Chapter 15: Testing for a difference between two dependent (Correlated) Groups. Example: Suppose you wanted to test the drug that may affect IQ, but this.

Slides:



Advertisements
Similar presentations
Chapter 12: Testing hypotheses about single means (z and t) Example: Suppose you have the hypothesis that UW undergrads have higher than the average IQ.
Advertisements

Chapter 15 Comparing Two Populations: Dependent samples.
Hypothesis test flow chart frequency data Measurement scale number of variables 1 basic χ 2 test (19.5) Table I χ 2 test for independence (19.9) Table.
Ethan Cooper (Lead Tutor)
Single Sample t-test Purpose: Compare a sample mean to a hypothesized population mean. Design: One group.
DEPENDENT SAMPLES t o Also called Paired t, Related Samples t o Purpose: Test whether two means are significantly different o Design: paired scores o.
1 Matched Samples The paired t test. 2 Sometimes in a statistical setting we will have information about the same person at different points in time.
Using Statistics in Research Psych 231: Research Methods in Psychology.
PSY 307 – Statistics for the Behavioral Sciences
Dependent t-Test CJ 526 Statistical Analysis in Criminal Justice.
The t-test:. Answers the question: is the difference between the two conditions in my experiment "real" or due to chance? Two versions: (a) “Dependent-means.
Chapter 14 Conducting & Reading Research Baumgartner et al Chapter 14 Inferential Data Analysis.
Independent Samples and Paired Samples t-tests PSY440 June 24, 2008.
Hypothesis test with t – Exercise 1 Step 1: State the hypotheses H 0 :  = 50H 1 = 50 Step 2: Locate critical region 2 tail test,  =.05, df = =24.
Don’t spam class lists!!!. Farshad has prepared a suggested format for you final project. It will be on the web
Inferences about Means of Dependent Samples Chapter 12 Homework: 1-4, 7 Problems 3, 4, & 7: skip parts i and l, do not calculate U in part n.
Hypothesis Testing Using The One-Sample t-Test
Hypothesis Testing: Two Sample Test for Means and Proportions
Psy B07 Chapter 1Slide 1 ANALYSIS OF VARIANCE. Psy B07 Chapter 1Slide 2 t-test refresher  In chapter 7 we talked about analyses that could be conducted.
Hypothesis Testing:.
Chapter Eleven Inferential Tests of Significance I: t tests – Analyzing Experiments with Two Groups PowerPoint Presentation created by Dr. Susan R. Burns.
Chapter 13 – 1 Chapter 12: Testing Hypotheses Overview Research and null hypotheses One and two-tailed tests Errors Testing the difference between two.
T-distribution & comparison of means Z as test statistic Use a Z-statistic only if you know the population standard deviation (σ). Z-statistic converts.
The Hypothesis of Difference Chapter 10. Sampling Distribution of Differences Use a Sampling Distribution of Differences when we want to examine a hypothesis.
Hypothesis test flow chart frequency data Measurement scale number of variables 1 basic χ 2 test (19.5) Table I χ 2 test for independence (19.9) Table.
Chapter 11 Hypothesis Tests: Two Related Samples.
One-Way Analysis of Variance Comparing means of more than 2 independent samples 1.
Chapter 9 Hypothesis Testing and Estimation for Two Population Parameters.
TWO-SAMPLE t-TESTS.  Independent versus Related Samples  Your two samples are independent if you randomly assign individuals into the two treatment.
Copyright © 2012 by Nelson Education Limited. Chapter 7 Hypothesis Testing I: The One-Sample Case 7-1.
Hypothesis Testing CSCE 587.
Testing the Difference Between Two Means: Dependent Samples
Hypothesis Testing Using the Two-Sample t-Test
© 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.
Statistics (cont.) Psych 231: Research Methods in Psychology.
Chapter 10: Analyzing Experimental Data Inferential statistics are used to determine whether the independent variable had an effect on the dependent variance.
Jeopardy Hypothesis Testing t-test Basics t for Indep. Samples Related Samples t— Didn’t cover— Skip for now Ancient History $100 $200$200 $300 $500 $400.
1 Inferences About The Pearson Correlation Coefficient.
Unit 8 Section 8-3 – Day : P-Value Method for Hypothesis Testing  Instead of giving an α value, some statistical situations might alternatively.
Chapter 8 Parameter Estimates and Hypothesis Testing.
The T-Test for Two Related Samples (Dependent Samples) Introduction to Statistics Chapter 11 April 6-8, 2010 Class #21-22.
Chapter 9: Testing Hypotheses Overview Research and null hypotheses One and two-tailed tests Type I and II Errors Testing the difference between two means.
Final Test Information The final test is Monday, April 13 at 8:30 am The final test is Monday, April 13 at 8:30 am GRH102: Last name begins with A - I.
Chapter 11: Additional Topics Using Inferences 11.1 – Chi-Square: Tests of Independence 11.2 – Chi-Square: Goodness of Fit 11.3 – Testing a Single Variance.
Sullivan – Fundamentals of Statistics – 2 nd Edition – Chapter 11 Section 1 – Slide 1 of 26 Chapter 11 Section 1 Inference about Two Means: Dependent Samples.
What if.... The two samples have different sample sizes (n)
Practice Does drinking milkshakes affect (alpha =.05) your weight? To see if milkshakes affect a persons weight you collected data from 5 sets of twins.
Hypothesis test flow chart frequency data Measurement scale number of variables 1 basic χ 2 test (19.5) Table I χ 2 test for independence (19.9) Table.
Chapter 11 The t-Test for Two Related Samples
Practice A research study was conducted to examine the differences between older and younger adults on perceived life satisfaction. A pilot study was.
Matched Pairs t-test Module 22a. Matched Pairs t-test To this point we have only looked at tests for single samples. Soon we will look at confidence intervals.
Chapter Eleven Performing the One-Sample t-Test and Testing Correlation.
Hypothesis test flow chart
The T-Test for Two Related Samples (Dependent Samples) Introduction to Statistics Chapter 11 March 31, 2009 Class #20.
Psychology 290 Lab z-tests & t-tests March 5 - 7, 2007 –z-test –One sample t-test –SPSS – Chapter 7.
Statistics (cont.) Psych 231: Research Methods in Psychology.
CHAPTER 7: TESTING HYPOTHESES Leon-Guerrero and Frankfort-Nachmias, Essentials of Statistics for a Diverse Society.
When the means of two groups are to be compared (where each group consists of subjects that are not related) then the excel two-sample t-test procedure.
Definition Two samples are independent if the sample selected from one population is not related to the sample selected from the second population. The.
Dependent-Samples t-Test
Central Limit Theorem, z-tests, & t-tests
CJ 526 Statistical Analysis in Criminal Justice
Comparing Two Groups Statistics 2126.
Hypothesis Testing.
Psych 231: Research Methods in Psychology
A paired-samples t-test compares the means of two related sets of data to see if they differ statistically. IQ Example We may want to compare the IQ scores.
So far We have been doing independent samples designs The observations in one group were not linked to the observations in the other group.
Psych 231: Research Methods in Psychology
Inference for Distributions
Presentation transcript:

Chapter 15: Testing for a difference between two dependent (Correlated) Groups. Example: Suppose you wanted to test the drug that may affect IQ, but this time you look for changes within each subject. This is done by measuring the IQ for each subject before and after taking the drug. For 9 subjects, you might get a result like this: The most common application for this test is called a ‘repeated-measures design’ where two measures are obtained from the same group of subjects, and you are looking for a difference in the means of these measures. SubjectIQ before (X) IQ after (Y)

The book discusses two ways of conducting t-tests for a repeated-measures design. We will only cover the second (easy) way. So we’ll be skipping sections 15.1 and 15.2 The easy (‘alternative’) way is to treat each subject as a single measure by calculating the difference (D) for the scores within each subject, and conducting a t- test on these values of D. SubjectIQ before (X) IQ after (Y) D=Y-X

Just perform a simple single sample t-test (like in Chapter 13) on the values of D using n-1 degrees of freedom, where n is the number of pairs. SubjectIQ before (X) IQ after (Y) D=Y-X All we are doing here is conducting a single-sample t- test on the differences.

SubjectIQ before (X) IQ after (Y) D=Y-X Looking in Table D, df = 8, area in one tail: t crit = ±2.306 Decision: reject H 0 and conclude that the drug had a significant effect on IQ using a two-tailed test with  =.05. This is the same equation for a single sample t-test, but with D instead of X:

Using APA Format: “There was a statistically significant change in IQ after taking the drug (M = 6.44, SD = 7.86), t(8)= 2.46, p<.05

The effect size is computed just as a single sample t-test. Again, just use ‘D’ for ‘X’: Remember, the general convention is that g=.2 is small, g=.5 is medium and g=.8 is large, so this is a large effect size What is the power of this test using this effect size? We will use the power curve for one mean: (not two means, because we’re really just conducting a hypothesis test on the mean of the differences)

Here’s the power curve for a two-tailed test for one mean with  =.05 from Chapter 13: For an effect size of 0.819, sample size of 9, what is the power? Answer: about.525 or so.

Power with correlated groups is calculated the same way as for a single sample design. Here’s the power curve for a two-tailed test with  =.05 from Chapter 13: For an effect size of 0.8, how many pairs (n) do we need for a power of 0.8? Answer: about 15 pairs (yellow curve)

Other examples (besides repeated measures) of testing difference of means between dependent (correlated) groups. The methods are the same as for repeated measures – calculate a t-test on the difference between each pair. Matched pairs experiments: Where pairs of subjects are naturally grouped together. For example, in identical twin studies a measure is made from each twin in a pair. D is the difference in scores for each pair of twins. Matched-subjects design: Where the experimenter matches pairs of subjects together based on some other variable such as age or visual acuity.

Example from the tutorial: 25) We measure the visual acuity of 31 republicans under two conditions: 'itchy' and 'tiny'. You then subtract the visual acuity of the 'tiny' from the 'itchy' conditions for each republicans and obtain a mean pair-wise difference of with a standard deviation is Using an alpha value of 0.01, is the visual acuity from the 'itchy' condition significantly different than from the 'tiny' condition? What is the effect size? Answer: D̄ = s D̄ = 1.32 t obs = t crit = ± 2.75 (df = 30) We fail to reject H 0. The visual acuity of itchy republicans is not significantly different than the visual acuity of tiny republicans (M=-2.15, SD = 7.37), t(30) = , p = Effect size: g = 0.29 (small)