Chapter 3Thought Question 1Thought Question 2Sampling TerminologyBias and VariabilitySampling StrategyProportionsMargin of ErrorCase StudySlide 10Slide 11Key ConceptsChapter 3 1Chapter 3What Do Samples Tell Us?Chapter 3 2Thought Question 1During a medical exam, the doctor measures your cholesterol two times. Do you think both measurements would be exactly the same? Why or why not?Chapter 3 3Thought Question 2To estimate the percentage of all adults who have an internet connection in their homes, a properly chosen sample of 1100 adults across the U.S. was sampled, and 60% said “yes”. How close do you think that is to the percentage of the entire country who have an internet connection? Within 30%? 10%? 5%? 1%? Exactly the same?Chapter 3 4Sampling TerminologyParameter–fixed, unknown number that describes the populationStatistic–known value calculated from a sample–a statistic is used to estimate a parameterBias–in repeated samples, the sample statistic consistently misses the population parameter in the same directionVariability–different samples from the same population may yield different values of the sample statisticChapter 3 5Bias and VariabilityConsider shooting arrows at a target:Bias means the archer systematically misses in the same direction. Variability means that the arrows are scattered.Chapter 3 6Sampling StrategyTo reduce bias, use random samplingTo reduce variability, use larger samples–estimates from random samples will be closer to the true values in the population if the samples are larger–how close will they be?margin of errorChapter 3 7The proportion of a population that has some outcome (“success”) is p.The proportion of successes in a sample is measured by the sample proportion:Proportionssample the in nsobservatio of number totalsample the in successes of numberpˆ“p-hat”Chapter 3 8The amount by which the proportion obtained from the sample ( ) will differ from the true population proportion (p) rarely exceeds the margin of error.Margin of ErrorpˆTypical margin of error: 1/sqrt(n)–In 95% of surveys, the sample proportion will not differ from the population proportion by any more than the margin of error. (“95% confidence”)demoChapter 3 9Case Study62% say it should be guaranteedby the governmentsame as in 2000, up 6 points from 1996 31% say it is not the responsibilityof the governmentGuaranteed Health Insurance in the U.S.? New York Times/CBS News Poll, January 2006Chapter 3 10How the Poll was Conducted This New York Times/CBS News poll was based on telephone interviews conducted January 20 through January 25, 2006 with 1,229 adults throughout the United States. The survey has a random sampling error of approx. ±3 percent. Case StudyChapter 3 11Conclusion (Confidence statement) For the proportion of the population who favor guaranteed health insurance, the sample proportion was = .62 (62%) and the margin of error was ±.03 (3%). We can then say that “we are 95% confident that the proportion of the population who favor guaranteed health insurance was between .59 and .65 (59% and 65%).”Case StudypˆChapter 3 12Key ConceptsParameter versus StatisticBias and VariabilityMargin of ErrorConfidence
View Full Document