Intro to Statistics for the Behavioral Sciences PSYC 1900 Lecture 17: Nonparametric Tests & Course Summary.

Slides:



Advertisements
Similar presentations
Chapter 16 Introduction to Nonparametric Statistics
Advertisements

KRUSKAL-WALIS ANOVA BY RANK (Nonparametric test)
PSY 307 – Statistics for the Behavioral Sciences Chapter 20 – Tests for Ranked Data, Choosing Statistical Tests.
Ordinal Data. Ordinal Tests Non-parametric tests Non-parametric tests No assumptions about the shape of the distribution No assumptions about the shape.
INTRODUCTION TO NON-PARAMETRIC ANALYSES CHI SQUARE ANALYSIS.
statistics NONPARAMETRIC TEST
Lecture 10 Non Parametric Testing STAT 3120 Statistical Methods I.
Nonparametric tests and ANOVAs: What you need to know.
© 2003 Pearson Prentice Hall Statistics for Business and Economics Nonparametric Statistics Chapter 14.
EPI 809 / Spring 2008 Wilcoxon Signed Rank Test. EPI 809 / Spring 2008 Signed Rank Test Example You work in the finance department. Is the new financial.
Analysis of Variance. Experimental Design u Investigator controls one or more independent variables –Called treatment variables or factors –Contain two.
Statistics 07 Nonparametric Hypothesis Testing. Parametric testing such as Z test, t test and F test is suitable for the test of range variables or ratio.
PSY 1950 Nonparametric Statistics November 24, 2008.
Wilcoxon Tests What is the Purpose of Wilcoxon Tests? What are the Assumptions? How does the Wilcoxon Rank-Sum Test Work? How does the Wilcoxon Matched-
Intro to Statistics for the Behavioral Sciences PSYC 1900 Lecture 17: Chi-Square.
Parametric & Nonparametric Models for Within-Groups Comparisons overview X 2 tests parametric & nonparametric stats Mann-Whitney U-test Kruskal-Wallis.
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.
Summary of Quantitative Analysis Neuman and Robson Ch. 11
Marshall University School of Medicine Department of Biochemistry and Microbiology BMS 617 Lecture 14: Non-parametric tests Marshall University Genomics.
Non-parametric statistics
Nonparametrics and goodness of fit Petter Mostad
Chapter 15 Nonparametric Statistics
Nonparametric or Distribution-free Tests
Choosing Statistical Procedures
Review I volunteer in my son’s 2nd grade class on library day. Each kid gets to check out one book. Here are the types of books they picked this week:
Chapter 14: Nonparametric Statistics
Copyright © 2010, 2007, 2004 Pearson Education, Inc Lecture Slides Elementary Statistics Eleventh Edition and the Triola Statistics Series by.
The paired sample experiment The paired t test. Frequently one is interested in comparing the effects of two treatments (drugs, etc…) on a response variable.
NONPARAMETRIC STATISTICS
Independent samples- Wilcoxon rank sum test. Example The main outcome measure in MS is the expanded disability status scale (EDSS) The main outcome measure.
Lesson Inferences about the Differences between Two Medians: Dependent Samples.
Copyright © 2012 Pearson Education. Chapter 23 Nonparametric Methods.
Previous Lecture: Categorical Data Methods. Nonparametric Methods This Lecture Judy Zhong Ph.D.
© 2000 Prentice-Hall, Inc. Statistics Nonparametric Statistics Chapter 14.
Chapter 16 The Chi-Square Statistic
© Copyright McGraw-Hill CHAPTER 13 Nonparametric Statistics.
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.
Nonparametric Statistics. In previous testing, we assumed that our samples were drawn from normally distributed populations. This chapter introduces some.
MGT-491 QUANTITATIVE ANALYSIS AND RESEARCH FOR MANAGEMENT OSMAN BIN SAIF Session 26.
Nonparametric Statistics
Lesson 15 - R Chapter 15 Review. Objectives Summarize the chapter Define the vocabulary used Complete all objectives Successfully answer any of the review.
ITEC6310 Research Methods in Information Technology Instructor: Prof. Z. Yang Course Website: c6310.htm Office:
Analysis of Variance (ANOVA) Brian Healy, PhD BIO203.
Experimental Design and Statistics. Scientific Method
CHI SQUARE TESTS.
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 11-1 Chapter 11 Chi-Square Tests and Nonparametric Tests Statistics for.
Nonparametric Statistical Methods. Definition When the data is generated from process (model) that is known except for finite number of unknown parameters.
Medical Statistics (full English class) Ji-Qian Fang School of Public Health Sun Yat-Sen University.
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.
NON-PARAMETRIC STATISTICS
IMPORTANCE OF STATISTICS MR.CHITHRAVEL.V ASST.PROFESSOR ACN.
Nonparametric Statistics
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.
Nonparametric Statistical Methods. Definition When the data is generated from process (model) that is known except for finite number of unknown parameters.
Copyright © 2010, 2007, 2004 Pearson Education, Inc Lecture Slides Elementary Statistics Eleventh Edition and the Triola Statistics Series by.
Lesson Test to See if Samples Come From Same Population.
Nonparametric statistics. Four levels of measurement Nominal Ordinal Interval Ratio  Nominal: the lowest level  Ordinal  Interval  Ratio: the highest.
Chapter 22 Inferential Data Analysis: Part 2 PowerPoint presentation developed by: Jennifer L. Bellamy & Sarah E. Bledsoe.
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.
Nonparametric Statistics
Chapter 12 Chi-Square Tests and Nonparametric Tests
Non-Parametric Tests 12/1.
Non-Parametric Tests 12/6.
Non-Parametric Tests.
Parametric and non parametric tests
Presentation transcript:

Intro to Statistics for the Behavioral Sciences PSYC 1900 Lecture 17: Nonparametric Tests & Course Summary

Chi-Square Effect Size Most common is Cramer’s Phi. Most common is Cramer’s Phi. Cramer’s squared gives an index of the amount of variance explained (similar to eta sqaured): Cramer’s squared gives an index of the amount of variance explained (similar to eta sqaured): Note that # groups in analyses with more than one classification variable refers to the smallest number of groups for one of the variables. Note that # groups in analyses with more than one classification variable refers to the smallest number of groups for one of the variables.

Definitions Nonparametric and distribution-free tests make fewer assumptions than others. Nonparametric and distribution-free tests make fewer assumptions than others. Do not assume population parameters Do not assume population parameters Do not assume normality Do not assume normality Still usually assume comparable distributions across groups Still usually assume comparable distributions across groups Less sensitive to outliers. More sensitive to medians. Less sensitive to outliers. More sensitive to medians. Rank-randomization tests Rank-randomization tests Class of nonparametrics tests based on the theoretical distribution of randomly assigned ranks Class of nonparametrics tests based on the theoretical distribution of randomly assigned ranks Usually less power than parametric versions. Usually less power than parametric versions.

Mann-Whitney Analogous to t test for two independent groups Analogous to t test for two independent groups Works with ranks rather than raw scores Works with ranks rather than raw scores Rank without regard to group, and compare sums of ranks in each group Rank without regard to group, and compare sums of ranks in each group If H 0 : true, sums of ranks should be approximately equal If H 0 : true, sums of ranks should be approximately equal

Example: Behavior Patterns and Cholesterol Selvin (1991) reports cholesterol of 20 men who are Type A and 20 Type B. Selvin (1991) reports cholesterol of 20 men who are Type A and 20 Type B. High cholesterol risk factor for heart disease High cholesterol risk factor for heart disease Question: Is there a relation between cholesterol and personality type? Question: Is there a relation between cholesterol and personality type?

Raw Data

Problems and Solution Data have several outliers Data have several outliers Not normally distributed Not normally distributed Convert to ranks (assigning tied ranks to tied scores) Convert to ranks (assigning tied ranks to tied scores) Rank without regard to group membership Rank without regard to group membership Sum ranks in each group. Sum ranks in each group.

Ranked Data W S = smaller sum (groups or abs. value) = 317 W S = smaller sum (groups or abs. value) = 317 Critical value with n 1 = n 2 = 20 is 328 Critical value with n 1 = n 2 = 20 is 328 Reject is Ws is LESS than critical value Reject is Ws is LESS than critical value

Conclusions Since 317 < 328, reject H 0 and conclude that the two groups do not have the same average cholesterol level. Since 317 < 328, reject H 0 and conclude that the two groups do not have the same average cholesterol level. Type A personality people have significantly higher cholesterol levels. Type A personality people have significantly higher cholesterol levels. Note that if is highest ranks are congregated in smaller group, use: Note that if is highest ranks are congregated in smaller group, use:

z Approximation We could use z approximation for large n j We could use z approximation for large n j p (z > 2.52) =.0059 p (z > 2.52) =.0059 p (z > +2.52) =.012: Reject H 0 p (z > +2.52) =.012: Reject H 0

Wilcoxon’s Matched-Pairs Signed-Ranks Test Analogous to matched-sample t Analogous to matched-sample t Each subject observed twice Each subject observed twice Compute difference scores Compute difference scores Rank difference scores Rank difference scores

Wilcoxon--cont. Compute sum of ranks of + and - difference scores separately Compute sum of ranks of + and - difference scores separately If difference is 0, ignore and reduce n If difference is 0, ignore and reduce n If H 0 true, sum of + and - ranks approx. equal If H 0 true, sum of + and - ranks approx. equal If tied differences, use tied ranks If tied differences, use tied ranks

Example: Stress and Beta-endorphins Hoaglin et al. (1985) report data on 19 patients collected at 12 hours and again at 10 min. before surgery. Hoaglin et al. (1985) report data on 19 patients collected at 12 hours and again at 10 min. before surgery. Dependent variable = beta-endorphin level. Dependent variable = beta-endorphin level. Beta-endorphins are body’s pain killers. Beta-endorphins are body’s pain killers. Data have several outliers. Data have several outliers.

Wilcoxon--cont. Sum positive ranks = 22 Sum positive ranks = 22 Sum negative ranks = 131 Sum negative ranks = 131 T = smaller sum = 22 T = smaller sum = 22 Critical value for n = 19 is between 46 and 47 for  =.05 Critical value for n = 19 is between 46 and 47 for  =.05 Since 22 < 46, reject null hypothesis Since 22 < 46, reject null hypothesis Beta--endorphins rise before surgery Beta--endorphins rise before surgery

Choice of Analysis Step 1 Step 1 What is the form of the dependent variable? What is the form of the dependent variable? Categorical Categorical Chi-Square Chi-Square Continuous Continuous Go to Step 2 Go to Step 2

Choice of Analysis Step 2 Step 2 What is the form of the independent variable? What is the form of the independent variable? Categorical with 1 iv Categorical with 1 iv 2 Levels: t-test 2 Levels: t-test 3 or more levels: ANOVA 3 or more levels: ANOVA Categorical with 2 or more iv’s Categorical with 2 or more iv’s Factorial ANOVA Factorial ANOVA Continuous with 1 iv Continuous with 1 iv Correlation or bivariate regression Correlation or bivariate regression Continuous with 2 or more iv’s Continuous with 2 or more iv’s Multiple Regression Multiple Regression