202602270832
Status: #reference
Tags:
State: #nascient

Design and Analysis of Experiments

This is in a sense the entire point of statistics. While statistics is great for many purposes, most of this utility is obtained from things we learn in high-school, like computing the average of things, checking how spread out a distribution is, etc.

Design and analysis of experiments is where we start to do meta-statistics, we are not just asking what are the number which tell us about the world, but what is the minimum context, the minimal assumptions required, so that the numbers we derive about the world can be trusted.

Design of experiments is all about studying the art of setting up an experiment so that the results derived from it have statistical significance, and of setting up things as to maximize the Recall (Statistical Power) of a test.

Once the experiment is designed, and run, the data can be fed to an appropriate Inference Engine to make statistics. (Inference engines are the way I call the different branches of statistics.)

Relevant Links