Hypothesis Testing

4,049 views

Published on

Published in: Technology, Health & Medicine
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
4,049
On SlideShare
0
From Embeds
0
Number of Embeds
7
Actions
Shares
0
Downloads
76
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Hypothesis Testing

  1. 1. HYPOTHESIS TESTING Amali N Ediriweera Dept. of HRM
  2. 2. Big picture Use a random sample to learn something about a larger population.
  3. 3. Two ways to learn about a population <ul><li>Confidence intervals </li></ul><ul><li>Hypothesis testing </li></ul>
  4. 4. Confidence Intervals <ul><li>Allow us to use sample data to estimate a population value, like the true mean or the true proportion. </li></ul><ul><li>Example: What is the true average amount students spend weekly on alcohol? </li></ul>
  5. 5. Hypothesis Testing <ul><li>Allows us to use sample data to test a claim about a population, such as testing whether a population proportion or population mean equals some number. </li></ul><ul><li>Example: Is the true average amount that students spent weekly on alcohol $20? </li></ul>
  6. 6. General Idea of Hypothesis Testing <ul><li>Make an initial assumption. </li></ul><ul><li>Collect evidence (data). </li></ul><ul><li>Based on the available evidence, decide whether or not the initial assumption is reasonable. </li></ul>
  7. 7. Example: Grade inflation? Population of 5 million college students Is the average GPA 2.7? Sample of 100 college students How likely is it that 100 students would have an average GPA as large as 2.9 if the population average was 2.7 ?
  8. 8. Making the Decision <ul><li>It is either likely or unlikely that we would collect the evidence we did given the initial assumption . </li></ul><ul><li>( Note: “Likely” or “unlikely” is measured by calculating a probability!) </li></ul><ul><li>If it is likely , then we “ do not reject ” our initial assumption. There is not enough evidence to do otherwise. </li></ul>
  9. 9. Making the Decision (cont’d) <ul><li>If it is unlikely, then: </li></ul><ul><ul><li>either our initial assumption is correct and we experienced an unusual event </li></ul></ul><ul><ul><li>or our initial assumption is incorrect </li></ul></ul><ul><li>In statistics, if it is unlikely, we decide to “ reject ” our initial assumption. </li></ul>
  10. 10. Idea of Hypothesis Testing: <ul><li>First , state 2 hypotheses, the null hypothesis (“H 0 ”) and the alternative hypothesis (“H A ”) </li></ul><ul><ul><li>H 0 : Defendant is not guilty. </li></ul></ul><ul><ul><li>H A : Defendant is guilty. </li></ul></ul>
  11. 11. An aside: Identification of hypotheses <ul><li>The null hypothesis always represents the status quo, i.e. the hypothesis that requires no change in current behavior. </li></ul><ul><li>The alternative hypothesis is the conclusion that the researcher is trying to make. </li></ul>
  12. 12. <ul><li>collect evidence, </li></ul><ul><ul><li>In statistics, the data are the evidence. </li></ul></ul><ul><li>Then , make initial assumption. </li></ul><ul><ul><li>In statistics, we always assume the null hypothesis is true . </li></ul></ul>
  13. 13. <ul><li>Then , make a decision based on the available evidence. </li></ul><ul><ul><li>If there is sufficient evidence (“beyond a reasonable doubt”), reject the null hypothesis . (Behave as if defendant is guilty.) </li></ul></ul><ul><ul><li>If there is not enough evidence, do not reject the null hypothesis . (Behave as if defendant is not guilty.) </li></ul></ul>
  14. 14. Important Point <ul><li>Neither decision entails proving the null hypothesis or the alternative hypothesis. </li></ul><ul><li>We merely state there is enough evidence to behave one way or the other. </li></ul><ul><li>This is also always true in statistics! No matter what decision we make, there is always a chance we made an error . </li></ul>
  15. 15. <ul><li>Goal: Keep  ,  reasonably small </li></ul>
  16. 16. Assumptions <ul><li>Assumptions needed for validity of Hypothesis Testing </li></ul><ul><li>1. Data are a RANDOM SAMPLE from the population of interest </li></ul><ul><ul><ul><li>(So that the sample can tell you about the population) </li></ul></ul></ul><ul><ul><li>2. The sample average is approximately NORMAL </li></ul></ul><ul><ul><ul><li>Either the data are normal (check the histogram) </li></ul></ul></ul><ul><ul><ul><li>Or the central limit theorem applies: </li></ul></ul></ul><ul><ul><ul><ul><li>Large enough sample size n , distribution not too skewed </li></ul></ul></ul></ul><ul><ul><ul><li>(So that the t table is technically appropriate) </li></ul></ul></ul>

×