Bug alert in rqPen!

The website I found this on said lady bugs are pests? I thought they ate aphids? I have recently been working with the rqPen package in R In order to do some penalized median regression ($latex L_1$ regression with a group lasso penalty) and have found a bug in the group lasso code. As it …

The Traveling Salesman Problem: Installing Concorde on Mac Catalina with CPLEX

Long time no post and, unfortunately for the casual reader, this post is mostly describing how to install Concorde optimizer for the Traveling Salesman Problem (TSP) with Mac OS Catalina using the CPLEX backend. If this means nothing to you, click away! First: CPLEX is a commercial linear programming solver available free for the academic …

Deep Neural Network Playground

I'm trying to simulate some binary data that a Bayesian Deep Neural Network (BDNN?) will do a good job of predicting. This has proven difficult because 1) it's hard (for me!) to develop a complicated function of the covariates that would make sense to use a BDNN on and 2) to actually fit the BDNN …

Sometimes in research, you get stuck

And you feel just like this https://www.thecut.com/2019/02/chubby-rat-stuck-in-manhole-germany.html

The Bias-Variance Trade-off

As you get into statistics, you hear people talk about the "bias-variance trade-off" a lot. And when people mention it, they will often start discussing the mean-squared error, which is a function of the bias and variance of an estimator. Then you start looking at formulas. But what does this concept mean intuitively? To answer …

Statistically Speaking

Puns. We really tried hard to get you some good puns for this blog. Inspired by the writers of Statisfaction, we tried to think of clever names that would also let you know this was about statistics and data science, etc. Here are some options we ran through: Voulez-vous Cauchy avec moi? (voulezvouscauchy.wordpress.com, my personal …