This preview shows pages 1–5. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Nonlinear regression Basic concepts and differences with linear Ideas behind LevenbergMarquardt Potential pitfalls Tools in Python HW#5 due today. Midterm ‘proposals’ due on Tuesday! A common task for scientists is to compare a set of measured data with a mathematical (theoretical) model. Simplest model is a line: Problem is to determine the slope and intercept which ‘best fits’ the data. Criteria for ‘best fit’ is that which minimizes the sum of squares of the residuals (difference between data point and model). A type of ‘optimization’ problem. f ( x ) = mx + b Plot of the sum of squares of the residuals vs free parameters shows how fit values do in fact find the minimum. Write code to determine slope and intercept from linear data. Use it to coefficient and decay constant for data: Plot the fit and data together on a loglinear plot (use semilogy) X Y ========== 0.0 2.10 0.2 0.92 0.4 0.55 0.6 0.21 0.8 0.15 1.0 0.04...
View
Full
Document
This note was uploaded on 10/05/2010 for the course PHYS phy503 taught by Professor Gladden during the Spring '09 term at Ole Miss.
 Spring '09
 Gladden

Click to edit the document details