User manual SAS BASIC ANALYSIS AND GRAPHING RELEASE 9

[. . . ] Basic Analysis and Graphing Get the Most from JMP® Whether you are a first-time or a long-time user, there is always something to learn about JMP. Visit JMP. com and to find the following: · · · · · · live and recorded Webcasts about how to get started with JMP video demos and Webcasts of new features and advanced techniques schedules for seminars being held in your area success stories showing how others use JMP a blog with tips, tricks, and stories from JMP staff a forum to discuss JMP with other users http://www. jmp. com/getstarted/ Release 9 Basic Analysis and Graphing "The real voyage of discovery consists not in seeking new landscapes, but in having new eyes. " Marcel Proust JMP, A Business Unit of SAS SAS Campus Drive Cary, NC 27513 The correct bibliographic citation for this manual is as follows: SAS Institute Inc. JMP® 9 Basic Analysis and Graphing, Copyright © 2010, SAS Institute Inc. , Cary, NC, USA ISBN 978-1-60764-596-2 All rights reserved. Produced in the United States of America. [. . . ] In a logistic probability plot, the y-axis represents probability. For k response levels, k - 1 smooth curves partition the total probability (which equals 1) among the response levels. The fitting principle for a logistic regression minimizes the sum of the negative natural logarithms of the probabilities fitted to the response events that occur­that is, maximum likelihood. Ordinal Logistic Regression When Y is ordinal, a modified version of logistic regression is used for fitting. The cumulative probability of being at or below each response level is modeled by a curve. The curves are the same for each level except that they are shifted to the right or left. The ordinal logistic model fits a different intercept, but the same slope, for each of r - 1 cumulative logistic comparisons, where r is the number of response levels. Each parameter estimate can be examined and tested individually, although this is seldom of much interest. The ordinal model is preferred to the nominal model when it is appropriate because it has fewer parameters to estimate. In fact, it is practical to fit ordinal responses with hundreds of response levels. Example of Nominal Logistic Regression This example uses the Penicillin. jmp sample data table. The data in this example comes from an experiment where 5 groups, each containing 12 rabbits, were injected with streptococcus bacteria. Once the rabbits were confirmed to have the bacteria in their system, they were given different doses of penicillin. You want to find out whether the natural log (In(dose)) of dosage amounts has any effect on whether the rabbits are cured. 222 Performing Simple Logistic Regression Example of Nominal Logistic Regression Chapter 7 1. Open the Penicillin. jmp sample data table. Notice that JMP automatically fills in Count for Freq. Count was previously assigned the role of Freq. Click OK. Figure 7. 2 Example of Nominal Logistic Report Chapter 7 Performing Simple Logistic Regression Logistic Report 223 The plot shows the fitted model, which is the predicted probability of being cured, as a function of ln(dose). The p-value is significant, indicating that the dosage amounts have a significant effect on whether the rabbits are cured. Launch the Logistic Platform You perform a logistic analysis using either the Fit Y by X platform or the Logistic platform. · To launch the Fit Y by X platform, select Analyze > Fit Y by X. See Figure 3. 2 in the "Introduction to the Fit Y by X Platform" chapter. or · To launch the Logistic platform, from the JMP Starter window, click on the Basic category and then click Logistic. The Logistic launch window appears. Figure 7. 3 The Logistic Launch Window For details about this window, see the "Introduction to the Fit Y by X Platform" chapter. Logistic Report To produce the plot shown in Figure 7. 4, follow the instructions in "Example of Nominal Logistic Regression, " p. 221. 224 Performing Simple Logistic Regression Logistic Report Chapter 7 Figure 7. 4 Example of Logistic Report The Logistic report window contains the following: · · · · "Logistic Plot, " p. [. . . ] Tan, Charles Y. , and Iglewicz, Boris (1999), "Measurement-methods Comparisons and Linear Statistical Relationship, " Technometrics, 41:3, 192­201. (1976), "An Introduction to Quality Control, " Nagoya, Japan: Central Japan Quality Control Association. (1958), "Estimation of Relationships for Limited Dependent Variables, " Econometrica, 26 24­36. (1995), Applied Reliability, 2nd Edition. [. . . ]