randomized experiment
An experimental design, pioneered by Ronald Fisher, in which treatment is randomly assigned to eliminate confounding factors, allowing causal effects of interventions to be estimated.
As defined in 196 | Judea Pearl on Cause and Effect
Where it comes up · 2
- 196 | Judea Pearl on Cause and Effect3 claims
- Ian Ayres on Super Crunchers and the Power of Data 10/22/20072 claims
Most important claims · 5 of 5Search all claims for “randomized experiment” →
- Reasoning is organized into a three-level hierarchy: level one is association/statistics (inferring the likelihood of one event from observing another, which covers correlation and 99% of machine learning); level two is intervention/action (what happens if I do X, which changes the probability space and is learnable from randomized experiments); and level three is counterfactual reasoning (explanation, retrospection, imagination, asking what would have happened had something not occurred).196 | Judea Pearl on Cause and Effect
- Capital One combines historical data mining (correlating customer attributes to predict products before an operator even answers, and computing counter-offers for rate negotiations) with massive randomized experiments on mailings to identify which promotions cause more new accounts.Ian Ayres on Super Crunchers and the Power of Data 10/22/2007
- The 1960s smoking-cancer controversy could not be settled by a randomized experiment (which would be unethical), and Fisher argued a hidden gene could make people both crave nicotine and develop cancer; the debate was resolved by bringing knowledge of plausibility to bear—calculating that such a gene would have to make carriers eight times more likely to smoke, a strength judged implausible.196 | Judea Pearl on Cause and Effect
- Ronald Fisher's introduction of randomized experiments changed the practice but not the philosophy of statistics, because he refused to talk in counterfactual terms and so could not prove that randomization yields the answer the farmer wants; Jerzy Neyman could prove it, but Fisher refused to use Neyman's notation, yet still convinced the community that randomization eliminates confounding factors.196 | Judea Pearl on Cause and Effect
- Measurement difficulties limit where statistical analysis can work: when you can't measure the outcome you care about (standard of living, happiness), lack a large enough comparable historical dataset, or can't run a randomized experiment, statistical prediction cannot answer the question.Ian Ayres on Super Crunchers and the Power of Data 10/22/2007