TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Good Experiment, Bad Experiment

25 pointsby xtacyover 5 years ago

3 comments

mwexlerover 5 years ago
This is philosophically interesting, but little of this really is about _running_ a good experiment. Perhaps it&#x27;s about choosing which ones to run?<p>Kohavi&#x27;s book will probably provide much more value than this kind of abstract post. See <a href="https:&#x2F;&#x2F;experimentguide.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;experimentguide.com&#x2F;</a> for more details.
评论 #22277198 未加载
daveFNbuckover 5 years ago
&gt; Good experiments define success up-front.<p>This is absolutely critical. If you&#x27;re not defining success up-front, you&#x27;re not running an experiment. You&#x27;re just doing a staged rollout. You can use the data to craft whatever story you want for most changes.
Nzenover 5 years ago
tl;dr former Slack director of product outlines twelve principles for a&#x2F;b type experiments with features, products, whatever. (ex Good experiments involve analyzing the results as opposed to &#x27;ship&#x2F;kill?&#x27;) Each principle has a couple of sentences of elaboration and calls out the opposite style to avoid.