DEV Community

#statistics

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
A/B testing: when the standard test is the wrong tool

A/B testing: when the standard test is the wrong tool

1
Comments
7 min read
Building a Real-Time Price Anomaly Detector with Python, SerpApi, and Robust Statistics

Building a Real-Time Price Anomaly Detector with Python, SerpApi, and Robust Statistics

1
Comments
11 min read
5 ML Math Concepts I Stopped Memorizing (And Started Actually Using)

5 ML Math Concepts I Stopped Memorizing (And Started Actually Using)

1
Comments
3 min read
The Fill Model Is Where Backtests Quietly Cheat

The Fill Model Is Where Backtests Quietly Cheat

Comments
4 min read
Percentiles, the IQR and the 1.5 Outlier Rule: How to Flag a Bad Row

Percentiles, the IQR and the 1.5 Outlier Rule: How to Flag a Bad Row

Comments
17 min read
Mean vs Median: When to Use Each, and When the Answer Changes

Mean vs Median: When to Use Each, and When the Answer Changes

Comments
16 min read
What Is a P-Value? Worked by Shuffling Nine Real Orders 126 Ways

What Is a P-Value? Worked by Shuffling Nine Real Orders 126 Ways

Comments
15 min read
Moving Averages: Smoothing a Series Without Smoothing Away the Truth

Moving Averages: Smoothing a Series Without Smoothing Away the Truth

Comments
17 min read
What a Clean Equity Curve Doesn't Prove

What a Clean Equity Curve Doesn't Prove

Comments
4 min read
What Shuffling Your Trade History Actually Tells You (And What It Doesn't)

What Shuffling Your Trade History Actually Tells You (And What It Doesn't)

Comments
4 min read
A/B Testing for Analysts: Sample Size First, Result Second

A/B Testing for Analysts: Sample Size First, Result Second

1
Comments
16 min read
Confidence Procedures Are Production Code

Confidence Procedures Are Production Code

Comments
9 min read
A Higher Pass Rate Can Mean a Worse Model. The Math Is Simpson's Paradox.

A Higher Pass Rate Can Mean a Worse Model. The Math Is Simpson's Paradox.

Comments
4 min read
A judge that agrees with your humans 92 percent of the time can be at 60 percent where the gate actually decides

A judge that agrees with your humans 92 percent of the time can be at 60 percent where the gate actually decides

Comments
8 min read
đź§© How Close Are We to the Human Limit of Solving a Rubik's Cube?

đź§© How Close Are We to the Human Limit of Solving a Rubik's Cube?

1
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.