A common task in data analysis is to locate observations that satisfy multiple criteria. For example, you might want to locate all zip codes in certain counties within specified states. The SAS DATA step contains the powerful WHERE statement, which enables you to extract a subset of data that satisfy
A customer asked: How do we go about summing a finite series in SAS? For example, I want to compute for various integers n ≥ 3. I want to output two columns, one for the natural numbers and one for the summation of the series. Summations arise often in statistical
The title of this article makes no sense. How can the number of elements (in fact, the number of anything!) not be a whole number? In fact, it can't. However, the title refers to the fact that you might compute a quantity that ought to be an integer, but is
Sometimes I get contacted by SAS/IML programmers who discover that the SAS/IML language does not provide built-in support for multiplication of matrices that have missing values. (SAS/IML does support elementwise operations with missing values.) I usually respond by asking what they are trying to accomplish, because mathematically matrix multiplication with
SAS procedures usually handle missing values automatically. Univariate procedures such as PROC MEANS automatically delete missing values when computing basic descriptive statistics. Many multivariate procedures such as PROC REG delete an entire observation if any variable in the analysis has a missing value. This is called listwise deletion or using
The SAS DATA step supports multidimensional arrays. However, matrices in SAS/IML are like mathematical matrices: they are always two dimensional. In simulation studies you might need to generate and store thousands of matrices for a later statistical analysis of their properties. How can you accomplish that unless you can create
In SAS, the order of variables in a data set is usually unimportant. However, occasionally SAS programmers need to reorder the variables in order to make a special graph or to simplify a computation. Reordering variables in the DATA step is slightly tricky. There are Knowledge Base articles about how
A SAS/IML programmer asked a question on a discussion forum, which I paraphrase below: I've written a SAS/IML function that takes several arguments. Some of the arguments have default values. When the module is called, I want to compute some quantity, but I only want to compute it for the
A SAS programmer recently posted a question to the SAS/IML Support Community about how to compute the kth smallest value in a vector of numbers. In the DATA step, you can use the SMALLEST function to find the smallest value in an array, but there is no equivalent built-in function
Like most programming languages, the SAS/IML language has many functions. However, the SAS/IML language also has quite a few operators. Operators can act on a matrix or on rows or columns of a matrix. They are less intuitive, but can be quite powerful because they enable you perform computations without
A common question on SAS discussion forums is how to compute the minimum and maximum values across several variables. It is easy to compute statistics across rows by using the DATA step. This article shows how to compute the minimum and maximum values for each observation (across variables) and, for
SAS/IML 13.1 includes a handy function for programmers who write a lot of modules. The PARENTNAME function obtains the name of the symbol that was passed in as a parameter to a user-defined module. How is this useful? Well, suppose that you want to create a SAS/IML module that prints
In a previous blog post, I described how to generate combinations in SAS by using the ALLCOMB function in SAS/IML software. The ALLCOMB function in Base SAS is the equivalent function for DATA step programmers. Recall that a combination is a unique arrangement of k elements chosen from a set
Have you written a SAS/IML program that you think is particularly clever? Are you the proud author of SAS/IML functions that extend the functionality of SAS software? You've worked hard to develop, debug, and test your program, so why not share it with others? There is now a location for
In my four years of blogging, the post that has generated the most comments is "How to handle negative values in log transformations." Many people have written to describe data that contain negative values and to ask for advice about how to log-transform the data. Today I describe a transformation
A colleague asked me an interesting question: I have a journal article that includes sample quantiles for a variable. Given a new data value, I want to approximate its quantile. I also want to simulate data from the distribution of the published data. Is that possible? This situation is common.
Today is my 500th blog post for The DO Loop. I decided to celebrate by doing what I always do: discuss a statistical problem and show how to solve it by writing a program in SAS. Two ways to parameterize the lognormal distribution I recently blogged about the relationship between
In many areas of statistics, it is convenient to be able to easily construct a uniform grid of points. You can use a grid of parameter values to visualize functions and to get a rough feel for how an objective function in an optimization problem depends on the parameters. And
In my book Simulating Data with SAS, I specify how to generate lognormal data with a shape and scale parameter. The method is simple: you use the RAND function to generate X ~ N(μ, σ), then compute Y = exp(X). The random variable Y is lognormally distributed with parameters μ
In my recent post on how to understand character vectors in SAS/IML, I left out an important topic: How can you allocate a character vector of a specified length? In this article, "length" means the maximum number of characters in an element, not the number of elements in a vector.
Last week Chris Hemedinger posted an article about spam that is sent to SAS blogs and discussed how anti-spam software helps to block spam. No algorithm can be 100% accurate at distinguishing spam from valid comments because of the inherent trade-off between specificity and sensitivity in any statistical test. Therefore,
SAS programmers are probably familiar with how SAS stores a character variable in a data set, but how is a character vector stored in the SAS/IML language? Recall that a character variable is stored by using a fixed-width storage structure. In the SAS DATA step, the maximum number of characters
I have previously written about the scope of local and global variables in the SAS/IML language. You might wonder whether SAS/IML modules can also have local scope. The answer is no. All SAS/IML modules are known globally and can be called by any other modules. Some object-oriented programming languages support
While at SAS Global Forum 2014 I attended a talk by Jorge G. Morel on the analysis of data with overdispersion. (His slides are available, along with a video of his presentation.) The Wikipedia defines overdispersion as "greater variability than expected from a simple model." For count data, the "simple
Last month I blogged about defining SAS/IML functions that have default parameter values. This language feature, which was introduced in SAS/IML 12.1, enables you to skip arguments when you call a user-defined function. The same technique enables you to define optional parameters. Inside the function, you can determine whether the
The SAS/IML language has several functions for finding the unions, intersections, and differences between sets. In fact, two of my favorite utility functions are the UNIQUE function, which returns the unique elements in a matrix, and the SETDIF function, which returns the elements that are in one vector and not
Many geeky mathematical people celebrate "pi day" on March 14, because the date is written 3/14 in the US, which is evocative of the decimal representation of π = 3.14.... Most people are familiar with the decimal representation of π. The media occasionally reports on a new computational tour-de-force that
Like many SAS programmers, I use the Statistical Graphics (SG) procedures to graph my data in SAS. To me, the SGPLOT and SGRENDER procedures are powerful, easy to use, and produce fabulous ODS graphics. I was therefore surprised when a SAS customer told me that he continues to use the
My previous post described how to use the "missing response trick" to score a regression model. As I said in that article, there are other ways to score a regression model. This article describes using the SCORE procedure, a SCORE statement, the relatively new PLM procedure, and the CODE statement.
A fundamental operation in statistical data analysis is to fit a statistical regression model on one set of data and then evaluate the model on another set of data. The act of evaluating the model on the second set of data is called scoring. One of first "tricks" that I
