Hypothesis Tests for a Population Proportion

Slides:



Advertisements
Similar presentations
Testing a Claim about a Proportion Assumptions 1.The sample was a simple random sample 2.The conditions for a binomial distribution are satisfied 3.Both.
Advertisements

The z-Test What is the Purpose of a z-Test? What are the Assumptions for a z- Test? How Does a z-Test Work?
Significance Tests for Proportions Presentation 9.2.
Inference about Two Population Proportions. Definition A sampling method is independent when the individuals selected for one sample do not dictate which.
Means Tests Hypothesis Testing Assumptions Testing (Normality)
Inference about Two Population Standard Deviations.
The Probability of a Type II Error and the Power of the Test
Testing Hypotheses about a Population Proportion Lecture 30 Sections 9.3 Wed, Oct 24, 2007.
Large sample CI for μ Small sample CI for μ Large sample CI for p
Slide Slide 1 Section 8-4 Testing a Claim About a Mean:  Known.
Copyright © 2011 Pearson Education, Inc. Putting Statistics to Work.
Testing Hypotheses about a Population Proportion Lecture 29 Sections 9.1 – 9.3 Fri, Nov 12, 2004.
Testing Hypotheses about a Population Proportion Lecture 29 Sections 9.1 – 9.3 Wed, Nov 1, 2006.
Testing Hypotheses about a Population Proportion Lecture 31 Sections 9.1 – 9.3 Wed, Mar 22, 2006.
Correlation. u Definition u Formula Positive Correlation r =
Hypothesis Tests for a Population Standard Deviation.
Step by Step Example of Hypothesis Testing of a Proportion.
Section 8.2 Day 3.
Hypothesis Testing – Two Population Variances
9.3 Hypothesis Tests for Population Proportions
Chapter 9 Hypothesis Testing.
Inference about Two Means - Independent Samples
Significance Test for the Difference of Two Proportions
Hypothesis Testing for Proportions
Hypothesis Testing: One Sample Cases
One-Sample Inference for Proportions
Hypothesis Testing I The One-sample Case
Testing Hypotheses about a Population Proportion
Comparing Two Proportions
Business Statistics Topic 7
Statistics Chapter 7 Review.
Chapters 20, 21 Hypothesis Testing-- Determining if a Result is Different from Expected.
Hypothesis Testing for Proportions
Section 8.2 Day 4.
Testing a Claim About a Mean:  Known
Testing Goodness of Fit
Inference about Two Means: Dependent Samples
Hypothesis Tests for a Population Mean in Practice
Unlocking the Mysteries of Hypothesis Testing
Inferences on Two Samples Summary
Elementary Statistics
STATISTICS INFORMED DECISIONS USING DATA
Statistical inference
Inference about Two Means: Independent Samples
Statistical Inference
Hypothesis Tests for Proportions
Hypothesis Testing.
Hypothesis Test for Independent Groups Two Proportions
Hypothesis tests for the difference between two proportions
Hypothesis Tests for a Population Mean
Hypothesis Tests for Proportions
Chi-Square Goodness of Fit Test
Lecture 10/24/ Tests of Significance
Hypothesis Tests for a Standard Deviation
CHAPTER 12 Inference for Proportions
Testing Hypotheses about a Population Proportion
CHAPTER 12 Inference for Proportions
Testing Hypotheses about a Population Proportion
Testing Hypotheses I Lesson 9.
Inference about Two Population Proportions
Testing Hypotheses about a Population Proportion
Hypothesis Testing for Proportions
Section 8.2 Day 2.
Hypothesis Tests for a Population Proportion
7.4 Hypothesis Testing for Proportions
Inferences from Matched Pairs
Inference about Two Means: Dependent Samples
Testing Hypotheses about a Population Proportion
Statistical inference
Testing a Claim About a Mean:  Known
Presentation transcript:

Hypothesis Tests for a Population Proportion

Definition When observed results are unlikely under the assumption that the null hypothesis is true, we say the result is statistically significant and we reject the null hypothesis

Classical Approach (TI-83/84) Write down a shortened version of claim Come up with null and alternate hypothesis (Ho always has the equals part on it) See if claim matches Ho or H1 Draw the picture and split α into tail(s) H1: p ≠ value Two Tail H1: p < value Left Tail H1: p > value Right Tail Find critical values (INVNORM) Find test statistic (1-PROPZTEST) If test statistic falls in tail, Reject Ho. If test statistic falls in main body, Accept Ho. Determine the claim based on step 3

Classical Approach (By Hand) Write down a shortened version of claim Come up with null and alternate hypothesis (Ho always has the equals part on it) See if claim matches Ho or H1 Draw the picture and split α into tails H1: p ≠ value Two Tail H1: p < value Left Tail H1: p > value Right Tail

Classical Approach (By Hand) (cont.)  

P-Value Approach (TI-83/84) Write down a shortened version of claim Come up with null and alternate hypothesis (Ho always has the equals part on it) See if claim matches Ho or H1 Find p-value (1-PROPZTEST) If p-value is less than α, Reject Ho. If p-value is greater than α, Accept Ho. Determine the claim based on step 3

P-Value Approach (By Hand)  

P-Value Approach (By Hand) (cont.) Lookup the z-score from step 4 in the Standard Normal Distribution table and find the p-value (Remember the p value is the area JUST in the tail(s)) If p-value is less than α, Reject Ho. If p-value is greater than α, Accept Ho. Determine the claim based on step 3

1. Claim According to ABC News in June 2012, 36% of people believe in UFO’s in the United States. If a sample of 200 people find that 74 of them believe in UFO’s, test the claim that the percentage that believe in UFO’s is greater now at α = 0.05

2. Claim According to the Chicago Tribune in 1990, 74% of teenagers believed in Angels. If a sample of 500 teenagers shows that 410 believe in Angels, test the claim that the percentage is the same at α = 0.10

3. Claim According to the Chicago Tribune in 1990, 50% of teenagers believed in ESP. If a sample of 400 teenagers shows that 190 believe in ESP, test the claim that the percentage is different nowadays at α = 0.01

4. Claim According to the Chicago Tribune in 1990, 29% of teenagers believed in witchcraft. If a sample of 500 teenagers shows that 80 believe in witchcraft, test the claim that the percentage is lower nowadays at α = 0.05

Two-Tailed Hypothesis Testing Using a Confidence Interval When testing Ho: p = po versus H1: p ≠ po, if a confidence interval (based on 1 – α) contains po, we do not reject the null hypothesis. However, if the confidence interval does not contain po, we conclude that p ≠ po at the level of significance