Week 111 Power of the t-test - Example In a metropolitan area, the concentration of cadmium (Cd) in leaf lettuce was measured in 7 representative gardens.

Slides:



Advertisements
Similar presentations
Chapter 18: Inference about One Population Mean STAT 1450.
Advertisements

Introduction Comparing Two Means
STATISTICAL INFERENCE PART V
Copyright ©2011 Brooks/Cole, Cengage Learning Testing Hypotheses about Means Chapter 13.
Copyright ©2011 Brooks/Cole, Cengage Learning Testing Hypotheses about Means Chapter 13.
Significance Testing Chapter 13 Victor Katch Kinesiology.
Copyright ©2006 Brooks/Cole, a division of Thomson Learning, Inc. More About Significance Tests Chapter 13.
Comparing Two Population Means The Two-Sample T-Test and T-Interval.
PSY 307 – Statistics for the Behavioral Sciences
Hyp Test II: 1 Hypothesis Testing: Additional Applications In this lesson we consider a series of examples that parallel the situations we discussed for.
MARE 250 Dr. Jason Turner Hypothesis Testing II. To ASSUME is to make an… Four assumptions for t-test hypothesis testing:
Topic 2: Statistical Concepts and Market Returns
Chapter 19: Two-Sample Problems
Chapter 11: Inference for Distributions
5-3 Inference on the Means of Two Populations, Variances Unknown
CHAPTER 19: Two-Sample Problems
C HAPTER 11 Section 11.2 – Comparing Two Means. C OMPARING T WO M EANS Comparing two populations or two treatments is one of the most common situations.
7.1 Lecture 10/29.
AP Statistics Section 13.1 A. Which of two popular drugs, Lipitor or Pravachol, helps lower bad cholesterol more? 4000 people with heart disease were.
Experimental Statistics - week 2
1/2555 สมศักดิ์ ศิวดำรงพงศ์
Chapter 19: Two-Sample Problems STAT Connecting Chapter 18 to our Current Knowledge of Statistics ▸ Remember that these formulas are only valid.
Lesson Comparing Two Means.
Ch 11 – Inference for Distributions YMS Inference for the Mean of a Population.
Comparing 2 population parameters Chapter 13. Introduction: Two Sample problems  Ex: How do small businesses that fail differ from those that succeed?
AP STATISTICS LESSON 11 – 2 (DAY 1) Comparing Two Means.
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.
More About Significance Tests
Dependent Samples: Hypothesis Test For Hypothesis tests for dependent samples, we 1.list the pairs of data in 2 columns (or rows), 2.take the difference.
Week 91 Large Sample Tests – Non-Normal population Suppose we have a large sample from a non-normal population and we are interested in conducting a hypotheses.
STATISTICAL INFERENCE PART VII
Comparing Two Population Means
Chapter 10 Comparing Two Means Target Goal: I can use two-sample t procedures to compare two means. 10.2a h.w: pg. 626: 29 – 32, pg. 652: 35, 37, 57.
1 Objective Compare of two matched-paired means using two samples from each population. Hypothesis Tests and Confidence Intervals of two dependent means.
Chapter 11 Inference for Distributions AP Statistics 11.1 – Inference for the Mean of a Population.
1 Happiness comes not from material wealth but less desire.
Business Statistics for Managerial Decision Comparing two Population Means.
Week 131 Paired t- test - Example OISE sponsored summer institute to improve the skills of high school teachers of foreign languages. One such institute.
For 95 out of 100 (large) samples, the interval will contain the true population mean. But we don’t know  ?!
Chapter 10 Inferences from Two Samples
Copyright © Cengage Learning. All rights reserved. 10 Inferences Involving Two Populations.
The Practice of Statistics Third Edition Chapter 13: Comparing Two Population Parameters Copyright © 2008 by W. H. Freeman & Company Daniel S. Yates.
Week101 Decision Errors and Power When we perform a statistical test we hope that our decision will be correct, but sometimes it will be wrong. There are.
AP Statistics Section 13.1 A. Which of two popular drugs, Lipitor or Pravachol, helps lower bad cholesterol more? 4000 people with heart disease were.
1 Section 9-4 Two Means: Matched Pairs In this section we deal with dependent samples. In other words, there is some relationship between the two samples.
Copyright © 2013, 2010 and 2007 Pearson Education, Inc. Section Inference about Two Means: Independent Samples 11.3.
BPS - 3rd Ed. Chapter 161 Inference about a Population Mean.
Lesson Comparing Two Means. Knowledge Objectives Describe the three conditions necessary for doing inference involving two population means. Clarify.
Week111 The t distribution Suppose that a SRS of size n is drawn from a N(μ, σ) population. Then the one sample t statistic has a t distribution with n.
Week121 Robustness of the two-sample procedures The two sample t-procedures are more robust against nonnormality than one-sample t-procedures. When the.
ISMT253a Tutorial 1 By Kris PAN Skewness:  a measure of the asymmetry of the probability distribution of a real-valued random variable 
MATB344 Applied Statistics I. Experimental Designs for Small Samples II. Statistical Tests of Significance III. Small Sample Test Statistics Chapter 10.
+ Unit 6: Comparing Two Populations or Groups Section 10.2 Comparing Two Means.
Learning Objectives After this section, you should be able to: The Practice of Statistics, 5 th Edition1 DESCRIBE the shape, center, and spread of the.
Essential Statistics Chapter 171 Two-Sample Problems.
Week 101 Test on Pairs of Means – Case I Suppose are iid independent of that are iid. Further, suppose that n 1 and n 2 are large or that are known. We.
Chapter 9 Lecture 3 Section: 9.3. We will now consider methods for using sample data from two independent samples to test hypotheses made about two population.
Chapter 7 Inference Concerning Populations (Numeric Responses)
CHAPTER 19: Two-Sample Problems ESSENTIAL STATISTICS Second Edition David S. Moore, William I. Notz, and Michael A. Fligner Lecture Presentation.
When  is unknown  The sample standard deviation s provides an estimate of the population standard deviation .  Larger samples give more reliable estimates.
AP Statistics Chapter 11 Section 2. TestConfidence IntervalFormulasAssumptions 1-sample z-test mean SRS Normal pop. Or large n (n>40) Know 1-sample t-test.
Chapter 11 Inference for Distributions AP Statistics 11.2 – Inference for comparing TWO Means.
Class Six Turn In: Chapter 15: 30, 32, 38, 44, 48, 50 Chapter 17: 28, 38, 44 For Class Seven: Chapter 18: 32, 34, 36 Chapter 19: 26, 34, 44 Quiz 3 Read.
Statistical Model A statistical model for some data is a set of distributions, one of which corresponds to the true unknown distribution that produced.
CHAPTER 19: Two-Sample Problems
Decision Errors and Power
Basic Practice of Statistics - 3rd Edition Two-Sample Problems
Essential Statistics Two-Sample Problems - Two-sample t procedures -
Hypothesis Testing – Introduction
CHAPTER 19: Two-Sample Problems
Presentation transcript:

week 111 Power of the t-test - Example In a metropolitan area, the concentration of cadmium (Cd) in leaf lettuce was measured in 7 representative gardens where sewage sludge was used as fertilizer. The following measurements (in mg/kg of dry weight) were obtained. Cd: Is there strong evidence that the mean concentration of Cd is higher than 12 ? Descriptive Statistics Variable N Mean Median TrMean StDev SE Mean Cd The hypothesis to be tested are: H 0 : μ = 12 vs H a : μ > 12. The test statistics is: degrees of freedom = 7 – 1 = 6

week 112 Since t = 1.26 < 1.943, we cannot reject H 0 at the 5% level and so there are no strong evidence. The P-value is 0.1 < P(T (6) ≥ 1.26) < 0.15 and so is greater then 0.05 indicating a non significant result. Find the power of the test when true mean is 13. We can use MINITAB to calculate the power for t-tests. MINITAB commands: Stat > Power and Sample size > 1 sample t 1-Sample t Test Testing mean = null (versus > null) Calculating power for mean = null + 1 Alpha = 0.05 Sigma = Sample Size Power

week 113 What is the probability of a type II error when  = 13? Find the power of the test when true mean is 20. Testing mean = null (versus > null) Calculating power for mean = null + 8 Alpha = 0.05 Sigma = Sample Size Power Use the tables to find the power when  = 20. Find the sample size if we specified a desired power of 0.90, when the true mean is Sample t Test Testing mean = null (versus > null) Calculating power for mean = null + 8 Alpha = 0.05 Sigma = Sample Size Target Power Actual Power

week 114 Match Pairs t-test In a matched pairs study, subjects are matched in pairs and the outcomes are compared within each matched pair. The experimenter can toss a coin to assign two treatment to the two subjects in each pair. Matched pairs are also common when randomization is not possible. One situation calling for match pairs is when observations are taken on the same subjects, under different conditions. A match pairs analysis is needed when there are two measurements or observations on each individual and we want to examine the difference. For each individual (pair), we find the difference d between the measurements from that pair. Then we treat the d i as one sample and use the one sample t – statistic to test for no difference between the treatments effect. Example: similar to exercise 7.41 on p482 in IPS.

week 115 Data Display Row Student Pretest Posttest improvement

week 116 One sample t-test for the improvement T-Test of the Mean Test of mu = vs mu > Variable N Mean StDev SE Mean T P improvem MINITAB commands for the paired t-test Stat > Basic Statistics > Paired t Paired T-Test and Confidence Interval Paired T for Posttest – Pretest N Mean StDev SE Mean Posttest Pretest Difference % CI for mean difference: (-0.049, 2.949) T-Test of mean difference=0 (vs > 0): T-Value = 2.02 P-Value = 0.029

week 117 Character Stem-and-Leaf Display Stem-and-leaf of improvement N = 20 Leaf Unit = (7)

week 118 Inference for non-normal populations Three general strategies are available for making inference about the mean of a clearly non-normal distribution based on small sample.  In some cases a distribution other than a normal distribution will describe the data well. There are many non-normal models for data, and inference procedures for these models are available.  Because skewness is the chief barrier to the use of t procedures on data without outliers, we can attempt to transform skewed data so that the distribution is symmetric and as close to normal as possible. CI and P-values from the t procedures applied to the transformed data will be quite accurate for even moderate sample size.  The third strategy is to use a distribution-free inference procedure. Such procedures do not assume that the population distribution has any specific form, such as normal. Distribution-free procedures are often called nonparametric procedures.

week 119 The sign test for matched pairs One way of analyzing nonnormal data is to use a distribution- free procedure, or nonparametric procedure. Distribution-free (nonparametric) tests have two drawbacks;  They are generally less powerful than the test designed for use with a specific distribution such as t-test.  We must often modify the statement of the hypothesis in order to use the distribution free test. The simplest distribution free test, and one of the most useful, is the sign test. Example Use a sign test to test whether attending the Institute improves listening skills (In Exercise 7.41 above).

week 1110 Solution Step-1: Calculate the differences (post-pre). Ignore pairs with difference 0. Step-2: Count the number of positive differences (X). In our example X=14. The test statistic of the sign test, is the count X of pairs with positive differences. Under the null hypothesis X ~ Bin (20, ½). P-values for X are based on this distribution. Step-3: Test the hypothesis: H 0 : p = 0.5 vs H a : p > 0.5 where p is the probability of a positive difference. Note that this is a test of H 0 : population median = 0 vs H a : population median > 0.

week 1111 The P-value for this test is given by P(X ≥14) = = MINITAB commands for the sign test Stat > Nonparametrics > 1 sample sign The MINITAB output for the above problem is given below. Sign Test for Median Sign test of median = versus > N Below Equal Above P Median Diff

week 1112 Two-sample problems The goal of inference is to compare the response in two groups. Each group is considered to be a sample form a distinct population. The responses in each group are independent of those in the other group. A two-sample problem can arise form a randomized comparative experiment or comparing random samples separately selected from two populations. Example: A medical researcher is interested in the effect of added calcium in our diet on blood pressure. She conducted a randomized comparative experiment in which one group of subjects receive a calcium supplement and a control group gets a placebo.

week 1113 Comparing two means (with two independent samples) Here we will look at the problem of comparing two population means when the population variances are known or the sample sizes are large. Suppose that a SRS of size n 1 is drawn from an N( μ 1, σ 1 ) population and that an independent SRS of size n 2 is drown from an N( μ 2, σ 2 ) population. Then the two-sample z statistics for testing the null hypothesis H 0 : μ 1 = μ 2 is given by and has the standard normal N(0,1) sampling distribution. Using the standard normal tables, the P-value for the test of H 0 against H a : μ 1 > μ 2 is P( Z ≥ z ) H a : μ 1 < μ 2 is P( Z ≤ z ) H a : μ 1 ≠ μ 2 is 2·P(Z ≥ |z|)

week 1114 Example A regional IRS auditor runs a test on a sample of returns filed by March 15 to determine whether the average return this year is larger than last year. The sample data are shown here for a random sample of returns from each year. Assume that the std. deviation of returns is known to be about 100 for both years. Test whether the average return is larger this year than last year. Last YearThis Year Mean Sample size100120

week 1115 Solution

week 1116 Comparing two population means (unknown std. deviations) Suppose that a SRS of size n 1 is drawn from a normal population with unknown mean  1 and that an independent SRS of size n 2 is drawn from another normal population with unknown mean  2. To test the null hypothesis H 0 :  1 =  2, we compute the two sample t-statistic This statistic has a t-distribution with df approximately equal to smaller of n 1 – 1 and n We can use this distribution to compute the P-value.

week 1117 Example The weight gains for n 1 = n 2 = 8 rats tested on diets 1 and 2 are summarized here. Test whether diet 2 has greater mean weight gain. Use the 5% significant level. The hypotheses to be tested are: H 0 : μ 1 = μ 2 vs H a : μ 1 < μ 2. The test statistic is Diet 1Diet 2 n88 Std dev mean3.13.2

week 1118 The P-value is P(T (7) ≤- 3.65) = P(T (7) ≥ 3.65), from table D we have < P-value < 0.01 and so we reject H 0 and conclude that the mean weight gain from diet 2 is significantly greater than that from diet 1 (at the 5% and 1% significant level). A C% CI for the difference between the two means is given by, For this example the 95% CI is

week 1119 The pooled two sample t-procedures If the two normal population distributions have the same std deviation, i.e. σ 1 = σ 2 = , then we can estimate the common stdev. by, This is called the pooled estimator of σ 2, it combines the information in both samples. The pooled two-sample t statistic is then, and has exactly a t-distribution with df = n 1 + n 2 – 2.

week 1120 Example In a study of heart surgery, one issue was the effects of drugs called beta blockers on the pulse rate of patients during surgery. The available subjects were divided into two groups of 30 patients each. The pulse rate of each patient at a critical point during the operation was recorded. The treatment group had mean 65.2 and std dev For the control group the mean was 70.3 and the std dev. was 8.3. a) Do beta-blocker reduce the pulse rate? b) Give a 99% CI for the difference in mean pulse rates. Denoting the control group as 1 and the treatment group as 2 the solution is …

week 1121 a) The hypotheses to be tested are: H 0 : μ 1 = μ 2 vs H a : μ 1 > μ 2. The pooled standard deviation is and the test statistic is The P-value is P(T (58) ≥ 2.45), using table D and df = 60 we get < P-value < 0.01 and so we have significant evidence that the mean pulse rate of the control group is higher than the mean of the treatment group at the 5% and 1% significant level. Does it mean that beta-blocker reduce the pulse rate?!

week 1122 b) A C level CI’s for μ 1 – μ 2 is given by For this example, a 99% CI is, = (-0.429, ) MINITAB command: Stat > Basic Statistics > 2 Sample t.

week 1123 Example A study compared various characteristics of 68 healthy and 33 failed firms. One of the variables was the ratio of current assets to current liabilities. Row Firms(Healthy/Failed) Ratio 1 h h h f f f 0.09

week 1124 Stem-and-leaf of Ratio failed N = 33 Leaf Unit = (10)

week 1125 Stem-and-leaf of Ratio healthy N = 68 Leaf Unit =

week 1126 Two Sample T-Test and Confidence Interval Two sample T for Ratio Firms N Mean StDev SE Mean failed healthy % CI for mu (f) - mu (h): ( , ) T-Test mu (f) = mu (h) (vs <): T = P = DF = 81 Two Sample T-Test and Confidence Interval (pooled test and CI) Two sample T for Ratio Firms(He N Mean StDev SE Mean f h % CI for mu (f) - mu (h): ( , ) T-Test mu (f) = mu (h) (vs <): T = P = DF = 99 Both use Pooled StDev = 0.593