~/talk

How to Properly Split-test Your WordPress Website

Talkat WordCamp Vienna 2015 · on Saturday, 2015-04-11· [wordpress, web-performance, developer-experience]
linkedin:igorkolosov
slides:none on file

Step-by-step checklist for valid WordPress split tests: set goals and KPIs, pick metrics and behavior/qualitative tools (Google Analytics Content Experiments, Optimizely, Visual Website Optimizer, Nelio, heatmaps and session recording), calculate sample size and honor the two-sided t-test requirement (example: 1,500 visitors per variation over 44 days), account for seasonality and business cycles, avoid caching and browser/device mismatches, prefer client-side jQuery/JS variations or separate URLs, expect ~30–40% win rate and treat “losing” tests as learning.

AI-written summary · about

  1. 0:00Introduction and welcome
  2. 0:45What is split testing
  3. 3:18Multivariate vs split testing
  4. 5:12Why split test designs
  5. 6:19Usability testing vs split testing
  6. 7:05Stepwise vs continuous redesign
  7. 8:30Continuous testing benefits
  8. 9:38Setting up measurements
  9. 12:07Defining sample size
  10. 13:55Seasonality in testing
  11. 14:39Aligning tests with business goals
  12. 15:48Creating testing roadmaps
  13. 16:34Business cycle considerations
  14. 17:40Technical checks before testing
  15. 19:28Tools and resources list
  16. 20:12What to test first
  17. 22:19Testing on WordPress
  18. 23:46Testing this presentation
  19. 24:51General testing pitfalls
  20. 27:03Misconceptions about failure
  21. 28:08Success rates in testing
  22. 28:30WordPress caching issues
  23. 30:16Plugin overload problems
  24. 31:42Clean testing solutions
  25. 32:02Recommended resources
  26. 32:26About the speaker
  27. 33:07Q&A and closing
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.