Publications by Wesley
JSM 2013 – Tuesday
The Joint Statistical Meeting in Montreal has proven to be very good. Here are a few highlight from Tuesday’s sessions. There is one major problem that exists and that is there are too many good sessions to attend. During one time block I had six session that I wanted to go to. Unfortunately, it is simply not possible to make it to all...
3270 sym 2 img
JSM 2013 – Wednesday
I was able to attend a continuing education short course workshops at the JSM conference that proved to be quite insightful. The discussion was on data mining and was titled “Applied Data Mining Analysis: A Step-by-Step Introduction Using Real-World Data Sets”. The presentation was given by Dan Steinberg and the examples that he gave were...
1677 sym
Data Scientists and Statisticians: Can’t We All Just Get Along
It seems that the title “data science” has taken the world by storm. It’s a title that conjures up almost mystical abilities of a person garnering information from oceans of data with ease. It’s where a data scientist can wave his or her hand like a Jedi Knight and simply tell the data what it should be. What is interesting about the ...
5251 sym 2 img
When Discussing Confidence Level With Others…
This post spawned from a discussion I had the other day. Confidence intervals are notoriously a difficult topic for those unfamiliar with statistics. I can’t really think of another statistical topic that is so widely published in newspaper articles, television, and elsewhere that so few people really understand. It’s been this way since the ...
4766 sym R (2799 sym/1 pcs) 8 img
Passing-Bablok Regression: R code for SAS users
While at the Joint Statistical Meeting a few weeks ago I was talking to a friend about various aspects to clinical trials. He indicated that no current R package was able to perfectly reproduce Passing-Bablok (PB) regression so that it exactly matched SAS. He ultimately wrote a couple of functions and kindly shared them with me so that I could sh...
1777 sym R (2353 sym/1 pcs) 4 img
The Beta Prior, Likelihood, and Posterior
The Beta distribution (and more generally the Dirichlet) are probably my favorite distributions. However, sometimes only limited information is available when trying set up the distribution. For example maybe you only know the lowest likely value, the highest likely value and the median, as a measure of center. That information is sufficien...
2847 sym R (6081 sym/1 pcs) 4 img
Probability of Avoiding a Run-off in the NYC 2013 Democratic Primary Election
The New York City mayoral Democratic primary election is taking place this coming Tuesday (Sep. 10th) and there are several candidates in the running. Bill de Blasio is the front runner and is expected to win. However, there is a catch. Even if he takes the plurality of the vote he may not actually win. In New York if the candidate does not get a...
4369 sym R (2251 sym/1 pcs) 2 img
The Eve of the NYC Democratic Mayoral Primary Election
It is the eve of the New York City Democratic mayoral primary election. This is a simple follow-up on my post from last Friday as I was curious how the final pre-Election Day polling was going to fall. It’s fairly clear who is going to get the most votes. Though we have a very good idea who is going to take the nomination it is still not ...
2540 sym R (2974 sym/1 pcs) 4 img
A Monty Simulation
I was listening to Science Friday from Sep 6th. and one of the discussions by Ira Flatow was on the well known Monty Hall Problem. This problem has been hashed out many times and in fact I was first introduced to the probability aspects of the problem while taking my introductory to statistics class when I was an undergraduate. Though the sol...
1339 sym R (1680 sym/1 pcs) 2 img
Profile Likelihood for New Jersey U.S. Senate Special Election
As it stands right now Cory Booker has a very good chance of winning the New Jersey Special U.S. Senate election on October 16 to replace Frank Lautenberg and fill the remainder of his term for the next 15 months. So with the election only about a month away I took advantage of some of the data from the pre-election polls to produce a likelihoo...
3250 sym R (2468 sym/1 pcs) 10 img