From the course: The Data Science of Experimental Design
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Choosing a test statistic
From the course: The Data Science of Experimental Design
Choosing a test statistic
- [Instructor] Now that we are gearing up for our experiment, we need to choose a test statistic. Please do not fear those of you without a statistics background. After you finish this course you'll be able to calculate your statistic using an Excel calculator I'll give you. So, you don't have to be an expert. But in this video, I'm going to teach you the theory behind the scenes. So, there are two main choices you can pick for statistics in your experiment. The confidence interval way or the chi-squared test way. Some of you might be familiar with confidence intervals already. These are ranges you can calculate when you assume your data represents a sample of a larger data set. Like in our scenario we set up our webpage, ran it for a while, and got a baseline 7% conversion rate, which estimates what we'd likely see in another time increment of the same length as the one we observed. So that's a sample. Because…
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.