Testing people for coronavirus is a public health measure that reduces the spread of coronavirus. Dr. Anthony Fauci, a US infectious disease expert, recently mentioned the concept of "pool testing." The verb "to pool" means "to combine from different sources." In a USA Today article, Dr. Deborah Birx, the coordinator

## Tag: **Statistical Thinking**

The first time I saw a formula for the pooled variance, I was quite confused. It looked like Frankenstein's monster, assembled from bits and pieces of other quantities and brought to life by a madman. However, the pooled variance does not have to be a confusing monstrosity. The verb "to

Every day we face risks. If we drive to work, we risk a fatal auto accident. If we eat red meat and fatty foods, we risk a heart attack. If we go out in public during a pandemic, we risk contracting a disease. A logical response to risk is to

During an outbreak of a disease, such as the coronavirus (COVID-19) pandemic, the media shows daily graphs that convey the spread of the disease. The following two graphs appear frequently: New cases for each day (or week). This information is usually shown as a histogram or needle plot. The graph

Books about statistics and machine learning often discuss the tradeoff between bias and variance for an estimator. These discussions are often motivated by a sophisticated predictive model such as a regression or a decision tree. But the basic idea can be seen in much simpler situations. This article presents a

The ROC curve is a graphical method that summarizes how well a binary classifier can discriminate between two populations, often called the "negative" population (individuals who do not have a disease or characteristic) and the "positive" population (individuals who do have it). As shown in a previous article, there is

The purpose of this article is to show how to use SAS to create a graph that illustrates a basic idea in a binary classification analysis, such as discriminant analysis and logistic regression. The graph, shown at right, shows two populations. Subjects in the "negative" population do not have some

In a previous article, I showed how to perform collinearity diagnostics in SAS by using the COLLIN option in the MODEL statement in PROC REG. For models that contain an intercept term, I noted that there has been considerable debate about whether the data vectors should be mean-centered prior to

In my book Simulating Data with SAS, I show how to use a graphical tool, called the moment-ratio diagram, to characterize and compare continuous probability distributions based on their skewness and kurtosis (Wicklin, 2013, Chapter 16). The idea behind the moment-ratio diagram is that skewness and kurtosis are essential for

Longitudinal data are used in many health-related studies in which individuals are measured at multiple points in time to monitor changes in a response variable, such as weight, cholesterol, or blood pressure. There are many excellent articles and books that describe the advantages of a mixed model for analyzing longitudinal

In a linear regression model, the predicted values are on the same scale as the response variable. You can plot the observed and predicted responses to visualize how well the model agrees with the data, However, for generalized linear models, there is a potential source of confusion. Recall that a

In a previous article, I mentioned that the VLINE statement in PROC SGPLOT is an easy way to graph the mean response at a set of discrete time points. I mentioned that you can choose three options for the length of the "error bars": the standard deviation of the data,

Is 4 an extreme value for the standard normal distribution? In high school, students learn the famous 68-95-99.7 rule, which is a way to remember that 99.7 percent of random observation from a normal distribution are within three standard deviations from the mean. For the standard normal distribution, the probability

At SAS Global Forum 2019, Daymond Ling presented an interesting discussion of binary classifiers in the financial industry. The discussion is motivated by a practical question: If you deploy a predictive model, how can you assess whether the model is no longer working well and needs to be replaced? Daymond

I think every course in exploratory data analysis should begin by studying Anscombe's quartet. Anscombe's quartet is a set of four data sets (N=11) that have nearly identical descriptive statistics but different graphical properties. They are a great reminder of why you should graph your data. You can read about

An important concept in multivariate statistical analysis is the Mahalanobis distance. The Mahalanobis distance provides a way to measure how far away an observation is from the center of a sample while accounting for correlations in the data. The Mahalanobis distance is a good way to detect outliers in multivariate

Statisticians often emphasize the dangers of extrapolating from a univariate regression model. A common exercise in introductory statistics is to ask students to compute a model of population growth and predict the population far in the future. The students learn that extrapolating from a model can result in a nonsensical

Feature generation (also known as feature creation) is the process of creating new features to use for training machine learning models. This article focuses on regression models. The new features (which statisticians call variables) are typically nonlinear transformations of existing variables or combinations of two or more existing variables. This

A frequent topic on SAS discussion forums is how to check the assumptions of an ordinary least squares linear regression model. Some posts indicate misconceptions about the assumptions of linear regression. In particular, I see incorrect statements such as the following: Help! A histogram of my variables shows that they

A SAS programmer recently asked how to interpret the "standardized regression coefficients" as computed by the STB option on the MODEL statement in PROC REG and other SAS regression procedures. The SAS documentation for the STB option states, "a standardized regression coefficient is computed by dividing a parameter estimate by

In a previous article, I showed how to find the intersection (if it exists) between two line segments in the plane. There are some fun problems in probability theory that involve intersections of line segments. One is "What is the probability that two randomly chosen chords of a circle intersect?"

Suppose you want to find observations in multivariate data that are closest to a numerical target value. For example, for the students in the Sashelp.Class data set, you might want to find the students whose (Age, Height, Weight) values are closest to the triplet (13, 62, 100). The way to

Last week I got the following message: Dear Rick: How can I create a normal distribution within a specified range (min and max)? I need to simulate a normal distribution that fits within a specified range. I realize that a normal distribution is by definition infinite... Are there any alternatives,

This article describes the advantages and disadvantages of principal component regression (PCR). This article also presents alternative techniques to PCR. In a previous article, I showed how to compute a principal component regression in SAS. Recall that principal component regression is a technique for handling near collinearities among the regression

How can you specify weights for a statistical analysis? Hmmm, that's a "weighty" question! Many people on discussion forums ask "What is a weight variable?" and "How do you choose a weight for each observation?" This article gives a brief overview of weight variables in statistics and includes examples of

Pearson's correlation measures the linear association between two variables. Because the correlation is bounded between [-1, 1], the sampling distribution for highly correlated variables is highly skewed. Even for bivariate normal data, the skewness makes it challenging to estimate confidence intervals for the correlation, to run one-sample hypothesis tests ("Is

Last week I blogged about the broken-stick problem in probability, which reminded me that the broken-stick model is one of the many techniques that have been proposed for choosing the number of principal components to retain during a principal component analysis. Recall that for a principal component analysis (PCA) of

Skewness is a measure of the asymmetry of a univariate distribution. I have previously shown how to compute the skewness for data distributions in SAS. The previous article computes Pearson's definition of skewness, which is based on the standardized third central moment of the data. Moment-based statistics are sensitive to

On discussion forums, I often see questions that ask how to Winsorize variables in SAS. For example, here are some typical questions from the SAS Support Community: I want an efficient way of replacing (upper) extreme values with (95th) percentile. I have a data set with around 600 variables and

In the classic textbook by Johnson and Wichern (Applied Multivariate Statistical Analysis, Third Edition, 1992, p. 164), it says: All measures of goodness-of-fit suffer the same serious drawback. When the sample size is small, only the most aberrant behaviors will be identified as lack of fit. On the other hand,