https://nalar.dev/tags/statistics/ Recent content in Statistics on Nalar Hugo en-us Wed, 02 Sep 2026 00:00:00 +0700 https://nalar.dev/bootstrap-confidence-intervals-with-resampling/ Wed, 02 Sep 2026 00:00:00 +0700 https://nalar.dev/bootstrap-confidence-intervals-with-resampling/ <p>A point estimate hides uncertainty. Reporting that median latency is 180 ms or a conversion-rate difference is 1.4 percentage points does not show how much that estimate might move if another sample were collected.</p> <p>Bootstrap resampling is a practical way to estimate sampling uncertainty when deriving an analytic formula is difficult or when the statistic is not a simple mean.</p> <h2 id="the-bootstrap-idea">The bootstrap idea</h2> <p>Given an observed sample of size <code>n</code>:</p> https://nalar.dev/robust-outlier-detection-with-median-absolute-deviation/ Wed, 02 Sep 2026 00:00:00 +0700 https://nalar.dev/robust-outlier-detection-with-median-absolute-deviation/ <p>Outlier detection often begins with a rule such as &ldquo;flag values more than three standard deviations from the mean.&rdquo; That works reasonably well for approximately normal data without severe contamination, but the same extreme observations you want to detect can move both the mean and the standard deviation.</p> <p>Median absolute deviation, usually abbreviated MAD, provides a more robust alternative.</p> <h2 id="why-mean-and-standard-deviation-can-be-fragile">Why mean and standard deviation can be fragile</h2> <p>Consider response times in milliseconds:</p>