Statistically significance in A/B Testing

A/B Tests in Marketing – Sample Size and Significance using R

A/B Tests in Marketing – Sample Size and Significance using R

Hypothesis Test: Difference Between Proportions
http://stattrek.com/hypothesis-test/difference-in-proportions.aspx

G-test vs T-test, which is better for A/B testing?
http://stats.stackexchange.com/questions/25209/difference-between-g-test-and-t-test-and-which-should-be-used-for-a-b-testing

Awell-known A/B test tutorial:
http://elem.com/~btilly/effective-ab-testing/

How do you determine what is “statistically significant” when looking at the results of an A/B test?
http://www.quora.com/How-do-you-determine-what-is-statistically-significant-when-looking-at-the-results-of-an-A-B-test

For better understanding, one should take course in statistical inference:
https://www.edx.org/course/uc-berkeleyx/uc-berkeleyx-stat2-3x-introduction-1533#.VEVFCSSfiaB

Topics need to catch up with

1. survival model:

2. Basic statistics in R:

3. Time series

4. Useful personal website:

 

Regression Diagnostics in R

Regression diagnostics:

http://dept.stat.lsa.umich.edu/~kshedden/Courses/Stat600/Notes/diagnostics.pdf

http://socserv.socsci.mcmaster.ca/jfox/Courses/Brazil-2009/index.html

http://www.stat.columbia.edu/~martin/W2024/R7.pdf

How to do it in R? ->

http://www.statmethods.net/stats/rdiagnostics.html

https://www.youtube.com/watch?v=eTZ4VUZHzxw&index=2&list=PLqzoL9-eJTNBJrvFcN-ohc5G13E7Big0e

 

 

Questions to think about

  1. Positive correlation but negative coefficient in regression?

    Related: http://stats.stackexchange.com/questions/65446/postive-correlation-but-negative-coefficient-in-regression

  2. How To Determine If A Sample Is Representative

    Example: search engine queries: Evaluating the retrieval effectiveness of Web search engines using a representative query sample

  3. Statistical test to tell whether two samples are pulled from the same population?

    Summary:  Summary of Statistical Tests