1STA 291 - Lecture 23 1STA 291Lecture 23• Testing hypothesis about population proportion(s)• Examples.Exam II curve• 100 --- 83 A• 82 --- 71 B• 70 --- 59 C• 58 --- 48 D• 47 ---- 0 ESTA 291 - Lecture 23 2About bonus project• Must include at least following items:• Clearly state the null hypothesis to be tested, and the alternative hypothesis.• What kind of data you want to collect? How many data you want? (yes, more data is always better, but be reasonable)• Pick an alpha level.-- For each item, give some discussion of why you think this is the right choice.-- there is an example of “home field advantage” in book. Read itSTA 291 - Lecture 23 32Example: compare 2 proportions• A nation wide study: an aspirin every other day can sharply reduce a man’s risk of heart attack. (New York Times, reporting Jan. 27, 1987)• Aspirin group: 104 Heart Att. in 11037• Placebo group: 189 Heart Att. in 11034• Randomized, double-blinded studySTA 291 - Lecture 23 4Example – cont.• Let aspirin = group 1; placebo = group 2p1 = popu. proportion of Heart att. for group 1p2 = popu. proportion of Heart att. for group 2STA 291 - Lecture 23 5=−=012012: which is equivalent to :0HppHpp≠−≠1212: or :0AAHppHppExample – cont.• We may use software to compute a p-value• p-value = 7.71e-07 = 0.000000771Or we can calculate by hand:STA 291 - Lecture 23 6−=−−+1212ˆˆˆˆˆˆ(1)(1)obsppzppppnn3Example – cont.• n1= 11037, n2 = 11034 z = - 0.00770602/0.001540777= - 5.001386STA 291 - Lecture 23 71ˆ104/110370.00942285p ==2ˆ189/110340.01712887p ==ˆ(104189)/(1103711034)0.013275p=++=Example – cont.• P-value= 2 x P(Z > | - 5.00|) • It falls out of the range of our Z- table, so……P-value is approx. zero. (much smaller than 0.0000? )What is alpha level? Say it was 0.01. Since P-value is smaller than alpha, we reject the null hypothesis.STA 291 - Lecture 23 8STA 291 - Lecture 23 9Example 2• Let p denote the proportion of Floridians who think that government environmental regulations are too strict• Test H0: p=0.5 against a two-sided alternative using data from a telephone poll of 834 people conducted in June 1995 in which 26.6% said regulations were too strict• Calculate the test statistic• Find the p-value and interpret• Using alpha=0.01, can you determine whether a majority or minority think that environmental regulations are too strict, or is it plausible that p=0.5 ? • Construct a 99% confidence interval. Explain the advantage of the confidence interval over the test.4STA 291 - Lecture 23 10Example 3: KY Kernel Jan 17, 2007• UK researcher developed a blood substitute. A total of 712 trauma patients in the study. 349 receive PolyHeme (a blood substitute), 363 receive regular blood.• 46 died in the PolyHeme group• 35 died in the regular group.• Is there any difference in the two rates of death?• This is very similar to the heart attack example.• The only place we need to be careful: our formula only work well for large n (here n1 and n2)• Usually we check np > 10, and n(1-p) > 10STA 291 - Lecture 23 11STA 291 - Lecture 23 12Decisions and Types of Errors in Tests of Hypotheses• Terminology:– The alpha-level (significance level) is a threshold number such that one rejects the null hypothesis if the p-value is less than or equal to it. The most common alpha-levels are .05 and .01– The choice of the alpha-level reflects how cautious the researcher wants to be (when it come to reject null hypothesis)5STA 291 - Lecture 23 13Type I and Type II Errors• Type I Error: The null hypothesis is rejected, even though it is true.• Type II Error: The null hypothesis is not rejected, even though it is false.• Setting the alpha-level low protect us from type I Error. (the probability of making a type I error is less than alpha)STA 291 - Lecture 23 14Type I and Type II ErrorsDecisionRejectDo not rejectthe null hypothesisTrueType I errorCorrectFalse CorrectType II errorSTA 291 - Lecture 23 15Type I and Type II Errors• Terminology:– Alpha= Probability of a Type I error– Beta = Probability of a Type II error– Power = 1 – Probability of a Type II error• For a given data, the smaller the probability of Type I error, the larger the probability of Type II error and the smaller the power• If you set alpha very small, it is more likely that you fail to detect a real difference (larger Beta).6STA 291 - Lecture 23 16• When sample size(s) increases, both error probabilities could be made to decrease.• Our Strategy: • keep type I error probability small by pick a small alpha.• Increase sample size to make Beta small.STA 291 - Lecture 23 17Type I and Type II Errors• In practice, alpha is specified, and the probability of Type II error could be calculated, but the calculations are usually difficult ( sample size calculation )• How to choose alpha?• If the consequences of a Type I error are very serious, then chose a smaller alpha, like 0.01.• For example, you want to find evidence that someone is guilty of a crime.• In exploratory research, often a larger probability of Type I error is acceptable (like 0.05 or even 0.1) STA 291 - Lecture 23 18Alternative and p -value computationOne-Sided TestsTwo-Sided TestalternativeHypothesisp-value:AHpp0<0:0=Hpp:AHpp0>:AHpp0≠00(1)/0−=−)obsppzppn()obsPZz<()obsPZz>2(||)⋅>obsPZz7STA 291 - Lecture 23 19Two sample cases are similar, with two differences:• Hypothesis involve 2 parameters from 2 populations• Test statistic is different, involve 2 samplesSTA 291 - Lecture 23 20Alternative and p -value computationOne-Sided TestsTwo-Sided TestalternativeHypothesisp-value12:0AHpp−<012:0Hpp−=12:0AHpp−>12:0AHpp−≠()obsPZz<()obsPZz>2(||)obsPZz⋅>STA 291 - Lecture 23 21Two p’s=−=−=−−+0120121212: which is equivalent to :0,ˆˆˆˆˆˆ(1)(1)obsHppHppppzppppnn8STA 291 - Lecture 23 22• Where the in the denominator is the combined (pooled) sample proportion.= Total number of successes over total number of observationsˆpSTA 291 - Lecture 23 23Attendance Survey Question 23• On a 4”x6” index card–Please write down your name and section number–Today’s Question: –What is your lab instructor’s