1. + Homework READ p. 261 - 268 COMPLETE (p.260)  91-98; (p.269)  102-108 Test Practice Ch 4 – Exp Design Exercises packet w/ answers Ch 4 – MC practice packet w/ answers Ch 4 – Review Packet w/ answers Please Complete the Following Bonus Test Chapter 3 – today-Th after school 4.2 Quiz Thursday in class (read p.252) Chapter 4 Test this Friday 11/9 Upcoming

2. + Solutions to last night’s homework 4.78(a) The blocks are the sexes. The cancer reacts differently to treatments in men and women so we want to eliminate sex as a lurking variable. We want to test all three types of treatments in both men and women. (b) If we used a completely randomized design, we could end up with a treatment that is given much more frequently to one of the two sexes. Then we will not know if any differences we see between that treatment and the others are due to the treatment itself, or the fact that cancer reacts differently in women than men. (c) If the researchers had only 800 men and no women, we would not have to have a block design. We could just randomly assign the treatments to the subjects. Unfortunately, we would only be able to make conclusions about how the treatments work in men.

3. + Day 9 / 11 Chapter 4: Designing Studies Section 4.2Experiments Section 4.3Using Studies Wisely

4. + Section 4.2 – Experiments After this section, you should be able to… STATE, in context, what statistically significant means DISTINGUISH between a completely randomized design and a randomized block design KNOW when a matched pairs experimental design is appropriate and how to implement such a design Learning Objectives

5. + Experiments AP Error Alert! Many students confuse blocking and treatment groups. Blocks are not formed at random. Instead they are formed by grouping experimental units that are similar in some way that is expected to systematically affect the response to the treatments. This means that each block should be very different from other blocks. However, a treatment group is formed at random, with the goal that the treatments groups will be as similar as possible to each other.

6. + Experiments Matched-Pairs Design A common type of randomized block design for comparing twotreatments is a matched pairs design. The idea is to create blocks bymatching pairs of similar experimental units. Definition A matched-pairs design is a randomized blocked experiment in which each block consists of a matching pair of similar experimental units. Chance is used to determine which unit in each pair gets each treatment. Sometimes, a “pair” in a matched-pairs design consists of a single unit that receives both treatments - Measure the same individuals for both treatments - Since the order of the treatments can influence the response, chance is used to determine with treatment is applied first for each unit.

7. + Experiments Matched Pairs Design Standing and Sitting Pulse Rate Design determines analysis A class of 24 AP students performed two experiments to determine if standing pulse rates are generally higher than sitting pulse rates. They conducted a completely randomized design in which twelve students were randomly assigned to sitting and standing groups using a random number generator. They then conducted a matched pairs design in which each student took his or her pulse rate sitting then again standing.

8. + Experiments Matched-Pairs Design Standing and Sitting Pulse Rate A Fathom dotplot of the pulse rates for the completely randomized design is shown below. The mean pulse rate for the standing group is 74.83; the mean for the sitting group is 68.33. So the average pulse rate is 6.5 beats per minute higher in the standing group.

9. + Experiments Matched-Pairs Design Standing and Sitting Pulse Rate A Fathom dotplot of the difference of the pulse rates for the matched-pairs design is shown below. The mean difference was 6.8 bpm.

10. + Experiments More on Blocking Unless the link is obvious, you must justify the reasonfor blocking on any variable! The difference between randomization and blocking:  You block to control for the variables you know about that might influence the response  You randomize to control for the variables you do NOT know about. Blocks allow us to draw separate conclusionsabout each block.

11. + Chapter 4 Designing Studies 4.1Samples and Surveys 4.2Experiments 4.3Using Studies Wisely

12. + Section 4.3 Using Studies Wisely After this section, you should be able to… DESCRIBE the challenges of establishing causation DEFINE the scope of inference DESCRIBE data ethics in designing studies Learning Objectives

13. + Using Studies Wisely Scope of InferenceWhat type of inference can be made from a particular study? The answer depends on the design of the study. Well-designed experiments randomly assign individuals to treatment groups. However, most experiments don’t selectexperimental units at random from the larger population. Thatlimits such experiments to inference about cause and effect. Observational studies don’t randomly assign individuals to groups, which rules out inference about cause and effect.Observational studies that use random sampling can make inferences about the population.

14. + Using Studies Wisely Your Turn: Which is Which? The U.S. Census Bureau carries out a monthly CurrentPopulation Survey of about 60,000 households. Their goals isto use data from these randomly selected households toestimate the percent of unemployed individuals in thepopulation. Scientists performed an experiment that randomly assigned 21volunteer subjects to one of two treatments: sleep deprivationfor one night or unrestricted sleep. The experimenters hopedto show that sleep deprivation causes a decrease inperformance two days later.

15. + Experiments AP Error Alert! Students often confuse the two types of inferences we can make: inferences about a population and inferences about cause and effect. Over the years, there have been many questions on the AP exam that ask students to discuss what type of inferences are appropriate based on the design of the study in the problem. Make sure you understand how the role of randomization in a study helps to decide which type of inference, if any, is appropriate. Random sampling  inference about a population Random treatment allocation  inference about cause & effect

16. + Using Studies Wisely What Can We Conclude? Vitamin C and Canker Sores A small-town dentist wants to know if a daily does of 500milligrams of vitamin C will result in fewer canker sores in themouth than taking no vitamin C. The dentist is considering four study designs. Read each of the following designs and determine what thedentist can conclude (if anything) from each study design. (Assume that the dentist compares the proportion of patientsin each group who complain of canker sores. And finds astatistically significant difference, with a smaller proportion ofthose taking vitamin C having canker sores.)

17. + Using Studies Wisely What Can We Conclude? Design 1: Get all dental patients in town with appointments in the next two weeks to take part in astudy. Give each patient a survey with two questions:(1) Do you take at least 500mg of vitamin C each day?(2) Do you frequently have canker sores? Based onpatients’ answers to Question 1, divide them into twogroups: those who take at least 500mg of vitamin Cdaily and those who don’t. Since the patients were not randomly selected, thedentist cannot infer that this result holds for a largerpopulation of dental patients. This was an observationalstudy since no treatments were deliberately imposed onthe patients. With no random assignment, no inferencefor cause & effect can be made.

18. + Using Studies Wisely What Can We Conclude? Design 2: Get all dental patients in town with appointments in the next two weeks to take part in astudy. Randomly assign half of them to take 500mgof vitamin C each day and the other half to abstainfrom taking vitamin C for three months. The dentist cannot make inferences about thisresult holding for a larger population of dentalpatients. However, the treatments were randomlyassigned to the subjects. Assuming proper controlin the experiment, she can conclude that takingvitamin C reduced the chance of getting cankersores in her subjects.

19. + Using Studies Wisely What Can We Conclude? Design 3: Select a random sample of dental patients in town and get them to take part in a study. Divide thepatients into two groups as in Design 1. Since the patients were randomly selected from thepopulation of dental patients in the town, the dentist cangeneralize the results of this study to the population.Because this was an observational study, no inferenceabout cause and effect can be made. The dentist wouldconclude that for the population of dental patients in thistown, those taking vitamin C have fewer canker soresthan those who don't. She can’t say whether the vitaminC causes this reduction or some other confoundingvariable. She cannot make inferences about the generalpopulation, since she surveyed only dental patients.

20. + Using Studies Wisely What Can We Conclude? Design 4: Select a random sample of dental patients in town and get them to take part in a study. Randomlyassign half of them to take 500mg of vitamin C each dayand the other half to abstain from taking vitamin C forthree months. As in Design 3, the random sampling allows the dentistto generalize the results of this study to the population ofdental patients in the town. As in Design 2, the randomassignment would allow her to conclude (assumingproper control) that taking vitamin C reduced the chanceof getting canker sores. So the dentist would concludethat for the population of dental patients in this town,those taking vitamin C will tend to have fewer cankersores than those who don’t due to the vitamin C. As with Design 3, she can’t extend this result to the generalpopulation of the town.

21. + Using Studies Wisely The Challenges of Establishing CausationA well-designed experiment tells us that changes in the explanatory variable cause changes in the response variable. Lack of realism can limit our ability to apply the conclusions of an experiment to the settings of greatest interest. In some cases it isn’t practical or ethical to do an experiment. Consider these questions: Does texting while driving increase the risk of having an accident?  Does going to church regularly help people live longer?  Does smoking cause lung cancer? It is sometimes possible to build a strong case for causation in the absence of experiments by considering data fromobservational studies.

22. + Using Studies Wisely The Challenges of Establishing CausationWhen we can’t do an experiment, we can use the following criteria for establishing causation.  The association is strong.  The association is consistent.  Larger values of the explanatory variable are associated with stronger responses.  The alleged cause precedes the effect in time.  The alleged cause is plausible. Discuss how each of these criteria apply to the observational studies of the relationship between smoking and lung cancer.

23. + Using Studies Wisely Data EthicsComplex issues of data ethics arise when we collect data from people. Here are some basic standards of data ethics thatmust be obeyed by all studies that gather data from humansubjects, both observational studies and experiments. All planned studies must be reviewed in advance by an institutional review board charged with protecting the safety and well-being of the subjects. All individuals who are subjects in a study must give their informed consent before data are collected. All individual data must be kept confidential. Only statistical summaries for groups of subjects may be made public. Basic Data Ethics

24. + Homework READ p. 261 - 268 COMPLETE (p.260)  91-98; (p.269)  102-108 Test Practice Ch 4 – Exp Design Exercises packet w/ answers Ch 4 – MC practice packet w/ answers Ch 4 – Review Packet w/ answers Please Complete the Following Bonus Test Chapter 3 – today-Th after school 4.2 Quiz Thursday in class (read p.252) Chapter 4 Test this Friday 11/9 Upcoming