How to determine if your A/B test is statistically significant
A/B testing tools often lie about whether something is "statistically significant." Here's an extremely simple, mathematically sound formula to compute it for yourself.
Topics /
The most popular blog posts about tech industry & business on Hacker News. 16,898 posts.
A/B testing tools often lie about whether something is "statistically significant." Here's an extremely simple, mathematically sound formula to compute it for yourself.
Derek Sivers official site. Thoughts on philosophy, culture, self-improvement. Author of Useful Not True, How to Live, Hell Yeah or No, Anything You Want.
« Reading List: The Apollo 11 Moon Landing | Main | Mozilla Thunderbird "Domain Name Mismatch": Explanation and Work-Around »
Short, fun but useful startup advice in just three words. Please add your own!
Learn about Meta: our mission, principles, leadership, who owns the company, apps (Instagram, Facebook, WhatsApp, Threads) and products like Quest.
A computational knowledge engine accessing trillions of pieces of curated data and millions of lines of algorithms will soon be released by Wolfram Research.
Automating releases, semantic version bumps, and API calls often involves configuring branch permissions and storing long-lived credentials in pipeline variables. Managing credential rotation adds an ongoing maintenance burden. Today, we’re introducing granular step-level permissions and container tokens in Bitbucket…
npm Blog (Archive); updates from the npm team are now published on the GitHub Blog and the GitHub Changelog
The folks at Behance and Cool Hunting asked me to talk at their 99% Conference a couple months ago. The 99% conference is aimed at creative professionals and is focused on Edison’s “99% perspiration.” And in the spirit of how to get your ideas to happen, they asked me to talk about entrepreneurship and the myriad […]
programming, philosophy, history, internet, startups
We’re building business infrastructure. As with other kinds of infrastructure (like hosting or electricity), we'd like to make it available to as broad a set of users as possible.
The original iPhone was great on day one. It couldn’t do as much as today’s iPhone, but it performed its feature-set extremely well. There were almost no rough edges or unpolished areas in its hardware or software, and nearly everything seemed justifiable, well conceived, and well executed.