Gelman’s Candy Weighing Demonstration

We did Andrew Gelman’s candy weighing demonstration in class on Friday. This was the first time I’ve had a chance to teach sampling in some time and really wanted to do it. These were not traditional statistics students, however. We did this in research methods. So these are students interested in management and getting drug through a statistics course. And that might be putting it nicely. Nevertheless, they were good about the experiment. We also had some slight modifications to Gelman’s procedure. First, we used the measurements (in grams) printed right on the side of the packaging. And everyone did

My Review of Monogan’s Political Analysis Using R

The Journal of Statistical Software has published another review I wrote, this time of Monogan’s Political Analysis Using R: No Title No Description The book is a solid choice for a primary or supplementary text in a political or policy methodology class, at the level of advanced undergraduate or first-year graduate student. You can get more information from Springer’s website: Political Analysis Using R | James E. Monogan III | Springer This book provides a narrative of how R can be useful in the analysis of public administration, public policy, and political science data specifically, in…

The Severity of Severe Events is Increasing

On Thursday night, Mary Catherine Cochran, executive director of the Patapsco Heritage Greenway, asked some very insightful questions about my analysis of flooding in Ellicott City: These questions are worth going into some detail, so let me now discuss what it means that the data is changing. Data is considered to be stationary if it is random and if the characteristics from randomness, such as mean and variance, do not change over time. You can kind of think of this like a bus schedule. Sometimes the bus comes on time. Sometimes it is late. Sometimes, it is even early. However,

What is a 100-year flood?

Last night, Mary Catherine Cochran, executive director of the Patapsco Heritage Greenway, asked some very insightful questions about my analysis of flooding in Ellicott City: These questions are worth going into some detail, so let me begin by discussing first, how I account for changing statistics. The answer is, I don’t, but that doesn’t matter. The how is interesting, but the why is critical to understanding both severe storms and rare events. There’s a common misconception that the “100-year flood” is what happens whenever any flood event happens. You often hear any flood described as a 100-year flood, but that’s

Statistical Likelihood of Extreme Events and the Ellicott City Floods

This time, the flood hit close to home, literally. Over the last week, Ellicott City has responded after a very bad storm dropped nearly six inches of rain in only two hours. The recovery effort will be long and difficult, but the Ellicott City Partnership has done a remarkable job coordinating resources for both immediate and long term needs. The storm and its effects were severe and Ellicott City will require strong leadership, going forward. However, there’s been some accusations and finger pointing, about who may be responsible for inflicting what damage. The evidence given is usually the gross severity

NaN versus NA in R

R has two different ways of representing missing data and understanding each is important for the user. NaN means “not a number” and it means there is a result, but it cannot be represented in the computer. The second, NA, explains that the data is just missing for unknown reasons. These appear at different times when working with R and each has different implications. NaN is distinct from NA. NaN implies a result that cannot be calculated for whatever reason, or is not a floating point number. Some calculations that lead to NaN, other than , are attempting to take