Sign in Subscribe

Topic

Statistics

A collection of 116 issues

Sampling Domain Knowledge

Say that we want to measure how often people go to risky websites. Let’s assume that the measurement of risk is expensive. We have data on how often people visit each domain on the web from a large sample. The number of unique domains in the data is large,

Homing in on the Home Advantage

A recent piece on ESPNCricinfo analyses the DRS data and argues that cricket should do away with neutral umpires. I reanalyzed the data. If a game is officiated by a home umpire, we expect the following: 1. Hosts will appeal less often as they are likely to be happier with

Nextdoor: Some Finer Points about KNN

The KNN classifier is one of the most intuitive ML algorithms. It predicts class by polling k nearest neighbors. Because it seems so simple, it is easy to miss a couple of the finer points: 1. Sample Splitting: Traditionally, when we split the sample, there is no peeking across samples.

Profit Maximizing Staffing

Say that there is a donation solicitation company. Say that there are 100M potential donors they can reach out to eachyear. Let’s also assume that the company gets paid on a contingency fee basis, getting a fixed percentage of all donations. The company currently follows the following process: it

Fooled by Randomness

Permutation-based methods for calculating variable importance and interpretation are increasingly common. Here are a few common places where they are used: Feature Importance (FI) The algorithm for calculating permutation-based FI is as follows: 1. Estimate a model 2. Permute a feature 3. Predict again 4. Estimate the decline in predictive

Monetizing Bad Models: Pay Per Correct Prediction

In many ML applications, especially ones where you need to train a model on customer data to get high levels of accuracy, the only models that ML SaaS companies can offer to a client out-of-the-box are bad. But many ML SaaS businesses hesitate to go to a client with a

The Nonscience of Machine Learning

In 2013, Girshick et al. released a paper that described a technique to solve an impossible-sounding problem—classifying each pixel of an image (or semantic segmentation). The technique that they proposed, R-CNN, combines deep learning, selective search, and SVM. It also has all sorts of ad hoc choices, from the

Fairly Certain: Using Uncertainty in Predictions to Diagnose Roots of Unfairness

One conventional definition of group fairness is that the ML algorithms produce predictions where the FPR (or FNR or both) is the same across groups. Fixating on equating FPR etc. can harm the very groups we are trying to help. So it may be useful to rethink how to solve

Optimal Data Collection When Strata and Strata Variances Are Known

With Ken Cor. What’s the least amount of data you need to collect to estimate the population mean with a particular standard error? For the simplest case—estimating the mean of a binomial variable using simple random sampling, a conservative estimate of the variance (p=.5), and a ±3

Equilibrium Fairness: How Fair Algorithms Can Hurt Those They Purport to Help

One definition of a fair algorithm is an algorithm that yields the same FPR across groups (an example of classification parity). To achieve that, we often have to trade in some accuracy. The final model is thus less accurate but fair. There are two concerns with such models: 1. Net