Introduction to Statistics (Winter term 2011/2012)

Course Content The application of statistical techniques is ubiquitous in quantitative neuroscience research. Knowledge of the basics of statistic is therefore essential for the correct understanding and interpretation of results published in the literature. Also, publishing and properly reporting the results of one's own research critically depend on statistical skills. This lecture will cover basic concepts important to experimentally working molecular neuroscientists, including descriptive statistics, hypothesis testing, and correlation and regression analysis.

The aim of the lecture is to provide a toolkit for basic statistical analysis and an understanding of important statistical concepts. At the end, students are able to apply the basic techniques to data and acquire additional knowledge on their own. They will also be able to critically assess the statistical techniques used in publications and be aware of the most common pitfalls in the use of statistics.

The course consists of lectures, exercises at home, computer exercises in class and a small project, where a statistical problem must be solved independently and presented afterwards.

Location and Time Wednesday, 9:30 am - 11.15 am, Lecture Hall 2, Graduate School
Important Information Download information sheet for details about times, exercises and grading.

On days with computer exercises, the course will be 9.30-12.00.

See also the course website at the Graduate School of Cellular & Molecular Neuroscience.

Lecture 1: Introduction & Descriptive Statistics pdf
Lecture 2: Probability theory and normal distribution pdf
Lecture 3: Error bars & t-tests pdf
Lecture 4: Two-sample, nonparametric, and paired sample testing pdf
Lecture 5: Linear regression and correlation pdf
Lecture 6: Analysis of Variance (ANOVA) pdf
Lecture 7: Experimental design and two-factor ANOVA pdf
Exercises New exercise sheet submission policy: return the exercise sheet on the day before next lecture (aka Tuesday), 8.30 am sharp, through the post box in the Graduate School or via email; from exercise sheets submitted late, we will deduct 1 point for every 2 hours of late submission
Date due Assignment Additional Downloads
Oct 11 pdf
Oct 18 pdf
Oct 25 pdf
Nov 8 pdf
Nov 22 pdf
Dec 13 pdf
Dec 20 pdf Samuels & Witmer, p. 326-331
Jan 17 pdf
Extra material
Chapter 1 of Samuels/Witmer
Some pages of chapter 2
Some pages of chapter 3.4
Some pages of chapter 6.1
Cummings et al
Some pages of chapter 6.4
Error bars for proportions
Matlab exercise 1
Alzheimer data file
Matlab exercise 2
Data file exercise 2
Jan. 18
Regression problem | data
ANOVA problem | data
Lecturer Philipp Berens and Alexander Ecker
University of Tuebingen BCCN CIN MPI