Appendix A Linear regression and the normal equations
Linear regression is used in chapter 4 in the RSM analyze stage, as well as in chapter 5 in the contextual bandit’s map from context and action to reward. It appears in many contexts in experimentation, machine learning, and quantitative trading. In this appendix, you’ll learn about the core component of the solution to a linear regression problem, the normal equation.
A.1 Univariate linear regression
In chapter 4, section 4.1.3 we sought a model that could interpolate a function of the business metric—which, in chapter 4, was markout_profit(threshold)—between three measured values of the system’s parameter (which was threshold). While there are simpler linear algebraic methods tailored to ...
Get Experimentation for Engineers now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
