Posts Tagged ‘ Significance ’

A/B Testing Primer and the DEED framework

November 14, 2017
By

Kaiser Fung, founder of Principal Analytics Prep and the Master of Science in Applied Analytics at Columbia, gives a short lecture on A/B testing for Harvard Business Review on Facebook Live.

Read more »

A/B Testing Primer and the DEED framework

November 14, 2017
By

Kaiser Fung, founder of Principal Analytics Prep and the Master of Science in Applied Analytics at Columbia, gives a short lecture on A/B testing for Harvard Business Review on Facebook Live.

Read more »

My letter to the New York Times is published

November 6, 2017
By

Kaiser Fung, founder of Principal Analytics Prep and author of Numbersense, reacts to the New York TImes Magazine article on Amy Cuddy and the power pose research program. He offers a guide to the controversy around the interpretation of data in social psychology experiments.

Read more »

Remember: p-values Are Not Effect Sizes

September 9, 2017
By
Remember: p-values Are Not Effect Sizes

Authors: John Mount and Nina Zumel. The p-value is a valid frequentist statistical concept that is much abused and mis-used in practice. In this article I would like to call out a few features of p-values that can cause problems in evaluating summaries. Keep in mind: p-values are useful and routinely taught correctly in statistics, … Continue reading Remember: p-values Are Not Effect Sizes

Read more »

Gelman digested read

August 16, 2017
By

It's hard to keep up with Andrew Gelman, so let me point to some interesting recent posts from his blog. Readings on philosophy of statistics (link): Andrew has a bunch of links of (mostly his own) writings about deep statistical issues. Science is about understanding how the world works, which involves questions of cause and effect, and randomness and unexplained variability. Data that can be observed are almost never sufficient…

Read more »

If you are using Facebook Ads split testing (A/B testing), stop fooling yourself

July 26, 2017
By

Kaiser Fung, founder of Principal Analytics Prep, and former director of Applied Analytics at Columbia University, explains why you can't run proper A/B tests on Facebook

Read more »

Dispute over analysis of school quality and home prices shows social science is hard

April 24, 2017
By
Dispute over analysis of school quality and home prices shows social science is hard

Most of my friends with families fret over school quality when deciding where to buy their homes. It's well known that good school districts are also associated with expensive houses. A feedback cycle is at work here: home prices surge where there are good schools; only richer people can afford to buy such homes; wealth brings other advantages, and so the schools tend to have better students, which leads to…

Read more »

My pre-existing United boycott, and some musing on randomness and fairness

April 12, 2017
By

You probably already saw the video - if not, do yourself a favor, and search for "man forcibly removed from overbooked United flight." Other than the video evidence, which is damning, we don't have many facts, other than assertions made by various parties, repeated endlessly on social media and mainline media. Some facts, such as the United CEO claiming the passenger was "belligerent," is an assault on the meaning of…

Read more »

sigr: Simple Significance Reporting

March 7, 2017
By
sigr: Simple Significance Reporting

sigr is a simple R package that conveniently formats a few statistics and their significance tests. This allows the analyst to use the correct test no matter what modeling package or procedure they use. Model Example Let’s take as our example the following linear relation between x and y: library('sigr') set.seed(353525) d <- data.frame(x= rnorm(5)) … Continue reading sigr: Simple Significance Reporting

Read more »

Be careful evaluating model predictions

December 3, 2016
By
Be careful evaluating model predictions

One thing I teach is: when evaluating the performance of regression models you should not use correlation as your score. This is because correlation tells you if a re-scaling of your result is useful, but you want to know if the result in your hand is in fact useful. For example: the Mars Climate Orbiter … Continue reading Be careful evaluating model predictions

Read more »


Subscribe

Email:

  Subscribe