Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-1 CHAPTER 17 BIVARIATE STATISTICS: NONPARAMETRIC TESTS.

Slides:



Advertisements
Similar presentations
Prepared by Lloyd R. Jaisingh
Advertisements

COMPLETE BUSINESS STATISTICS
Chapter 16 Introduction to Nonparametric Statistics
Irwin/McGraw-Hill © Andrew F. Siegel, 1997 and l Chapter 16 l Nonparametrics: Testing with Ordinal Data or Nonnormal Distributions.
Parametric/Nonparametric Tests. Chi-Square Test It is a technique through the use of which it is possible for all researchers to:  test the goodness.
© 2011 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license.
Hypothesis Testing IV Chi Square.
Chapter 13: The Chi-Square Test
Chapter 11 Contingency Table Analysis. Nonparametric Systems Another method of examining the relationship between independent (X) and dependant (Y) variables.
Chapter 12 Chi-Square Tests and Nonparametric Tests
Chapter 14 Analysis of Categorical Data
Chapter 12 Chi-Square Tests and Nonparametric Tests
Test statistic: Group Comparison Jobayer Hossain Larry Holmes, Jr Research Statistics, Lecture 5 October 30,2008.
Chapter 16 Chi Squared Tests.
Bivariate Statistics GTECH 201 Lecture 17. Overview of Today’s Topic Two-Sample Difference of Means Test Matched Pairs (Dependent Sample) Tests Chi-Square.
Statistics for Managers Using Microsoft® Excel 5th Edition
Aaker, Kumar, Day Seventh Edition Instructor’s Presentation Slides
© 2004 Prentice-Hall, Inc.Chap 10-1 Basic Business Statistics (9 th Edition) Chapter 10 Two-Sample Tests with Numerical Data.
Student’s t statistic Use Test for equality of two means
PSY 307 – Statistics for the Behavioral Sciences Chapter 19 – Chi-Square Test for Qualitative Data Chapter 21 – Deciding Which Test to Use.
15-1 Introduction Most of the hypothesis-testing and confidence interval procedures discussed in previous chapters are based on the assumption that.
BCOR 1020 Business Statistics
Chapter 12 Chi-Square Tests and Nonparametric Tests
Nonparametrics and goodness of fit Petter Mostad
Chapter 15 Nonparametric Statistics
Nonparametric or Distribution-free Tests
Inferential Statistics
AM Recitation 2/10/11.
Aaker, Kumar, Day Ninth Edition Instructor’s Presentation Slides
Statistics for Managers Using Microsoft Excel, 5e © 2008 Prentice-Hall, Inc.Chap 12-1 Statistics for Managers Using Microsoft® Excel 5th Edition Chapter.
Chapter 14: Nonparametric Statistics
NONPARAMETRIC STATISTICS
Nonparametric Statistics aka, distribution-free statistics makes no assumption about the underlying distribution, other than that it is continuous the.
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 11-1 Chapter 11 Chi-Square Tests and Nonparametric Tests Statistics for.
Chapter 16 The Chi-Square Statistic
© Copyright McGraw-Hill CHAPTER 13 Nonparametric Statistics.
1/23 Ch10 Nonparametric Tests. 2/23 Outline Introduction The sign test Rank-sum tests Tests of randomness The Kolmogorov-Smirnov and Anderson- Darling.
Biostatistics, statistical software VII. Non-parametric tests: Wilcoxon’s signed rank test, Mann-Whitney U-test, Kruskal- Wallis test, Spearman’ rank correlation.
Ordinally Scale Variables
Copyright © Cengage Learning. All rights reserved. 14 Elements of Nonparametric Statistics.
1 Nonparametric Statistical Techniques Chapter 17.
Nonparametric Tests: Chi Square   Lesson 16. Parametric vs. Nonparametric Tests n Parametric hypothesis test about population parameter (  or  2.
Lesson 15 - R Chapter 15 Review. Objectives Summarize the chapter Define the vocabulary used Complete all objectives Successfully answer any of the review.
Chapter 13 CHI-SQUARE AND NONPARAMETRIC PROCEDURES.
© aSup-2007 CHI SQUARE   1 The CHI SQUARE Statistic Tests for Goodness of Fit and Independence.
Copyright © 2010 Pearson Education, Inc. Slide
Copyright ©2011 Pearson Education, Inc. publishing as Prentice Hall 12-1 Chapter 12 Chi-Square Tests and Nonparametric Tests Statistics for Managers using.
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 11-1 Chapter 11 Chi-Square Tests and Nonparametric Tests Statistics for.
© Copyright McGraw-Hill CHAPTER 11 Other Chi-Square Tests.
Chapter 11: Chi-Square  Chi-Square as a Statistical Test  Statistical Independence  Hypothesis Testing with Chi-Square The Assumptions Stating the Research.
CHAPTERS HYPOTHESIS TESTING, AND DETERMINING AND INTERPRETING BETWEEN TWO VARIABLES.
CD-ROM Chap 16-1 A Course In Business Statistics, 4th © 2006 Prentice-Hall, Inc. A Course In Business Statistics 4 th Edition CD-ROM Chapter 16 Introduction.
Nonparametric Statistics
Tuesday PM  Presentation of AM results  What are nonparametric tests?  Nonparametric tests for central tendency Mann-Whitney U test (aka Wilcoxon rank-sum.
Chapter 15 The Chi-Square Statistic: Tests for Goodness of Fit and Independence PowerPoint Lecture Slides Essentials of Statistics for the Behavioral.
Biostatistics Nonparametric Statistics Class 8 March 14, 2000.
Section Copyright © 2014, 2012, 2010 Pearson Education, Inc. Lecture Slides Elementary Statistics Twelfth Edition and the Triola Statistics Series.
Outline of Today’s Discussion 1.The Chi-Square Test of Independence 2.The Chi-Square Test of Goodness of Fit.
Copyright c 2001 The McGraw-Hill Companies, Inc.1 Chapter 11 Testing for Differences Differences betweens groups or categories of the independent variable.
Chapter 14 Nonparametric Methods and Chi-Square Tests
Chapter Fifteen Chi-Square and Other Nonparametric Procedures.
Slide Slide 1 Copyright © 2007 Pearson Education, Inc Publishing as Pearson Addison-Wesley. Nonparametric Statistics.
Chapter 14 – 1 Chi-Square Chi-Square as a Statistical Test Statistical Independence Hypothesis Testing with Chi-Square The Assumptions Stating the Research.
Copyright © 2010, 2007, 2004 Pearson Education, Inc Lecture Slides Elementary Statistics Eleventh Edition and the Triola Statistics Series by.
© 2006 by The McGraw-Hill Companies, Inc. All rights reserved. 1 Chapter 11 Testing for Differences Differences betweens groups or categories of the independent.
Statistical Fundamentals: Using Microsoft Excel for Univariate and Bivariate Analysis Alfred P. Rovai Chi-Square Goodness-of- Fit Test PowerPoint Prepared.
Nonparametric statistics. Four levels of measurement Nominal Ordinal Interval Ratio  Nominal: the lowest level  Ordinal  Interval  Ratio: the highest.
1 Nonparametric Statistical Techniques Chapter 18.
Nonparametric Statistics Overview. Objectives Understand Difference between Parametric and Nonparametric Statistical Procedures Nonparametric methods.
Non-parametric Tests Research II MSW PT Class 8. Key Terms Power of a test refers to the probability of rejecting a false null hypothesis (or detect a.
Presentation transcript:

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-1 CHAPTER 17 BIVARIATE STATISTICS: NONPARAMETRIC TESTS

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-2 What The Experts Say A parametric procedure is an exact solution to an approximate problem, whereas a nonparametric procedure is an approximate solution to an exact problem. --Amir D. Aczel, Complete Business Statistics (Homewood, Ill.: Irwin/McGraw-Hill, 1999).

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-3 Learning Objectives Explain the use of various nonparametric tests Run various nonparametric tests Interpret the results obtained from nonparametric tests

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-4 Get This! Does Color Matter? Officials in the U.S. government responsible for several million questionnaires every year have reported that yellow paper produces the highest percentage of returns, with pink next in effectiveness Francis Buttle, a professor of marketing at Cranfield University in the United Kingdom, and Gavin Thomas, an independent marketing research consultant, were not convinced that color makes a difference They conducted an experiment as part of a large survey into the perceived cost and benefits of ISO 9000 in certified organizations.

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-5 Get This! Does Color Matter? – cont’d The experiment was designed to evaluate whether yellow-colored paper stock produced a significantly different response rate than white. More white questionnaires (29.32%) were returned than yellow (28.24%). The researchers used a statistical technique called “chi-square test of significance” to analyze the data. They concluded that the difference in response rates between yellow and white returns was not significant.

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-6 Now Ask Yourself Do you think paper color matters when it comes to deciding whether or not a questionnaire will be completed and mailed back to the researcher? Do you think the chi-square test of significance was really necessary to generate the findings? Why or why not? Could the Internet have been used to conduct a similar study? Why or why not?

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-7 Nonparametric methods of testing hypotheses are not concerned with particular population parameters. We do not have to know the shape of the population or make assumptions for the purpose of testing hypotheses. They have relatively easy computations and are relatively easy to understand. They can be used with ranked information and for tests involving small samples sizes. Their applications are limited to certain types of information. Nonparametric Tests

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-8 They tend to be less precise and efficient than parametric methods. They can be used in any of the following situations: –When the population distribution from which the sample is drawn cannot be assumed to be normal. –When the sampling distribution is known not to be normal. –When nonmetric (nominal- or ordinal-scaled) data are used. Nonparametric Tests – cont’d

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-9 Contingency Tables – Chi-Square Test of Independence A contingency table or cross-tabulation table is a statistical table in which row entries classify data according to one variable and column entries classify data according to another variable. When there are r rows and c columns in the table, it is called an r x c contingency table. –The frequencies in the cells are called cell frequencies. –The total of the frequencies in each row or each column is called the marginal frequency. –The same formula used to explain the goodness-of- fit test can be used to compute the value of  2.

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-10 where = observed frequency in cell i = expected or theoretical frequency in cell i k = number of mutually exclusive categories The number of degrees of freedom of an r x c contingency table is (r - 1)(c - 1). Contingency tables may be constructed in various ways. Sometimes they simply show the numbers of elements in each cell. Other times, raw percentages are provided in each cell. Contingency Tables – Chi-Square Test of Independence – cont’d

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-11 Rank-Sum Tests Use some sort of ranking totals in their calculations Wilcoxon Test Mann-Whitney (U) Test Kruskal-Wallis (H) Test

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-12 Wilcoxon Test for Matched Pairs  a.k.a., the signed-rank test  Analyzes ordinal data for differences between two related samples by using plus and minus signs and considers both the magnitudes of the differences and ranks of the differences between the paired values. –Test is used when there is a natural way to pair data. –Test works well for before and after data to test for a median difference of zero. –Test can take the place of a one-sample t-test when we cannot assume a normal distribution. –Purpose of the test is to decide whether the difference between a computed signed-rank sum and the expected rank sum of the same sign is large enough to be significant.

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-13 The sum of all ranks: 1, 2, 3, … n can be obtained by (n/2)(1+n) The expected value of T is ½ of the sum of all ranks, or E(T) = n(1+n)/4 When the sample size is large, preferably 10 or more, the sampling distribution of T is approximately normal. The standard error of the statistic T is and the standard normal z is Wilcoxon Test for Matched Pairs – cont’d

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-14 Mann-Whitney (U) Test a.k.a., the U test Is another type of rank-sum test. This test can be used to determine whether two independent samples are drawn from identical populations or from two populations with the same median. This test can take the place of the two- sample t-test when the researcher is unsure about the normality assumption.

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-15 Let n 1 = the number of items in sample A n 2 = the number of items in sample B The sum of cumulative items of first sample A, denoted by the letter U, can be obtained by two methods. Method 1.Count the number of A items that precede each B item. The sum of the numbers counted is the value of U. Method 2.Use the following formula: where R 1 = total of ranks of A items Mann-Whitney (U) Test – cont’d

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-16 When the sample sizes are large, preferably both n 1 and n 2 larger than 10, the sampling distribution of the U is approximately normal. The expected value of U is the standard error of the statistic U is and the standard normal z is Mann-Whitney (U) Test – cont’d

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-17 Kruskal-Wallis (H) Test A type of rank-sum test. This test can be used to determine whether k independent samples are drawn from identical populations or from k populations with the same median. This test may be used to substitute for the method of one-way analysis of variance. a.k.a., the H test If the null hypothesis that k samples are drawn from identical populations is true and each sample size is 5 or more, the sampling distribution of the statistic H can be approximated by the  2 distribution with D (degrees of freedom) = k - 1.

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-18 Groupings of Two Sample Nonparametric Tests TWO SAMPLES Independent Paired NONPARAMETRIC TEST Chi-Square Mann-Whitney Kruskal-Wallis Chi-Square Wilcoxin

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-19 Decision Time! We ran some of the nonparametric tests using Microsoft Excel and SPSS. As a marketing manager, you must be careful not to squander your company’s financial resources. In some of the computer runs, SPSS provided much more detailed results, but the SPSS software tends to be an added expense for companies since SPSS does not come with most computers like Excel does. Based on your brief experiences with the two types of software, would you spend a little more money to obtain more detailed results? Why or why not?

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-20 Net Impact The Internet: Does not aid in the analysis of nonparametric data, but it can be used to help explain why certain events occur. Can contribute information that helps researchers better understand the relationships that the tests reveal.

Marketing Research, 2 nd Edition Alan T. Shao Copyright © 2002 by South-Western PPT-21 Chapter 17 End of Presentation