Topic outline

  • General

    How to lie with statistics? (5cr)

    This is an advanced course in statistics. The course is aimed at master's students and doctoral students interested in statistics. Maturity in performing statistical analysis is needed and thus students should have taken at least one master's level statistics course before attending this course. There are no other prerequisites.

    Note that all the lectures are given on campus. Remote attendance is not possible. 

    Content

    During this course, students talk about typical problems and faults in sample selection, choices of location measure, graphical presentation of data, forming questionnaires, statistical testing, and regression analysis. Students are assumed to be familiar with these methods before attending the course. The focus will be on examples about using these methods wrongly --- either accidentally or on purpose --- and on improving statistical analyses.

    Intended learning outcomes

    The objectives are to learn to evaluate statistical analyses critically, to learn to avoid typical pitfalls in simple statistical analyses and to learn to improve presentation of the results obtained in statistical analyses. The objective is not to learn to lie with statistics, but to learn to spot if there is something fishy in a statistical analysis. The ultimate goal is to learn to tell the truth with statistics.

    Lectures and assignments

    The course consists of 12 lectures, lecture assignments, project work and study journal. Lectures are on Mondays and on Wednesdays from 10.15 to 12.00 in Y313. Majority of the lectures, instead of traditional lecturing, consists of discussions. Students find problematic data examples themselves and their findings and ideas for improving data analyses are discussed during the lectures. Students learn to defend their ideas and discoveries by conducting their project works where statistical analyses are used in justifying opinions and claims. Students write a study journal. In the study journals students may write down notes about their thoughts and reactions to what has been discussed. Writing and submitting a study journal on time is compulsory for completing the course!

    Lecture topics

    Lecture 1 (Mon 23.10, 10.15-12.00, Y313): Introduction --- We talk about the project works and about all the lecture assignment and about common errors and problems that are related to the lecture assignment topics. 

    Lecture 2 (Wed 25.10, 10.15-12.00, Y313): Getting ready for the project works

    Lecture 3 (Mon 30.10, 10.15-12.00, Y313): Sampling

    Lecture 4 (Wed 1.11, 10.15-12.00, Y313): Measures of location and scatter

    Lecture 5 (Mon 6.11, 10.15-12.00, Y313): Graphics

    Lecture 6 (Wed 8.11, 10.15-12.00, Y313): Testing 

    Lecture 7 (Mon 13.11, 10.15-12.00, Y313): Regression analysis

    Lecture 8 (Wed 15.11, 10.15-12.00, Y313): Questionnaires

    Lecture 9 (Mon 20.11, 10.15-12.00, Y313): Statistics related to timely topics (climate change, current conflicts,...)

    Lecture 10 (Wed 22.11, 10.15-12.00, Y313): Project work presentations

    Lecture 11 (Mon 27.11, 10.15-12.00, Y313): Project work presentations

    Lecture 12 (Wed 29.11, 10.15-12.00, Y313): Summary 

    Lecture assignments

    There is an assignment related to almost every lecture. Submit your assignments on time! Late submission is not possible! For Lecture 2, every student has to come up with at least two possible project work topics. On Lecture 2, we discuss about the topics and every student selects his/her topic or project group. Project work presentations take place on Lecture 10 and 11 so there is plenty of time to prepare for that. For Lecture 3, every student has to find one real data example or invent two examples that illustrate the problems related to biased samples. For Lecture 4, every student has to find one real data example or simulate two examples, where different location and/or scatter measures tell completely different stories. For Lecture 5, every student has to find one real data example or simulate two examples about misleading graphical presentation. For Lecture 6, every student has to find one real data example or simulate two examples, where results of statistical testing are false or misleading. For Lecture 7, every student has to find one real data example or simulate two examples, where regression analysis gives misleading results. For Lecture 8, every student has to find one real data example or write two made up examples of badly worded questionnaire questions or answer choices.  For Lecture 9, every student has to give one example or simulate two examples related to misleading interpretation, analysis or comparison of data that is related to some timely topic. For Lectures 10 and 11, every student has to submit presentation slides and a file, where the distribution of the workload related to the project work is explained.

    Examples and ways to improve statistical analyses are discussed during the lectures. 

    Study journal

    In order to complete the course, students have to keep a study journal (approximately 1/2 pages per lecture). Study journal must be submitted on time! Writing and submitting the study journal on time is compulsory for completing the course!

    Assessment

    The assessment is based on attendance, the lecture assignments, compulsory study journal and the project work. Writing and submitting the study journal on time is compulsory for completing the course! Final grade of the course is given by

    grade = 5 - 0.5ms - 0.5ma - 1md - 1ij,

    where ms is the number of the student's missed lectures, ma is the number of the student's missed lecture assignments, md is 1 if the student does not present his/her project work (and 0 if the student does present his/her project work), and ij is 1 if the student's study journal is incomplete (and 0 if the study journal is complete). The grades are rounded up to the closest integer. For example, grade 5 may be obtained by full attendance, completing all but one lecture assignments, submitting a complete study journal on time and presenting the project work. Grade 3 may be obtained by full attendance, completed lecture assignments, and submitting an incomplete study journal on time. Grade 1 may be obtained by attending all but 2 lectures, completing all but 2 lecture assignments, and submitting an incomplete study journal on time.

    Workload

    Majority of students' workload comes from independent assignments. Lecture assignments take on average 7*8 = 56 hours to complete. That includes finding representative data examples and observing problems in them. Writing the study journal takes on average 20-25 h as total. Working on the project work takes on average about 15-20 h. Attending the lectures takes as total 24 h.

    Learning materials

    Main materials for this course are the examples given by the students.