From the course: Machine Learning and AI Foundations: Prediction, Causation, and Statistical Inference
Unlock the full course today
Join today to access over 24,800 courses taught by industry experts.
Solution: Evaluate significant finding
From the course: Machine Learning and AI Foundations: Prediction, Causation, and Statistical Inference
Solution: Evaluate significant finding
(upbeat electro-pop music) - [Instructor] So here we are, we have these two different scores and the challenge was, what do we make of this? What does it mean by implication? Do we believe it? Two, what are the implications for future analysis? So let's go down the list of the things to think about when your p-value is below 0.05, which is certainly the case here. We have 2.9 times 10 to the negative fifth. I know it's a little frustrating sometimes when you get the scientific notation, but in other words we're well below 0.05 and it really should be thought of as a threshold phenomenon. So we've got a significant result. What do we make of it? Well, one possibility obviously is that this is real and that it represents a real phenomenon which has implications for further analysis, but let's rule out the other possibilities. So the first possibility to rule out is sure it's significant, but it's not meaningful in…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
-
(Locked)
Using probability to measure uncertainty8m 23s
-
(Locked)
p-value review1m 28s
-
(Locked)
Hypothesis testing checklist3m 59s
-
(Locked)
Taleb on normality, mediocristan, and extremistan2m 39s
-
(Locked)
Challenge: Evaluate significant finding1m 50s
-
(Locked)
Solution: Evaluate significant finding5m 34s
-
(Locked)
-
-
-
-