DEV Community

#statistics

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
You Don't Need a Math PhD for Data Science — You Need to Stop Skipping the Boring Step

You Don't Need a Math PhD for Data Science — You Need to Stop Skipping the Boring Step

Comments
4 min read
Your eval monitor fired on four days this week. At your sample size, that was the most likely count

Your eval monitor fired on four days this week. At your sample size, that was the most likely count

Comments
8 min read
Run forty experiments against one eval set and you will find an improvement that is not there

Run forty experiments against one eval set and you will find an improvement that is not there

Comments 3
4 min read
Part 6 - STATISTICS

Part 6 - STATISTICS

Comments
8 min read
Your eval monitor fired on four days this week. At your sample size, that was the most likely count

Your eval monitor fired on four days this week. At your sample size, that was the most likely count

1
Comments
8 min read
Upgrading the judge ends one score series and starts another

Upgrading the judge ends one score series and starts another

5
Comments
9 min read
One account was 29% of the subset my recommendation rested on. I'm retracting the recommendation.

One account was 29% of the subset my recommendation rested on. I'm retracting the recommendation.

1
Comments
6 min read
AI told me a method didn't work. It had barely run it.

AI told me a method didn't work. It had barely run it.

Comments
18 min read
Beyond the Mean: An Engineer's Guide to Making Decisions with Statistical Inference

Beyond the Mean: An Engineer's Guide to Making Decisions with Statistical Inference

1
Comments
11 min read
Why "Accuracy" Is the Wrong Metric for Probabilistic Prediction Models

Why "Accuracy" Is the Wrong Metric for Probabilistic Prediction Models

Comments
4 min read
Your A/B test has three goals and they disagree. Now what?

Your A/B test has three goals and they disagree. Now what?

Comments
7 min read
A noisy judge does not just add error bars. It shrinks the effect you are trying to measure.

A noisy judge does not just add error bars. It shrinks the effect you are trying to measure.

1
Comments
11 min read
Part 5 - STATISTICS

Part 5 - STATISTICS

Comments
6 min read
I read the metric libraries of five widely-used eval tools. The metric was never the hard part.

I read the metric libraries of five widely-used eval tools. The metric was never the hard part.

Comments 3
7 min read
How many outcomes before you can quote a percentage?

How many outcomes before you can quote a percentage?

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