Fitting Models to Biological Data Using Linear and Nonlinear Regression: A Practical Guide to Curve Fitting

by Harvey Motulsky, Arthur Christopoulos

Overview

Most biologists use nonlinear regression more than any other statistical technique, but there are very few places to learn about curve-fitting. This book, by the author of the very successful Intuitive Biostatistics, addresses this relatively focused need of an extraordinarily broad range of scientists.

Product Details

ISBN-13:	9780195171792
Publisher:	Oxford University Press
Publication date:	05/27/2004
Pages:	352
Product dimensions:	9.70(w) x 7.06(h) x 0.88(d)

About the Author

University of Melbourne

Table of Contents

Fitting data with nonlinear regression1. An example of nonlinear regression2. Preparing data for nonlinear regression3. Nonlinear regression choices4. The first five questions to ask about nonlinear regression results5. The results of nonlinear regression6. Troubleshooting "bad fits"Fitting data with linear regression7. Choosing linear regression8. Interpreting the results of linear regressionModels9. Introducing models10. Tips on choosing a model11. Global models12. Compartmental models and defining a model with a differential equationHow nonlinear regression works13. Modeling experimental error14. Unequal weighting of data points15. How nonlinear regression minimized the sum-of-squaresConfidence intervals of the parameters16. Asymptotic standard errors and confidence intervals17. Generating confidence intervals by Monte Carlo simulations18. Generating confidence intervals via model comparison19. comparing the three methods for creating confidence intervals20. Using simulations to understand confidence intervals and plan experimentsComparing models21. Approach to comparing models22. Comparing models using the extra sum-of-squares F test23. Comparing models using Akaike's Information Criterion24. How should you compare modes-AICe or F test? 25. Examples of comparing the fit of two models to one data set26. Testing whether a parameter differs from a hypothetical valueHow does a treatment change the curve?27. Using global fitting to test a treatment effect in one experiment28. Using two-way ANOVA to compare curves29. Using a paired t test to test for a treatment effect in a series of matched experiments30. Using global fitting to test for a treatment effect in a series of matched experiments31. Using an unpaired t test to test for a treatment effect in a series of unmatched experiments32. Using global fitting to test for a treatment effect in a series of unmatched experimentsFitting radioligand and enzyme kinetics data33. The law of mass action34. Analyzing radioligand binding data35. Calculations with radioactivity36. Analyzing saturation radioligand binding data37. Analyzing competitive binding data38. Homologous competitive binding curves39. Analyzing kinetic binding data40. Analyzing enzyme kinetic dataFitting does-response curves41. Introduction to dose-response curves42. The operational model of agonist action43. Dose-response curves in the presence of antagonists44. Complex dose-response curvesFitting curves with GraphPad Prism45. Nonlinear regression with Prism46. Constraining and sharing parameters47. Prsim's nonlinear regression dialog48. Classic nonlinear models built-in to Prism49. Importing equations and equation libraries50. Writing user-defined models in Prism51. Linear regression with Prism52. Reading unknowns from standard curves53. Graphing a family of theoretical curves54. Fitting curves without regression