+ +Lecture NotesStatistics 301Professor WardropFall, 2008See:stat.wisc.edu/~wardrop/courses/301fall2008.htmlhenceforth referred to as ‘course website.’These notes are on the c ourse website.+ 1+ +Every day:• Try to remember to put your cell phoneon silent or vibrate before class. If youmust take a call, leave the lecture hall.• Collect your trash and recyclables at theend of class, take them with you and dis-pose of them properly.• Remind yourself to vote in November.+ 2+ +Trying to enroll in Lecture 3 or 4?Send the following information:• your name and student id• a prioritized list of all discussions you arewilling to accept; put most fav orite first,least favorite la st ; refer to a discussion byits three digit number, e .g. 342, not itsfive digit c om puter code .to [email protected], but want to change your discussion?This will be ‘handled informally.’+ 3+ +There will be two exams:• Midterm on Thursday, October 23, in lec-ture room during class time with an extra10 m i nutes (85 minutes t otal).• Final, ac c ording to university schedule, inroom assigned by university (120 minutes).Both exams are open book, open notes andyou should bring a c alculator.You must readCalendar, Exa m Schedule, Etc.from course website.+ 4+ +There wi ll be two extra class meetings, forreviews for the exams. Details will follow.Balanced by two canceled class periods:• Tuesday, November 25 (the week of Thanks-giving). (There will be discussions thatweek; details to follow.)• One ‘snow day.’Note: If we do not need a snow day, then thesecond review will be during the last lectureperiod, Thursday, Dec ember 11.+ 5+ +ReadDetermination of Course Gradefrom course website.Main ideas.• 200 points are possible: 132 points forexams; 51 (3 × 17) points for projects;and 17 points for homewor k.• Note the four components of ‘not exams:’three projects and homework, each worth17 points. You may drop one or two ofthese ‘without penalty’ (see website andfuture email for details).Course Grade: A AB BCourse S c ore: 186.0 179.0 160.0BC C D140.0 120.0 100.0+ 6+ +ReadProject Assignmenton course website.Main points.• You may submit one, two or three projects.You m ay not submit both 1A and 1B.• Restriction. This is extremely important.I want to encourage you to submit teamprojects. If you submit one individual (i.e.not a team) project, there is no penalty.On a second individual projec t, you willlose one-half point. I wi l l not accept athird individual project. If you feel thatyou have a valid reason for not working ona team , email it to m e and I will considermaking an exc e pt ion for you.+ 7+ +ReadSome Useful Comments on Homework As-signments; Homework Assignments; and Home-work Assignments, by due date• Homework will be due most Fridays, inyour TA’s mailbox by 1:00 PM. Homeworkwill be collected the previous day in lec-ture.• Homework is graded plus or minus.• One minus is forgiven; after that you losetwo points for each minus.• One point will be given for submitting bothTA and faculty evaluat i ons at end of term.• To appeal a minus, send Wardrop an emailwith re ason(s). Don’t ask your TA.+ 8+ +Miscellaneous: Rea dCourse S y l l abusNote the existence ofFive Model Proje c ts; Honors assignment; Re-vised Student Study GuideYou should print and bring to cl assCourse NotesThere are three ‘Extra Exercises’ documentsthat provide homework /practice questions.There w il l be two ‘Prac tice Exam Questionsand Solutions’ documents, when ready.Web site for exact P-value for Fisher’s testwill be needed for projects 1A or 1B, but donot print it.Finally, if your book is missing Table A.7 onpage 656, you may pr int it from the coursewebsite.+ 9+ +Chapter 1: Comparative Studies (CS)Example: The Infidelity Study (IS) on page11; read it.There are four components t o a CS.1. The subjects (usually called units). Theseare the people, obj e c ts, tr ials, whateve r , fromwhich we obtain information.In the IS, the subjects are Therese’s 20 femalefriends.2. The response is obtained from each sub-ject. In the IS t he response is the answer yesor no. It i s a dichotomy giving us a dichoto-mous response.A response could have more t ha n two cate-gories or it could be a number . Multiple re-sponses are also possible.+ 10+ +We are interested in studies in which the re-sponse varies over subjects. We invent the no-tion of factors. A factor is a characteristic ofa subject that might influence (a strong word)or be associated wit h (weaker) the value ofthe response.In any CS there are many possible fact ors;a factor may be spe c i fic and relatively easyto dete r mine (e.g. marital status of subject)or vague and difficult to determine (e.g. sub-ject’s attitude towards marria ge).Of all possible factor s, the researcher selectsone factor to be the study factor. The studyfactor is the third com ponent of a compara-tive study.+ 11+ +In the IS, Therese chose t he study factor tobe the gender of the cheater (discuss otherpossible wor dings).The possible v alues of the st udy factor arecalled its levels.In the IS, the levels are: husband and wife.Very roughly speaking, the purpose of a CS isto invest iga te whether the level of t he studyfactor influences (that strong word aga i n) oris associated with (weaker, again) the va l ueof the response.In this course, we restric t att ention to studyfactors that ha v e exactly two levels. In Chap-ters 1–3 and 5–7 we rest r i c t att e nt ion to r e -sponses that are dichotomous. In Chapters12, 15 and 16 we consider numerical responses.In Cha pte r s 8 and 13 we consider studies withtwo responses.+ 12+ +Consider the IS again. The following questionis very important .Should eac h subject read and answer bothversions of the question, or only one?In other words, should we obtain a responsefor both leve l s of the study fa c tor or for onlyone?Discuss.In Chapt e r s 1–3, we restrict attenti on to stud-ies in which each subject is ‘exposed’ to ex-actly one level of the study factor .This r aises an obvious question:How do we assign subjects to levels?+ 13+ +The widely accepted answer is: by random-ization.Randomization dates back at le ast to Ben-jamin Franklin and studies of animal mag-netism, but statisticians tend to identify itspopularity with t he effort s of Sir Ronald Fisher(1890–1962), a statistician and genet i c i st .Randomization in the IS:• Assign the numbe r s 1, 2, . . . , 20 to thesubjects in a ny