Test of hypothesis

48,978 views
48,898 views

Published on

Published in: Technology, Health & Medicine
6 Comments
44 Likes
Statistics
Notes
No Downloads
Views
Total views
48,978
On SlideShare
0
From Embeds
0
Number of Embeds
20
Actions
Shares
0
Downloads
3,362
Comments
6
Likes
44
Embeds 0
No embeds

No notes for slide

Test of hypothesis

  1. 1. Test of Hypothesis <ul><li>Hypothesis- Hypothesis is generally considered the most important instrument in research. Its main function is to suggest new functions and ideas. In social sciences where direct knowledge of population parameters is rare hypothesis testing is the often used for deciding whether sample data supports our purpose </li></ul>
  2. 2. WHAT IS A HYPOTHESIS <ul><li>Generally hypothesis is considered as an assumption or a supposition which has to be proved or disproved. </li></ul><ul><li>But for a researcher hypothesis is a formal question that he has to resolve </li></ul>
  3. 3. WHAT IS A HYPOTHESIS <ul><li>A hypothesis may be defined as a proposition or a set of propositions set forth as an explanation for the occurrence of some specific group of phenomena . A research hypothesis is a predictive statement capable of being tested by scientific methods that relate an independent variable to some dependent variable </li></ul>
  4. 4. WHAT IS A HYPOTHESIS <ul><li>Example </li></ul><ul><li>The mileage of automobile A is as good as automobile b </li></ul><ul><li>The customer loyalty of brand A is better than brand B. </li></ul><ul><li>These hypotheses are capable of objectively verified and tested </li></ul>
  5. 5. Characteristics of a hypothesis <ul><li>Hypothesis should be clear and precise </li></ul><ul><li>Hypothesis should be capable of being tested </li></ul><ul><li>Hypothesis should be able to relate to a variable. </li></ul>
  6. 6. Characteristics of a hypothesis <ul><li>Hypothesis must be limited in scope and must be specific </li></ul><ul><li>Hypothesis must be stated in very simple terms. </li></ul><ul><li>Hypothesis must be consistent with most known facts </li></ul>
  7. 7. Characteristics of a hypothesis <ul><li>Hypothesis must be testable within a reasonable time </li></ul><ul><li>Hypothesis must explain the facts which most need explaining </li></ul>
  8. 8. Basic concepts concerning testing of hypothesis <ul><li>Null Hypothesis and alternative hypothesis </li></ul><ul><li>In statistical analysis if we want to compare method A with method B and if we proceed with the assumption that both methods are equally good then this assumption is termed as null hypothesis. </li></ul>
  9. 9. Basic concepts concerning testing of hypothesis <ul><li>As against this we may feel that method A is better than method B then we call it as alternative hypothesis </li></ul>
  10. 10. Basic concepts concerning testing of hypothesis <ul><li>Null Hypothesis is generally is termed as H0 and alternative hypothesis symbolized as Ha </li></ul>
  11. 11. Basic concepts concerning testing of hypothesis <ul><li>Suppose we want to test the hypothesis that the population mean µ is equivalent to hypnotized mean then µ0 = 100 </li></ul><ul><li>Then null hypothesis would be population mean is equal to hypothysed mean i.e </li></ul><ul><li>Ho: µ= µHo = 100 </li></ul>
  12. 12. Basic concepts concerning testing of hypothesis <ul><li>The null hypothesis, H0 represents a theory that has been put forward, either because it is believed to be true or because it is to be used as a basis for argument, but has not been proved. </li></ul>
  13. 13. Basic concepts concerning testing of hypothesis <ul><li>For example, in a clinical trial of a new drug, the null hypothesis might be that the new drug is no better, on average, than the current drug. We would write H0: there is no difference between the two drugs on average. </li></ul>
  14. 14. Basic concepts concerning testing of hypothesis <ul><li>If our sample results do not support this then we assume something else is true. The alternative that we will accept is known as alternative hypothesis Ha </li></ul><ul><li>Alternative Hypothesis would be </li></ul><ul><li>Ho: µ ≠ µHo i.e population mean is not equal to hypothized mean </li></ul>
  15. 15. Basic concepts concerning testing of hypothesis <ul><li>The alternative hypothesis, H a , is a statement of what a statistical hypothesis test is set up to establish </li></ul>
  16. 16. Basic concepts concerning testing of hypothesis <ul><li>For example, in a clinical trial of a new drug, the alternative hypothesis might be that the new drug has a different effect, on average, compared to that of the current drug. We would write Ha: the two drugs have different effects, on average.. </li></ul>
  17. 17. Basic concepts concerning testing of hypothesis <ul><li>The alternative hypothesis might also be that the new drug is better, on average, than the current drug. In this case we would write Ha: the new drug is better than the current drug, on average </li></ul>
  18. 18. Basic concepts concerning testing of hypothesis <ul><li>Ho: µ < µHo i.e population mean is greater than hypothized mean </li></ul><ul><li>Ho: µ > µHo i.e population mean is lesser than hypothysed mean </li></ul><ul><li>The null hypothesis and alternative hypothesis is chosen before the sample is drown </li></ul>
  19. 19. Following considerations are kept in view <ul><li>The alternative hypothesis is one which one wants to prove </li></ul>
  20. 20. Following considerations are kept in view <ul><li>We give special consideration to the null hypothesis. This is due to the fact that the null hypothesis relates to the statement being tested, whereas the alternative hypothesis relates to the statement to be accepted if / when the null is rejected. </li></ul>
  21. 21. Following considerations are kept in view <ul><li>The final conclusion once the test has been carried out is always given in terms of the null hypothesis. We either 'reject H0 in favour of H a ' or 'do not reject H0'; we never conclude 'reject H a ', or even 'accept H a ' </li></ul>
  22. 22. Following considerations are kept in view <ul><li>If we conclude 'do not reject H0', this does not necessarily mean that the null hypothesis is true, it only suggests that there is not sufficient evidence against H0 in favour of H a ; rejecting the null hypothesis then, suggests that the alternative hypothesis may be true. </li></ul>
  23. 23. Type I Error α error <ul><li>In a hypothesis test, a type I error occurs when the null hypothesis is rejected when it is in fact true; that is, H0 is wrongly rejected. </li></ul>
  24. 24. Type I Error α error <ul><li>For example, in a clinical trial of a new drug, the null hypothesis might be that the new drug is no better, on average, than the current drug; that is H0: there is no difference between the two drugs on average. A type I error would occur if we concluded that the two drugs produced different effects when in fact there was no difference between them. </li></ul>
  25. 25. Type I Error α error <ul><li>The following table gives a summary of possible results of any hypothesis test: </li></ul>
  26. 26. Type I Error α error Type II Error Right Decision H a Right Decision Type I Error H 0 Truth Don't reject H 0 Reject H 0 Decision
  27. 27. Type I Error α error <ul><li>A type I error is often considered to be more serious, and therefore more important to avoid, than a type II error. The hypothesis test procedure is therefore adjusted so that there is a guaranteed 'low' probability of rejecting the null hypothesis wrongly; </li></ul>
  28. 28. Type I Error α error <ul><li>this probability is never 0. This probability of a type I error can be precisely computed as, </li></ul><ul><li>P(type I error) = significance level = The exact probability of a type II error is generally unknown. </li></ul>
  29. 29. Type I Error α error <ul><li>If we do not reject the null hypothesis, it may still be false (a type II error) as the sample may not be big enough to identify the falseness of the null hypothesis (especially if the truth is very close to hypothesis). </li></ul>
  30. 30. Type I Error α error <ul><li>For any given set of data, type I and type II errors are inversely related; the smaller the risk of one, the higher the risk of the other. </li></ul><ul><li>A type I error can also be referred to as an error of the first kind </li></ul>
  31. 31. Type II Error β error <ul><li>In a hypothesis test, a type II error occurs when the null hypothesis H0, is not rejected when it is in fact false. </li></ul>
  32. 32. Type I Error α error <ul><li>For example, in a clinical trial of a new drug, the null hypothesis might be that the new drug is no better, on average, than the current drug; that is H0: there is no difference between the two drugs on average. </li></ul>
  33. 33. Type I Error α error <ul><li>A type II error would occur if it was concluded that the two drugs produced the same effect, that is, there is no difference between the two drugs on average, when in fact they produced different ones. </li></ul>
  34. 34. Type I Error α error <ul><li>A type II error is frequently due to sample sizes being too small. </li></ul><ul><li>The probability of a type II error is symbolised by and written: </li></ul><ul><li>P(type II error) = (but is generally unknown). </li></ul><ul><li>A type II error can also be referred to as an error of the second kind </li></ul>
  35. 35. Significance Level <ul><li>The significance level of a statistical hypothesis test is a fixed probability of wrongly rejecting the null hypothesis H0, if it is in fact true. </li></ul>
  36. 36. Significance Level <ul><li>It is the probability of a type I error and is set by the investigator in relation to the consequences of such an error. That is, we want to make the significance level as small as possible in order to protect the null hypothesis and to prevent, as far as possible, the investigator from inadvertently making false claims. </li></ul>
  37. 37. Significance Level <ul><li>The significance level is usually denoted by Significance Level = P(type I error) = Usually, the significance level is chosen to be = 0.05 = 5%. </li></ul>
  38. 38. Significance Level <ul><li>One-sided Test </li></ul><ul><li>A one-sided test is a statistical hypothesis test in which the values for which we can reject the null hypothesis, H0 are located entirely in one tail of the probability distribution. </li></ul>
  39. 39. Significance Level <ul><li>In other words, the critical region for a one-sided test is the set of values less than the critical value of the test, or the set of values greater than the critical value of the test. </li></ul><ul><li>A one-sided test is also referred to as a one-tailed test of significance </li></ul>
  40. 40. Significance Level <ul><li>The choice between a one-sided and a two-sided test is determined by the purpose of the investigation or prior reasons for using a one-sided test </li></ul>
  41. 41. Significance Level <ul><li>Example </li></ul><ul><li>Suppose we wanted to test a manufacturers claim that there are, on average, 50 matches in a box. We could set up the following hypotheses </li></ul><ul><li>Ho: µ =50 as against </li></ul><ul><li>Ha: µ <50 or </li></ul><ul><li>Ha: µ >50 </li></ul>
  42. 42. Significance Level <ul><li>Either of these two alternative hypotheses would lead to a one-sided test. Presumably, we would want to test the null hypothesis against the first alternative hypothesis since it would be useful to know if there is likely to be less than 50 matches, on average, in a box (no one would complain if they get the correct number of matches in a box or more). </li></ul>
  43. 43. Significance Level <ul><li>Yet another alternative hypothesis could be tested against the same null, leading this time to a two-sided test: </li></ul><ul><li>Ho: µ =50 as against </li></ul><ul><li>Ha: µ ≠ 50 </li></ul>
  44. 44. Significance Level <ul><li>That is, nothing specific can be said about the average number of matches in a box; only that, if we could reject the null hypothesis in our test, we would know that the average number of matches in a box is likely to be less than or greater than 50. </li></ul>
  45. 45. Two-Sided Test <ul><li>A two-sided test is a statistical hypothesis test in which the values for whic h we can reject the null hypothesis, H0 are located in both tails of the probability distribution. </li></ul>
  46. 46. Two-Sided Test <ul><li>In other words, the critical region for a two-sided test is the set of values less than a first critical value of the test and the set of values greater than a second critical value of the test </li></ul><ul><li>A two-sided test is also referred to as a two-tailed test of significance. </li></ul>
  47. 47. Two-Sided Test <ul><li>The choice between a one-sided test and a two-sided test is determined by the purpose of the investigation or prior reasons for using a one-sided test. </li></ul>
  48. 48. <ul><li>Thank you </li></ul>

×