This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: ENGR 19500 — Function Discovery Choosing a Model—Function Discovery Excel and MATLAB extend the tools of linear regression to other data models. An important skill in modeling is identifying the functional relationship between two variables of interest. Some common functions of interest are Linear: y(x) = mx + b Power: y(x) = b x m Exponential: y(x) = b 10 mx Logarithmic: x(y) = b 10 my Fortunately, these functions all have unique behaviors that distinguish them. Frequently, the context of the variables being modeled will determine one or more model parameters. Steps for function discovery To discover which of these functions best represents the relationship between two variables, we will consider what the data and the theory indicate near the origin. Sometimes, it will be useful to plot the data on various types of axis scales as a diagnostic tool to understand the nature of the relationship. • Examine data and theory near the origin; look for zeros and ones for a hint as to type....
View Full Document
This note was uploaded on 04/23/2011 for the course ENGR 132 taught by Professor Kutson during the Spring '11 term at Purdue.
- Spring '11