1. CHAPTER 14 Introduction to Inference BPS - 5TH ED.CHAPTER 14 1

2. STATISTICAL INFERENCE  Provides methods for drawing conclusions about a population from sample data  Confidence Intervals  What is the population mean?  Tests of Significance  Is the population mean larger than 66.5? BPS - 5TH ED.CHAPTER 14 2

3. INFERENCE ABOUT A MEAN SIMPLE CONDITIONS 1. SRS from the population of interest 2. Variable has a Normal distribution N( ,  ) in the population 3. Although the value of  is unknown, the value of the population standard deviation  is known BPS - 5TH ED.CHAPTER 14 3

4. CONFIDENCE INTERVAL A level C confidence interval has two parts 1. An interval calculated from the data, usually of the form: estimate ± margin of error 2. The confidence level C, which is the probability that the interval will capture the true parameter value in repeated samples; that is, C is the success rate for the method. BPS - 5TH ED.CHAPTER 14 4

5. CASE STUDY BPS - 5TH ED.CHAPTER 14 5 NAEP Quantitative Scores (National Assessment of Educational Progress) Rivera-Batiz, F. L., “Quantitative literacy and the likelihood of employment among young adults,” Journal of Human Resources, 27 (1992), pp. 313-328. What is the average score for all young adult males?

6. CASE STUDY BPS - 5TH ED.CHAPTER 14 6 NAEP Quantitative Scores The NAEP survey includes a short test of quantitative skills, covering mainly basic arithmetic and the ability to apply it to realistic problems. Scores on the test range from 0 to 500, with higher scores indicating greater numerical abilities. It is known that NAEP scores have standard deviation  = 60.

7. CASE STUDY BPS - 5TH ED.CHAPTER 14 7 NAEP Quantitative Scores In a recent year, 840 men 21 to 25 years of age were in the NAEP sample. Their mean quantitative score was 272. On the basis of this sample, estimate the mean score  in the population of all 9.5 million young men of these ages.

8. CASE STUDY BPS - 5TH ED.CHAPTER 14 8 NAEP Quantitative Scores 1. To estimate the unknown population mean , use the sample mean = 272. 2. The law of large numbers suggests that will be close to , but there will be some error in the estimate. 3. The sampling distribution of has the Normal distribution with mean  and standard deviation

9. CASE STUDY BPS - 5TH ED.CHAPTER 14 9 NAEP Quantitative Scores

10. CASE STUDY BPS - 5TH ED.CHAPTER 14 10 NAEP Quantitative Scores 4. The 68-95-99.7 rule indicates that and  are within two standard deviations (4.2) of each other in about 95% of all samples.

11. CASE STUDY BPS - 5TH ED.CHAPTER 14 11 NAEP Quantitative Scores So, if we estimate that  lies within 4.2 of, we’ll be right about 95% of the time.

12. CONFIDENCE INTERVAL MEAN OF A NORMAL POPULATION Take an SRS of size n from a Normal population with unknown mean  and known standard deviation . A level C confidence interval for  is: BPS - 5TH ED.CHAPTER 14 12

13. CONFIDENCE INTERVAL MEAN OF A NORMAL POPULATION BPS - 5TH ED.CHAPTER 14 13

14. CASE STUDY BPS - 5TH ED.CHAPTER 14 14 NAEP Quantitative Scores Using the 68-95-99.7 rule gave an approximate 95% confidence interval. A more precise 95% confidence interval can be found using the appropriate value of z* (1.960) with the previous formula. We are 95% confident that the average NAEP quantitative score for all adult males is between 267.884 and 276.116.

15. CAREFUL INTERPRETATION OF A CONFIDENCE INTERVAL  “ We are 95% confident that the mean NAEP score for the population of all adult males is between 267.884 and 276.116. ” (We feel that plausible values for the population of males ’ mean NAEP score are between 267.884 and 276.116.)  ** This does not mean that 95% of all males will have NAEP scores between 267.884 and 276.116. **  Statistically: 95% of all samples of size 840 from the population of males should yield a sample mean within two standard errors of the population mean; i.e., in repeated samples, 95% of the C.I.s should contain the true population mean. BPS - 5TH ED.CHAPTER 14 15

16. CONFIDENCE INTERVALS: THE 4-STEPPROCESS 1. STATE: What is the practical question that requires estimating a parameter? 2. PLAN: Identify the parameter, choose a level of confidence, and select the type of confidence interval that fits the situation. 3. SOLVE: Carry out the work in two phases: 1. Check the conditions for the interval you plan to use 2. Calculate the confidence interval 4. CONCLUDE: Return to the practical question to describe your results in this setting. BPS - 5TH ED.CHAPTER 14 16

17. STATING HYPOTHESES BPS - 5TH ED.CHAPTER 14 17

18. STATING HYPOTHESES NULL HYPOTHESIS, H 0  The statement being tested in a statistical test is called the null hypothesis.  The test is designed to assess the strength of evidence against the null hypothesis.  Usually the null hypothesis is a statement of “ no effect ” or “ no difference ”, or it is a statement of equality.  When performing a hypothesis test, we assume that the null hypothesis is true until we have sufficient evidence against it. BPS - 5TH ED.CHAPTER 14 18

19. STATING HYPOTHESES ALTERNATIVE HYPOTHESIS, H A  The statement we are trying to find evidence for is called the alternative hypothesis.  Usually the alternative hypothesis is a statement of “ there is an effect ” or “ there is a difference ”, or it is a statement of inequality.  The alternative hypothesis should express the hopes or suspicions we bring to the data. It is cheating to first look at the data and then frame H a to fit what the data show. BPS - 5TH ED.CHAPTER 14 19

20. THE HYPOTHESES FOR MEANS EXAMPLES: BPS - 5TH ED.CHAPTER 14 20  Null: H 0 :  =  0 u One sided alternatives H a :   H a :   u Two sided alternative H a :  0

21. CASE STUDY I BPS - 5TH ED.CHAPTER 14 21 Sweetening Colas Diet colas use artificial sweeteners to avoid sugar. These sweeteners gradually lose their sweetness over time. Trained testers sip the cola and assign a “sweetness score” of 1 to 10. The cola is then retested after some time and the two scores are compared to determine the difference in sweetness after storage. Bigger differences indicate bigger loss of sweetness.

22. CASE STUDY I BPS - 5TH ED.CHAPTER 14 22 Sweetening Colas Suppose we know that for any cola, the sweetness loss scores vary from taster to taster according to a Normal distribution with standard deviation  = 1. The mean  for all tasters measures loss of sweetness. The sweetness losses for a new cola, as measured by 10 trained testers, yields an average sweetness loss of = 1.02. Do the data provide sufficient evidence that the new cola lost sweetness in storage?

23. CASE STUDY I BPS - 5TH ED.CHAPTER 14 23 Sweetening Colas  If the claim that  = 0 is true (no loss of sweetness, on average), the sampling distribution of from 10 tasters is Normal with  = 0 and standard deviation  The data yielded = 1.02, which is more than three standard deviations from  = 0. This is strong evidence that the new cola lost sweetness in storage.  If the data yielded = 0.3, which is less than one standard deviations from  = 0, there would be no evidence that the new cola lost sweetness in storage.

24. CASE STUDY I BPS - 5TH ED.CHAPTER 14 24 Sweetening Colas

25. STATING THE HYPOTHESES EXAMPLE 1 BPS - 5TH ED.CHAPTER 14 25 Sweetening Colas The null hypothesis is no average sweetness loss occurs, while the alternative hypothesis (that which we want to show is likely to be true) is that an average sweetness loss does occur. H 0 :  = 0H a :  > 0 This is considered a one-sided test because we are interested only in determining if the cola lost sweetness (gaining sweetness is of no consequence in this study).

26. STATING THE HYPOTHESES EXAMPLE II BPS - 5TH ED.CHAPTER 14 26 Studying Job Satisfaction Does the job satisfaction of assembly workers differ when their work is machine-paced rather than self- paced? A matched pairs study was performed on a sample of workers, and each worker’s satisfaction was assessed after working in each setting. The response variable is the difference in satisfaction scores, self- paced minus machine-paced.

27. HYPOTHESES EXAMPLE II BPS - 5TH ED.CHAPTER 14 27 Studying Job Satisfaction The null hypothesis is no average difference in scores in the population of assembly workers, while the alternative hypothesis (that which we want to show is likely to be true) is there is an average difference in scores in the population of assembly workers. H 0 :  = 0H a :  ≠ 0 This is considered a two-sided test because we are interested determining if a difference exists (the direction of the difference is not of interest in this study).

28. TEST STATISTIC BPS - 5TH ED.CHAPTER 14 28

29. TEST STATISTIC TESTING THE MEAN OF A NORMAL POPULATION Take an SRS of size n from a Normal population with unknown mean  and known standard deviation . The test statistic for hypotheses about the mean (H 0 :  =  0 ) of a Normal distribution is the standardized version of : BPS - 5TH ED.CHAPTER 14 29

30. CASE STUDY I BPS - 5TH ED.CHAPTER 14 30 Sweetening Colas If the null hypothesis of no average sweetness loss is true, the test statistic would be: Because the sample result is more than 3 standard deviations above the hypothesized mean 0, it gives strong evidence that the mean sweetness loss is not 0, but positive.

31. P-VALUES BPS - 5TH ED.CHAPTER 14 31

32. P-VALUE Assuming that the null hypothesis is true, the probability that the test statistic would take a value as extreme or more extreme than the value actually observed is called the P- value of the test. The smaller the P-value, the stronger the evidence the data provide against the null hypothesis. That is, a small P-value indicates a small likelihood of observing the sampled results if the null hypothesis were true. i.e. small p-values are evidence against the null hypotheses. BPS - 5TH ED.CHAPTER 14 32

33. P-VALUE FOR TESTING MEANS  H a :  >  0 v P-value is the probability of getting a value as large or larger than the observed test statistic (z) value.  H a :  <  0 v P-value is the probability of getting a value as small or smaller than the observed test statistic (z) value.  H a :  0 v P-value is two times the probability of getting a value as large or larger than the absolute value of the observed test statistic (z) value. BPS - 5TH ED.CHAPTER 14 33

34. CASE STUDY I BPS - 5TH ED.CHAPTER 14 34 Sweetening Colas For test statistic z = 3.23 and alternative hypothesis H a :  > 0, the P-value would be: P-value = P(Z > 3.23) = 1 – 0.9994 = 0.0006 If H 0 is true, there is only a 0.0006 (0.06%) chance that we would see results at least as extreme as those in the sample; thus, since we saw results that are unlikely if H 0 is true, we therefore have evidence against H 0 and in favor of H a.

35. CASE STUDY I BPS - 5TH ED.CHAPTER 14 35 Sweetening Colas

36. CASE STUDY II BPS - 5TH ED.CHAPTER 14 36 Studying Job Satisfaction Suppose job satisfaction scores follow a Normal distribution with standard deviation  = 60. Data from 18 workers gave a sample mean score of 17. If the null hypothesis of no average difference in job satisfaction is true, the test statistic would be:

37. CASE STUDY II BPS - 5TH ED.CHAPTER 14 37 Studying Job Satisfaction For test statistic z = 1.20 and alternative hypothesis H a :  ≠ 0, the P-value would be : P-value= P(Z 1.20) = 2 P(Z 1.20) = (2)(0.1151) = 0.2302 If H 0 is true, there is a 0.2302 (23.02%) chance that we would see results at least as extreme as those in the sample; thus, since we saw results that are likely if H 0 is true, we therefore do not have good evidence against H 0 and in favor of H a.

38. CASE STUDY II BPS - 5TH ED.CHAPTER 14 38 Studying Job Satisfaction

39. STATISTICAL SIGNIFICANCE BPS - 5TH ED.CHAPTER 14 39

40. STATISTICAL SIGNIFICANCE  If the P-value is as small as or smaller than the significance level  (i.e., P-value ≤  ), then we say that the data give results that are statistically significant at level .  If we choose  = 0.05, we are requiring that the data give evidence against H 0 so strong that it would occur no more than 5% of the time when H 0 is true.  If we choose  = 0.01, we are insisting on stronger evidence against H 0, evidence so strong that it would occur only 1% of the time when H 0 is true. BPS - 5TH ED.CHAPTER 14 40

41. TESTS FOR A POPULATION MEAN The four steps in carrying out a significance test: 1. State the null and alternative hypotheses. 2. Calculate the test statistic. 3. Find the P-value. 4. State your conclusion in the context of the specific setting of the test. The procedure for Steps 2 and 3 is on the next page. BPS - 5TH ED.CHAPTER 14 41

42. BPS - 5TH ED.CHAPTER 14 42

43. CASE STUDY I BPS - 5TH ED.CHAPTER 14 43 Sweetening Colas 1. Hypotheses:H 0 :  = 0 H a :  > 0 2. Test Statistic: 3. P-value:P-value = P(Z > 3.23) = 1 – 0.9994 = 0.0006 4. Conclusion: Since the P-value is smaller than  = 0.01, there is very strong evidence that the new cola loses sweetness on average during storage at room temperature.

44. CASE STUDY II BPS - 5TH ED.CHAPTER 14 44 Studying Job Satisfaction 1. Hypotheses:H 0 :  = 0 H a :  ≠ 0 2. Test Statistic: 3. P-value:P-value = 2P(Z > 1.20) = (2)(1 – 0.8849) = 0.2302 4. Conclusion: Since the P-value is larger than  = 0.10, there is not sufficient evidence that mean job satisfaction of assembly workers differs when their work is machine-paced rather than self-paced.

45. CONFIDENCE INTERVALS & TWO-SIDED TESTS BPS - 5TH ED.CHAPTER 14 45 A level  two-sided significance test rejects the null hypothesis H 0 :  =  0 exactly when the value  0 falls outside a level (1 –  ) confidence interval for .

46. CASE STUDY II BPS - 5TH ED.CHAPTER 14 46 A 90% confidence interval for  is: Since  0 = 0 is in this confidence interval, it is plausible that the true value of  is 0; thus, there is not sufficient evidence (at  = 0.10) that the mean job satisfaction of assembly workers differs when their work is machine-paced rather than self-paced. Studying Job Satisfaction