Published on March 5, 2014
Most A/B testing results are Illusory Martin Goodson, Skimlinks
These are my opinions not those of my employer!
What’s an A/B test? Example: Free delivery A: Control B: Variant
‘How can you talk for 40 minutes about A/B testing?’
A/B tests are very easy to get wrong
What my experience is based on
What this talk is about 3 Statistical concepts Errors and consequences These errors are exactly how A/B testing software works
What this talk is about Statistical Power Multiple Testing Regression to the Mean
What is Statistical Power? The probability that you will detect a true difference between two samples
What is Statistical Power? Example: are men taller than women, on average?
What is Statistical Power? Example: free delivery on a website
Why is Statistical Power important? 1. False negatives 2. False positives
Precision Proportion of true positives in the positive results Its a function of power, significance level and prevalence.
If you have good power? Out of 100 tests 10 really drive uplift You detect 8 5 false positives 8/13 of positive tests are real
If you have bad power? Out of 100 tests 10 really drive uplift You detect 3 5 false positives 3/8 of winning tests are real!
Marketer: ‘We need results in 2 weeks time’ Me: ‘We can’t run this test for only two weeks we won’t get robust results’
Marketer: ‘We need results in 2 weeks time’ Me: ‘We can’t run this test for only two weeks we won’t get robust results’ Marketer: ‘Why are you being so negative?’
Calculating Power Alpha: probability of a positive result when the null hypothesis is true (5%) Beta: probability of not seeing a positive result when the null hypothesis is true Power = 1- Beta (80-90%)
Calculating Power Use a power calculator: Online R (power.prop.test) python (statsmodels.stats.power)
Approximate sample sizes Using a power calculator and asking for 80% power and significance level of 5%: 6000 conversions to detect 5% uplift 1600 conversions to detect 10% uplift
Effect of multiple testing if you run 20 tests at a significance level of 5% you will obtain 1 win, just by chance.
Giving targets for successful tests.
Stopping tests early
Stopping tests early Simulations show that stopping an A/A test when you see a positive results will result in successful test 41% of the time.
Stopping tests early That works out to a precision of 20%
Negative uplift. Stopping an A/B test with negative effect results in a win 9% of the time!
A True Story
Regression to the mean Give 100 students a true/false test They all answer randomly Take only the top scoring 10% of the class Test them again What will the results be?
Estimates of uplift are generally wrong.
What you need to do to get it right ● Do a power calculation first to estimate sample size ● Use a valid hypothesis - don’t use a scattergun approach ● Do not stop the test early ● Perform a second ‘validation’ test
My details firstname.lastname@example.org @martingoodson http://goo.gl/jvhwmB Download my whitepaper on A/B testing here
Skimlinks After Party! Levante Bar 5 minutes away Come hungry! Invites + Map at the booth http://skimlinks.com/jobs
Presentación que realice en el Evento Nacional de Gobierno Abierto, realizado los ...
In this presentation we will describe our experience developing with a highly dyna...
Presentation to the LITA Forum 7th November 2014 Albuquerque, NM
Un recorrido por los cambios que nos generará el wearabletech en el futuro
Um paralelo entre as novidades & mercado em Wearable Computing e Tecnologias Assis...
Menu My opinionated talk on A/B testing 08 May 2015. Talk from PyData London 2014. Most Winning A/B Test Results are Illusory. Talk Summary. Many people ...
http://www.slideshare.net/PyData/py-data-goodson ... Most Winning A/B Test Results are Illusory ... A/B testing results? | Qubit | March 2014 ...
Martin Goodson 26 June 2015 My ... PyData London 2014 Most Winning A/B Test Results are Illusory Talk Summary Many people have started to suspect that ...
Martin Goodson (Skimlinks) Most Winning A/B Test Results are Illusory Level: Intermediate ... Schedule for Sunday, Feb 23, 2014. Time:
... PyData London co-organiser, ... Martin Goodson Skimlinks Most Winning A/B Test Results are Illusory. ... and is chair of EuroPython 2014 in Berlin, ...
http://pydata.org/ PyData ... Evidence from a Matched Dataset in Central London by PyData. ... Martin Goodson - Most Winning A/B Test Results are Illusory
Martin Goodson - Machine learning ... My opinionated talk on A/B testing Martin Goodson - Most Winning A/B Test Results are Illusory. 6. 7. 2 comments ...
View Martin Goodson’s professional profile on LinkedIn. ... May 2012 – January 2014 (1 year 9 months) London, ... Most A/B test results are illusory.