Prueba

Analyzing Data with GraphPad Prism
A companion to GraphPad Prism version 3

Harvey Motulsky
President GraphPad Software Inc. Hmotulsky@graphpad.com

GraphPad Software, Inc.

© 1999 GraphPad Software, Inc. All rights reserved. All Rights Reserved. GraphPad Prism, Prism and InStat are registered trademarks of GraphPad Software, Inc. GraphPad is a trademark of GraphPad Software, Inc.Use of the software is subject to the restrictions contained in the accompanying software license agreement. Citation: H.J. Motulsky, Analyzing Data with GraphPad Prism, 1999, GraphPad Software Inc., San Diego CA, www.graphpad.com. Acknowledgements: The following individuals made substantial contributions towards development of this book: Arthur Christopoulos (Neuroscience Research inPsychiatry, Univ. Minnesota), Lee Limbird (Dept. Pharmacology, Vanderbilt University), Rick Neubig (Dept. Pharmacology, Univ. Michigan), Paige Searle (Vice-president GraphPad Software). How to reach GraphPad: Phone: Fax: Email: Web: Mail: 858-457-3909 (619-457-3909 before June 12, 1999) 858-457-8141 (619-457-8141 before June 12, 1999) support@graphpad.com or sales@graphpad.com www.graphpad.comGraphPad Software, Inc. 5755 Oberlin Drive #110 San Diego, CA 92121 USA

Contents
Preface.........................................................................................................2 Introduction to statistical comparisons..........................................................3
Garbage in, garbage out................................................................................... 3 When do you need statistical calculations? ........................................................ 3 The key concept: Sampling from a population.................................................... 4 Confidence intervals ........................................................................................ 8 P values.......................................................................................................... 9 Hypothesis testing and statistical significance................................................... 11 Statistical power ............................................................................................ 13 A Bayesian perspective on interpreting statistical significance............................ 15 Beware of multiple comparisons..................................................................... 17 Outliers......................................................................................................... 18

Analyzing one group...................................................................................23
Entering data to analyze one group................................................................. 23 Frequency distributions .................................................................................. 24 Column statistics............................................................................................ 25 Interpreting descriptive statistics...................................................................... 26 The results of normalitytests........................................................................... 29 The results of a one-sample t test..................................................................... 30 The results of a Wilcoxon rank sum test........................................................... 34 Row means and totals .................................................................................... 37

t tests andnonparametric comparisons .......................................................39
Introduction to comparing of two groups ......................................................... 39 Entering data to compare two groups with a t test (or a nonparametric test) ........ 39 Choosing an analysis to compare two groups................................................... 41 The results of an unpaired t...