Class 27. Daniel B. Rowe, Ph.D. Department of Mathematics, Statistics, and Computer Science. Marquette University MATH 1700

Similar documents
Class 27. Daniel B. Rowe, Ph.D. Department of Mathematics, Statistics, and Computer Science. Marquette University MATH 1700

Class 23. Daniel B. Rowe, Ph.D. Department of Mathematics, Statistics, and Computer Science. Marquette University MATH 1700

Agenda: Recap. Lecture. Chapter 12. Homework. Chapt 12 #1, 2, 3 SAS Problems 3 & 4 by hand. Marquette University MATH 4740/MSCS 5740

11/19/ Chapter 10 Overview. Chapter 10: Two-Sample Inference. + The Big Picture : Inference for Mean Difference Dependent Samples

Chapter 20. Comparing Two Proportions. BPS - 5th Ed. Chapter 20 1

Chapter 22. Comparing Two Proportions. Copyright 2010 Pearson Education, Inc.

MOST PEOPLE WOULD RATHER LIVE WITH A PROBLEM THEY CAN'T SOLVE, THAN ACCEPT A SOLUTION THEY CAN'T UNDERSTAND.

STA Learning Objectives. Population Proportions. Module 10 Comparing Two Proportions. Upon completing this module, you should be able to:

Chapter 22. Comparing Two Proportions. Copyright 2010, 2007, 2004 Pearson Education, Inc.

Stat 200 -Testing Summary Page 1

Comparing Two Populations. Topic 15 - Two Sample Inference I. Comparing Two Means. Comparing Two Pop Means. Background Reading

A quick activity - Central Limit Theorem and Proportions. Lecture 21: Testing Proportions. Results from the GSS. Statistics and the General Population

Chapter 11: Asking and Answering Questions About the Difference of Two Proportions

2 1. The r.s., of size n2, from population 2 will be. 2 and 2. 2) The two populations are independent. This implies that all of the n1 n2

Final Examination Solutions 17/6/2010

Successful HE applicants. Information sheet A Number of applicants. Gender Applicants Accepts Applicants Accepts. Age. Domicile

Expectation and Variance of a random variable

Chapter 13, Part A Analysis of Variance and Experimental Design

Direction: This test is worth 150 points. You are required to complete this test within 55 minutes.

Sample Size Determination (Two or More Samples)

π: ESTIMATES, CONFIDENCE INTERVALS, AND TESTS Business Statistics

October 25, 2018 BIM 105 Probability and Statistics for Biomedical Engineers 1

Sampling Distributions, Z-Tests, Power

Common Large/Small Sample Tests 1/55

(7 One- and Two-Sample Estimation Problem )

Recall the study where we estimated the difference between mean systolic blood pressure levels of users of oral contraceptives and non-users, x - y.

7-1. Chapter 4. Part I. Sampling Distributions and Confidence Intervals

Economics Spring 2015

Class 24. Daniel B. Rowe, Ph.D. Department of Mathematics, Statistics, and Computer Science. Marquette University MATH 1700

BIOS 4110: Introduction to Biostatistics. Breheny. Lab #9

Interval Estimation (Confidence Interval = C.I.): An interval estimate of some population parameter is an interval of the form (, ),

University of California, Los Angeles Department of Statistics. Hypothesis testing

Agreement of CI and HT. Lecture 13 - Tests of Proportions. Example - Waiting Times

Topic 9: Sampling Distributions of Estimators

April 18, 2017 CONFIDENCE INTERVALS AND HYPOTHESIS TESTING, UNDERGRADUATE MATH 526 STYLE

Topic 9: Sampling Distributions of Estimators

TABLES AND FORMULAS FOR MOORE Basic Practice of Statistics

Statistics. Chapter 10 Two-Sample Tests. Copyright 2013 Pearson Education, Inc. publishing as Prentice Hall. Chap 10-1

MidtermII Review. Sta Fall Office Hours Wednesday 12:30-2:30pm Watch linear regression videos before lab on Thursday

STAT431 Review. X = n. n )

Statistical Inference About Means and Proportions With Two Populations

DS 100: Principles and Techniques of Data Science Date: April 13, Discussion #10

Read through these prior to coming to the test and follow them when you take your test.

Stat 319 Theory of Statistics (2) Exercises

Statistical Inference (Chapter 10) Statistical inference = learn about a population based on the information provided by a sample.

Lecture 7: Non-parametric Comparison of Location. GENOME 560, Spring 2016 Doug Fowler, GS

Overview. p 2. Chapter 9. Pooled Estimate of. q = 1 p. Notation for Two Proportions. Inferences about Two Proportions. Assumptions

Goodness-of-Fit Tests and Categorical Data Analysis (Devore Chapter Fourteen)

Math 140 Introductory Statistics

Data Analysis and Statistical Methods Statistics 651

ENGI 4421 Confidence Intervals (Two Samples) Page 12-01

Chapter 1 (Definitions)

Describing the Relation between Two Variables

TABLES AND FORMULAS FOR MOORE Basic Practice of Statistics

MBACATÓLICA. Quantitative Methods. Faculdade de Ciências Económicas e Empresariais UNIVERSIDADE CATÓLICA PORTUGUESA 9. SAMPLING DISTRIBUTIONS

Lecture 7: Non-parametric Comparison of Location. GENOME 560 Doug Fowler, GS

Statistics 20: Final Exam Solutions Summer Session 2007

Comparing your lab results with the others by one-way ANOVA

MATH 320: Probability and Statistics 9. Estimation and Testing of Parameters. Readings: Pruim, Chapter 4

STAT 515 fa 2016 Lec Sampling distribution of the mean, part 2 (central limit theorem)

Parameter, Statistic and Random Samples

- E < p. ˆ p q ˆ E = q ˆ = 1 - p ˆ = sample proportion of x failures in a sample size of n. where. x n sample proportion. population proportion

Chapter two: Hypothesis testing

Chapter 13: Tests of Hypothesis Section 13.1 Introduction

MA238 Assignment 4 Solutions (part a)

Final Review. Fall 2013 Prof. Yao Xie, H. Milton Stewart School of Industrial Systems & Engineering Georgia Tech

Hypothesis Testing (2) Barrow, Statistics for Economics, Accounting and Business Studies, 4 th edition Pearson Education Limited 2006

Lecture 8: Non-parametric Comparison of Location. GENOME 560, Spring 2016 Doug Fowler, GS

Topic 9: Sampling Distributions of Estimators

Commonly Used Distributions and Parameter Estimation

Fermat s Little Theorem. mod 13 = 0, = }{{} mod 13 = 0. = a a a }{{} mod 13 = a 12 mod 13 = 1, mod 13 = a 13 mod 13 = a.

To make comparisons for two populations, consider whether the samples are independent or dependent.

STAC51: Categorical data Analysis

Exam II Review. CEE 3710 November 15, /16/2017. EXAM II Friday, November 17, in class. Open book and open notes.

M1 for method for S xy. M1 for method for at least one of S xx or S yy. A1 for at least one of S xy, S xx, S yy correct. M1 for structure of r

This chapter focuses on two experimental designs that are crucial to comparative studies: (1) independent samples and (2) matched pair samples.

Correlation. Two variables: Which test? Relationship Between Two Numerical Variables. Two variables: Which test? Contingency table Grouped bar graph

Continuous Data that can take on any real number (time/length) based on sample data. Categorical data can only be named or categorised

This is an introductory course in Analysis of Variance and Design of Experiments.

Big Picture. 5. Data, Estimates, and Models: quantifying the accuracy of estimates.

Discrete Probability Functions

Chapter 6 Sampling Distributions

Formulas and Tables for Gerstman

Statistical inference: example 1. Inferential Statistics

Confidence intervals summary Conservative and approximate confidence intervals for a binomial p Examples. MATH1005 Statistics. Lecture 24. M.

1 Inferential Methods for Correlation and Regression Analysis

Central Limit Theorem the Meaning and the Usage

Day 8-3. Prakash Balachandran Department of Mathematics & Statistics Boston University. Friday, October 28, 2011

Announcements. Unit 5: Inference for Categorical Data Lecture 1: Inference for a single proportion

STAT 155 Introductory Statistics Chapter 6: Introduction to Inference. Lecture 18: Estimation with Confidence

1036: Probability & Statistics

Since X n /n P p, we know that X n (n. Xn (n X n ) Using the asymptotic result above to obtain an approximation for fixed n, we obtain

UCLA STAT 110B Applied Statistics for Engineering and the Sciences

Estimation for Complete Data

KLMED8004 Medical statistics. Part I, autumn Estimation. We have previously learned: Population and sample. New questions

Logit regression Logit regression

Hypothesis Testing. Evaluation of Performance of Learned h. Issues. Trade-off Between Bias and Variance

Mathematical Notation Math Introduction to Applied Statistics

Tests of Hypotheses Based on a Single Sample (Devore Chapter Eight)

BIOSTATISTICS. Lecture 5 Interval Estimations for Mean and Proportion. dr. Petr Nazarov

Transcription:

Marquette Uiversity MATH 700 Class 7 Daiel B. Rowe, Ph.D. Departmet of Mathematics, Statistics, a Computer Sciece Copyright 07 by D.B. Rowe

Marquette Uiversity MATH 700 Agea: Recap Chapter 0.-0.3 Lecture Chapter 0.4-0.5 Problem Solvig Sessio

Marquette Uiversity MATH 700 Recap Chapter 0.-0.3 3

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0. Iferece for Mea Differece Two Depeet Samples Cofiece Iterval Proceure With Paire Differece x x (0.) s ( i ) i i ukow, a -α cofiece iterval for μ =(μ -μ ) is: i Cofiece Iterval for Mea Differece (Depeet Samples) s s t( f, / ) to t( f, / ) where f=- (0.) 4

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0. Iferece for Mea Differece Two Depeet Samples Example: Costruct a 95% CI for mea ifferece i Bra B A tire wear. 8,, 9,,, 9 i s: i 6 f 5 i t( f, / ).57 6.3 0.05 s ( i ) i s 5. s t( f, / ) (0.090,.7) Figure from Johso & Kuby, 0. 5

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0. Iferece for Mea Differece Two Depeet Samples 6 8,, 9,,, 9 Example: Test mea ifferece of Bra B mius Bra A is zero. Step H 0 : μ =0 vs. H a : μ 0 Step 5 Step f 5 0 t*.05 s / Step 3 6.3 6.3 0 s 5. t* 3.03 5./ 6 Step 4 t( f, / ).57 Sice t*>t(f,α/), reject H 0 Coclusio: Sigificat ifferece i trea wear at.05 level. Figures from Johso & Kuby, 0. 6

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.3 Iferece for Mea Differece Two Iepeet Samples Cofiece Iterval Proceure With a ukow, a -α cofiece iterval for is: f Cofiece Iterval for Mea Differece (Iepeet Samples) s s s s ( x x) t( f, / ) to ( x x) t( f, / ) where f is either calculate or smaller of f, or f (0.8) Actually, this is for σ σ. Next larger umber tha s / s / s s If usig a computer program. If ot usig a computer program. 7

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.3 Iferece Mea Differece Cofiece Iterval f Example: Itereste i ifferece i mea heights betwee me a wome. The heights of 0 females a 30 males is measure. Costruct a 95% cofiece iterval for, & ukow s s m f ( xm x f) t( f, / ) m f (.9) (.8) (69.8 63.8).09 30 0 m f m f x x f m m s f s 0.05 t(9,.05).09 therefore 4.75 to 7.5 Figure from Johso & Kuby, 0. m 8

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios TuTh 0 0.3 Iferece for Mea Differece Two Iepeet Samples Hypothesis Testig Proceure 77 values males a females x x m x f Is the height of males = height of females at α=.05? 9

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.3 Iferece for Mea Differece Two Iepeet Samples Hypothesis Testig Proceure 77 values Step H 0 : μ f =μ m vs. H a : μ f μ m Step ( xm xf ) ( m f ) t* s s m f f 9.05 m f Step 3 Step 4 (70.9 65.3) (0) t* 9.05 8.0 5.4 30 47 t( f, / ).05 Step 5 Reject H 0 x x s s m f m f m f 30 47 70.9 65.3 8.0 5.4 TuTh 0 9.05.05, height males height females x m x f 0

Marquette Uiversity MATH 700 Chapter 0: Ifereces Ivolvig Two Populatios Questios? Homework: Chapter 0 # 3, 5, 3, 5, 9, 3, 35 4, 45, 53, 57, 58, 59, 63, 83, 85, 9, 98, 99, 0, 3, 5, 7, 9, 5 33

Marquette Uiversity MATH 700 Lecture Chapter 0.4-0.5

Recall Marquette Uiversity MATH 700 9: Ifereces Ivolvig Oe Populatio 9. Iferece about the Biomial Probability of Success We talke about a Biomial experimet with two outcomes. Each performace of the experimet is calle a trial. Each trial is iepeet.,,3,...! x x 0 p P( x) p ( p) x!( x)! x 0,..., Chapter 5 = umber of trials or times we repeat the experimet. x = the umber of successes out of trials. p = the probability of success o a iiviual trial. 3

9: Ifereces Ivolvig Oe Populatio 9. Iferece about the Biomial Probability of Success Whe we perform a biomial experimet we ca estimate the probability of heas as Sample Biomial Probability x p'. where x is the umber of successes i trials. This is a poit estimate. Recall the rule for a CI is poit estimate Recall Marquette Uiversity MATH 700 some amout i.e. umber of H out of flips (9.3) 4

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.4 Iferece for Differece betwee Two Proportios For Biomial, where x is umber of successes out of trials. We sai that mea( cx) cp a variace( cx) c pq. mea( x / ) p a variace( x / ) pq /. We are ofte itereste i comparisos betwee proportios p p. There is aother rule that says that if x a x are raom variables, the mea( x x) mea( x) mea( x) x x x x further, mea mea mea x x pq pq a variace. if x & x iepeet q=-p 5

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.4 Iferece for Differece betwee Two Proportios That is where. a. i the gree box below come from If iepeet samples of size a are raw with p =P (success) a p =P (success), the the samplig istributio of p p has these properties:. mea p p p p pq pq. staar error p (0.0) p 3. approximately ormal ist if a are sufficietly large. ie I, >0 II p, q, p, q >5 III sample<0% of pop 6

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.4 Iferece for Differece betwee Two Proportios Cofiece Iterval Proceure Assumptios for ifferece betwee two proportios p -p : The a raom observatios are selecte iepeetly from two populatios that are ot chagig Cofiece Iterval for the Differece betwee Two Proportios p - p p q p q p q p q ( p p ) z( / ) to ( p p ) z( / ) x x where p a p. (0.) 7

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.4 Iferece for Differece betwee Two Proportios Cofiece Iterval Proceure Example: Costruct a 99% CI for proportio of female A s mius male A s ifferece pf pm. Fill i. pq 0 values f f pq m m z( / ) ( pf p m) z( / ) m 5 f m x f f 68 pf f xm xm p m x f 43 m TuTh 0 Top 5 of 6 exams. 8

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.4 Iferece for Differece betwee Two Proportios Hypothesis Testig Proceure We ca perform hypothesis tests o the proportio H 0 : p p vs. H a : p < p pq pq pq H 0 : p p vs. H a : p > p H 0 : p = p vs. H a : p p whe p p p. Test Statistic for the Differece betwee two Proportios- 0 ( p Populatio Proportios Kow p ) ( p0 p0) z* pq x x (0.) p p p kow

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.4 Iferece for Differece betwee Two Proportios Hypothesis Testig Proceure Test Statistic for the Differece betwee two Proportios- Populatio Proportios UKow z* (0.5) where we assume p =p a use poole estimate of proportio x x p pq pq x x p pq pp ( p p) ( p p ) 0 0 pq p p p p estimate 0

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.4 Iferece for Differece betwee Two Proportios Is proportio of Salesma s efectives less tha Competitor s?.05 Step Step Fill i. xs x c s c Step 3 Step 4 Step 5 Figure from Johso & Kuby, 0. 3

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.5 Iferece for Ratio of Two Variaces Two I. Samples Hypothesis Testig Proceure We ca perform hypothesis tests o two variaces H 0 : vs. H a : Assumptios: Iepeet H 0 : vs. H a : samples from ormal istributio H 0 : vs. H a : Test Statistic for Equality of Variaces F s with f a f. s * Use ew table to fi areas for ew statistic. Actually F* igore ( ) s / ( ) ( ) s / ( ) (0.6) 9

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.5 Iferece for Ratio of Two Variaces Two I. Samples Properties of F istributio. F is o-egative f(f).6. F is osymmetrical.4 3. F is a family of ists. f =ν = -,f =ν = -. igore, ( ) ( ) ( 4), 4. 0.8 0.6 0.4 0. / f( F, ) / F ( )/ F μ - -.6667..004 =, = =5, = =5, =5 =0, =0 =50, =00 0 0 3 4 5 6 7 igore F 30

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.5 Iferece for Ratio of Two Variaces Two I. Samples Hypothesis Testig Proceure Test Statistic for Equality of Variaces F s with f a f. (0.6) s * Will also ee critical values. P F F( f, f, ) Table 9 Appeix B Page 7 Figure from Johso & Kuby, 0. 3

f Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two 0.5 Iferece Ratio of Two Variaces Example: Fi F(5,8,0.05). f f Table 9, Appeix B, Page 7. 0.05 Pops. f Figures from Johso & Kuby, 0. 3

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.5 Iferece for Ratio of Two Variaces Two I. Samples Hypothesis Testig Proceure Oe taile tests: Arrage H 0 & H a so H a is always greater tha H 0 : vs. H a : H 0 : vs. H a : / / F* s H 0 : vs. H a : H 0 : / vs. H a : / F* s s s Reject H 0 if F* s / s > F(f,f,α). Two taile tests: put larger sample variace s i umerator H 0 : vs. H a : H 0 : / vs. H a : / if s s, ifs s Reject H 0 if F* s / s > F(f,f,α/). 33

Marquette Uiversity MATH 700 0: Ifereces Ivolvig Two Populatios 0.5 Iferece for Ratio of Two Variaces Two I. Samples 77 values Is variace of male heights greater tha that of females?.0 Step Fill i. 30 Step Step 3 Step 4 x x s s m f m f m f 47 70.9 65.3 8.0 5.4 TuTh 0 x m x f Step 5 34

Marquette Uiversity MATH 700 Chapter 0: Ifereces Ivolvig Two Populatios Questios? Homework: Chapter 0 # 3, 5, 3, 5, 9, 3, 35 4, 45, 53, 57, 58, 59, 63, 83, 85, 9, 98, 99, 0, 3, 5, 7, 9, 5 33 40

Marquette Uiversity MATH 700 Problem Solvig Sessio 4