Luchsinger Mathematics AG

Crash Course in Statistics for Neuroscience Center Zurich, University of Zurich, Summer 2016 [2.5 credit points]


If you miss more than 3 h (half day) of Course, you don't get any CP's!

Time:

Date Time Lecturer Subject Venue
June 27 0900-1200 & 1300-1600 Dr. Christoph Luchsinger Theory Y27 H35/36
June 28 0900-1200 & 1300-1600 Dr. Christoph Luchsinger Theory Y27 H35/36
June 30 0900-1200 Dr. Christoph Luchsinger Theory Y27 H35/36
July 1 0900-1200 Dr. Christoph Luchsinger Theory Y27 H35/36
July 4 0900-1200 Dr. Christoph Luchsinger Theory Y27 H35/36
July 4 1300-1600 Dr. Daniel Stekhoven and Dr. Adin Ross-Gillespie Introduction to R Y27 H35/36
July 5 0900-1200 & 1300-1600 Dr. Daniel Stekhoven and Dr. Adin Ross-Gillespie Performing statistical analyses in R Y27 H35/36
July 6 0900-1200 & 1300-1600 Dr. Daniel Stekhoven and Dr. Adin Ross-Gillespie Diagnosis, visualisation & workshop Y27 H35/36

Lecturers:

Aims of the Course: Participants...

  1. have basic knowledge of probability theory
  2. can solve simple statistical problems without help
  3. can reconstruct the train of thought of correct solutions to more complicated problems and adapt them to their own problems with same structure
  4. have basic knowledge of statistics, enabling them to familiarize themselves with more advanced topics in the literature given below
  5. have R-Documentation to methods treated (no complete introduction!)
  6. see limitations of statistical reasoning

We are going to omit (among other topics): descriptive statistics (important, read yourself, too time-consuming); Design of Experiments (important, too individual, too time-consuming, we touch some of it); Quality control

The way I teach: A script is online (below). Please print it out. Therefore you are not going to lose time just copying from the blackboard or OHP. Instead, we are going to solve many problems in class. For example, I will first motivate the term of "Mean" (or "Variance"), then give the definition, then I solve 1 or 2 problems using this new statistical concept, then maybe one problem will be solved together in class, then you have to solve some problems yourself. Finally, at the end of the day, there is time to solve additional exercises with me being present in the class room. Teaching will be very interactively. I will omit almost all proofs!
The binomial distribution (a discrete random variable) and the normal distribution (a continuous random variable) will be treated broadly. We will present the theory of chapter 6 and 7 using the binomial and normal random variables.
Please bring light pens (Leuchtstifte) in the following three colours to the course: Blue="Structure", Red="Danger" and Green="important, learn by heart".

Contents / Downloads (Script):

First 5 chapters are a necessary, theoretical and mathematical basis; data and applications follow in chapters 6 - 10.

  1. Probability
  2. Random Variables
  3. Expectations
  4. Selected Probability Distributions; please also visit Online-Demos Distributions
  5. Law of Large Numbers

    Summary chapters 1-5
    Solutions to Exercises Chapters 1-5

  6. Estimators and Confidence Intervals
  7. Test theory (incl 1 way ANOVA)
  8. Regression

Prerequisits:

Administration/Registration: Heidi Gauss, hgauss@neuroscience.uzh.ch, Tel. 044 635 33 82

Consulting hours: breaks; follow-up treatment (only topics treated in this course) via E-Mail and phone.

Literature: Script and in particular the following books:

Links:


Webmaster: Dr. Christoph Luchsinger / chris@all-acad.com