Two-Sample Proportions Inference

Slides:



Advertisements
Similar presentations
Chapter 12: Inference for Proportions BY: Lindsey Van Cleave.
Advertisements

BCOR 1020 Business Statistics Lecture 22 – April 10, 2008.
Warm-up An experiment on the side effects of pain relievers assigned arthritis patients to one of several over-the-counter pain medications. Of the 440.
AP Statistics: Chapter 23
5-3 Inference on the Means of Two Populations, Variances Unknown
Significance Tests for Proportions Presentation 9.2.
Two-Sample Proportions Inference Notes: Page 211.
Inference for Two Proportions Chapter 22
Two-Sample Proportions Inference. Sampling Distributions for the difference in proportions When tossing pennies, the probability of the coin landing on.
Ch 10 Comparing Two Proportions Target Goal: I can determine the significance of a two sample proportion. 10.1b h.w: pg 623: 15, 17, 21, 23.
Confidence Intervals and Hypothesis tests with Proportions.
Chapter 10 Inferences from Two Samples
Inference for Proportions One Sample. Confidence Intervals One Sample Proportions.
Biostatistics Class 6 Hypothesis Testing: One-Sample Inference 2/29/2000.
Chapter 22 Two-Sample Proportions Inference. Steps for doing a confidence interval: 1)State the parameter 2)Assumptions – 1) The samples are chosen randomly.
12.1 Inference for A Population Proportion.  Calculate and analyze a one proportion z-test in order to generalize about an unknown population proportion.
What is a Test of Significance?. Statistical hypotheses – statements about population parameters Examples Mean weight of adult males is greater than 160.
Two-Sample Proportions Inference. Sampling Distributions for the difference in proportions When tossing pennies, the probability of the coin landing.
Lecture 8 Estimation and Hypothesis Testing for Two Population Parameters.
Name Mean of Sampling Distribution Standard Deviation/Error of Sampling Distribution 1 sample z-Interval for Proportions 1 sample z-interval for Means.
Chapter 12 Inference for Proportions AP Statistics 12.2 – Comparing Two Population Proportions.
Two-Sample Proportions Inference. Conditions TwoindependentTwo independent SRS’s (or randomly assigned treatments) Populations > 10n Both sampling dist.’s.
Two-Sample Inference Procedures with Means. Two-Sample Procedures with Means two differentGoal: Compare two different populations/treatments INDEPENDENT.
Chapter 11 Inference for Distributions AP Statistics 11.2 – Inference for comparing TWO Means.
Section Copyright © 2014, 2012, 2010 Pearson Education, Inc. Lecture Slides Elementary Statistics Twelfth Edition and the Triola Statistics Series.
Two-Sample Proportions Inference
Two-Sample Inference Procedures with Means
More on Inference.
Warm-up An experiment on the side effects of pain relievers assigned arthritis patients to one of several over-the-counter pain medications. Of the 440.
Two-Sample Proportions Inference
One-Sample Inference for Proportions
Two-Sample Proportions Inference
STAT 312 Chapter 7 - Statistical Intervals Based on a Single Sample
Estimation & Hypothesis Testing for Two Population Parameters
Lecture Slides Elementary Statistics Twelfth Edition
Comparing Two Populations or Treatments
The Relationship between Confidence Intervals & Hypothesis Tests
Chapter 8: Inference for Proportions
Hypothesis Tests for 1-Sample Proportion
Independent samples t-test for the difference between two means.
Inferences About Means from Two Groups
Statistics in Applied Science and Technology
Two-Sample Inference Procedures with Means
Comparing Two Proportions
Confidence Intervals.
Section 10-4 – Analysis of Variance
Confidence Intervals for Proportions
More on Inference.
Two-Sample Inference Procedures with Means
Two-Sample Inference Procedures with Means
Independent samples t-test for the difference between two means.
Comparing Two Proportions
Independent Samples: Comparing Means
CHAPTER 6 Statistical Inference & Hypothesis Testing
Two-Sample Hypothesis Test with Means
Two-Sample Hypothesis Test of Proportions
Chapter 13: Inferences about Comparing Two Populations Lecture 7a
Two-Sample Proportions Inference
Determining Which Method to use
Lecture Slides Elementary Statistics Twelfth Edition
Chapter 12 Inference for Proportions
Two-Sample Inference Procedures with Means
Comparing Two Proportions
Comparing Two Proportions
Inference on Proportions Confidence Intervals and Hypothesis Test
Two-Sample Inference Procedures with Means
Chapter 9 Lecture 3 Section: 9.3.
Testing a Claim About a Mean:  Known
Presentation transcript:

Two-Sample Proportions Inference

Sampling Distributions for a Difference in Proportions Flipping and spinning pennies – is there a difference?

Conditions Two independent SRS’s (or randomly assigned treatments) Populations > 10n Both sampling dist.’s approx. normal:

Confidence Interval for a Difference in Proportions (Remember: Use p-hat when p is not known)

 Sampling dist. is approx. normal At Community Hospital, the burn center is experimenting with a new plasma compress treatment. A random sample of 316 patients with minor burns received this treatment. Of these patients, 259 had no visible scars after treatment. Another random sample of 419 patients with minor burns received no plasma compress treatment. In this group, 94 had no visible scars after treatment. a) Determine the shape and standard error of the sampling distribution of the difference in the proportions of people with visible scars between the two treatments. n1p1 = 259 > 5, n1(1 – p1) = 57 > 5 n2p2 = 94 > 5, n2(1 – p2) = 325 > 5  Sampling dist. is approx. normal

2 independent randomly assigned treatments b) Construct a 95% confidence interval for the true difference in proportion of people who had no visible scars (plasma – control group). Conditions: 2 independent randomly assigned treatments n1p1 = 259 > 5, n1(1 – p1) = 57 > 5 n2p2 = 94 > 5, n2 (1 – p2) = 325 > 5  Sampling dist.’s are approx. normal Pop. of burn patients > 7350 Since these are all burn patients, we can add: 316 + 419 = 735. If they’re different populations, we have to list them separately.

We are 95% confident that the true difference in proportions of people with no visible scars (plasma – control) is between 53.7% and 65.4%. If we made lots of intervals this way, 95% of them would contain the true difference in proportions.

Researchers want to estimate the difference in proportions of people who are against the death penalty in Texas & California. If the two sample sizes are the same, what size sample is needed to be within 2% of the true difference at 90% confidence?  n = 3383

So which decision is correct? Researchers comparing the effectiveness of two pain medications randomly selected a group of patients who had been complaining of joint pain. They randomly divided these people into two groups, and then administered the painkillers. Of the 112 people who received medication A, 84 said this pain reliever was effective. Of the 108 people in the other group, 66 reported that pain reliever B was effective. a) Construct two separate 95% confidence intervals for the proportion of people who reported that each pain reliever was effective. Is there a significant difference between these two proportions? b) Construct a 95% confidence interval for the difference in the proportions of people who find these medications effective. Is there a significant difference between these two proportions? CIA = (.67, .83) CIB = (.52, .70) Since the intervals overlap, we do not have evidence of a significant difference in the proportion of people who report each pain reliever is effective. CI = (0.017, 0.261) Since zero is not in the interval, there is a significant difference in these proportions. So which decision is correct? The second one – more directly compares the populations

Hypothesis Statements H0: p1 = p2 H0: p1 – p2 = 0 Ha: p1 – p2 > 0 Ha: p1 – p2 < 0 Ha: p1 – p2 ≠ 0 Be sure to define both p1 & p2! Ha: p1 > p2 Ha: p1 < p2 Ha: p1 ≠ p2

We assume the population proportions are equal in the H0. Thus, the standard deviation ( ) is the same for both populations. Therefore, we pool the variances!

Test Statistic p1 – p2 =0

A forest in Oregon has an infestation of spruce moths A forest in Oregon has an infestation of spruce moths. In an effort to control the moths, one area has been regularly sprayed by airplanes. In this area, a random sample of 495 spruce trees showed that 81 had been killed by moths. A nearby area received no spray. In this area, a random sample of 518 spruce trees showed that 92 had been killed by the moths. Do these data indicate that the proportion of spruce trees killed by the moths is different in the two areas?

Pop. of spruce trees > 10,130 Conditions: 2 independent SRS’s n1p1 = 81 > 5, n1(1 – p1) = 414 > 5, n2p2 = 92 > 5, n2(1 – p2) = 426 > 5  Normal samp. dist. Pop. of spruce trees > 10,130 H0: p1 = p2 where p1 and p2 are the true proportions Ha: p1 ≠ p2 of trees killed by moths in the treated and untreated areas

p-value = 0.5547 α = 0.05 Since p-value > α, we fail to reject H0. There is not sufficient evidence to suggest that the proportion of spruce trees killed by the moth is different in the two areas.