "sweeping out" particular rows of the X`X matrix. As you do so, the estimates for the regression coefficients, the error sum of squares, and

Sometimes it is important to ensure that a matrix has unique rows. When the data are all numeric, there is an easy way to detect (and delete!) duplicate rows in a matrix. The main idea is to subtract one row from another. Start with the first row and subtract it

I often claim that the "natural syntax" of the SAS/IML language makes it easy to implement an algorithm or statistical formula as it appears in a textbook or journal. The other day I had an opportunity to test the truth of that statement. A SAS programmer wanted to implement the

Many people know that a surface can contain a saddle point, but did you know that you can define the saddle point of a matrix? Saddle points in matrices are somewhat rare, which means that if you choose a random matrix you are unlikely to choose one that has a

Happy holidays to all my readers! My greeting-card to you is an image of a self-similar Christmas tree. The image (click to enlarge) was created in SAS by using two features that I blog about regularly: matrix computations and ODS statistical graphics. Self-similarity in Kronecker products I have previously shown

A previous article discussed the mathematical properties of the singular value decomposition (SVD) and showed how to use the SVD subroutine in SAS/IML software. This article uses the SVD to construct a low-rank approximation to an image. Applications include image compression and denoising an image. Construct a grayscale image The

A SAS user needed to convert a program from MATLAB into the SAS/IML matrix language and asked whether there is a SAS/IML equivalent to the fliplr and flipud functions in MATLAB. These functions flip the columns or rows (respectively) of a matrix; "LR" stands for "left-right" and "UD" stands for

For a time series { y1, y2, ..., yN }, the difference operator computes the difference between two observations. The kth-order difference is the series { yk+1 - y1, ..., yN - yN-k }. In SAS, the DIF function in the DATA step computes differences between observations. The DIF function

Rotation matrices are used in computer graphics and in statistical analyses. A rotation matrix is especially easy to implement in a matrix language such as the SAS Interactive Matrix Language (SAS/IML). This article shows how to implement three-dimensional rotation matrices and use them to rotate a 3-D point cloud. Define

Every year near Halloween I write an article in which I demonstrate a simple programming trick that is a real treat to use. This year's trick (which features the CMISS function and the crossproducts matrix in SAS/IML) enables you to count the number of observations that are missing for pairs

What is weighted regression? How does it differ from ordinary (unweighted) regression? This article describes how to compute and score weighted regression models. Visualize a weighted regression Technically, an "unweighted" regression should be called an "equally weighted " regression since each ordinary least squares (OLS) regression weights each observation equally.

Last week I showed how to represent a Markov transition matrix in the SAS/IML matrix language. I also showed how to use matrix multiplication to iterate a state vector, thereby producing a discrete-time forecast of the state of the Markov chain system. This article shows that the expected behavior of

Many computations in elementary probability assume that the probability of an event is independent of previous trials. For example, if you toss a coin twice, the probability of observing "heads" on the second toss does not depend on the result of the first toss. However, there are situations in which

A grid is a set of evenly spaced points. You can use SAS to create a grid of points on an interval, in a rectangular region in the plane, or even in higher-dimensional regions like the parallelepiped shown at the left, which is generated by three vectors. You can use

Children in primary school learn that every positive number has a real square root. The number x is a square root of s, if x2 = s. Did you know that matrices can also have square roots? For certain matrices S, you can find another matrix X such that X*X

Last week I attended SAS Global Forum 2016 in Las Vegas. I and more than 5,000 other attendees discussed and shared tips about data analysis and statistics. Naturally, I attended many presentations that featured using SAS/IML software to implement advanced analytical algorithms. Several speakers showed impressive mastery of SAS/IML programming

Last week I showed how to create dummy variables in SAS by using the GLMMOD procedure. The procedure enables you to create design matrices that encode continuous variables, categorical variables, and their interactions. You can use dummy variables to replace categorical variables in procedures that do not support a CLASS

I began 2016 by compiling a list of popular articles from my blog in 2015. This "People's Choice" list contains many interesting articles, but some of my personal favorites did not make the list. Today I present the "Editor's Choice" list of articles that deserve a second look. I've grouped

A recent question posted on a discussion forum discussed storing the strictly upper-triangular portion of a correlation matrix. Suppose that you have a correlation matrix like the following: proc iml; corr = {1.0 0.6 0.5 0.4, 0.6 1.0 0.3 0.2, 0.5 0.3 1.0 0.1, 0.4 0.2 0.1 1.0}; Every correlation

You've had a long day. You've implemented a custom algorithm in the SAS/IML language. But before you go home, you want to generate some matrices and test your program. If you are like me, you prefer a short statement—one line would be best. However, you also want the flexibility to

Occasionally a SAS statistical programmer will ask me, "How can I construct a large correlation matrix?" Often they are simulating data with SAS or developing a matrix algorithm that involves a correlation matrix. Typically they want a correlation matrix that is too large to input by hand, such as a