Breadcrumb Navigation
Tabs
About this course - learning outcomes
Statistical data analysis 1
First part of a compact hands-on block course over six half days on statistical data analysis and inference - from basic concepts to parameter estimation and hypothesis testing. The parts 1 and 2 can be attended independently (1+1 ECTS)
About
Statistical inference is the process of deducing properties of an underlying probability distribution (model/theory) by analysis of data. What does it mean when we quantify new measurements, claim findings like discoveries or exclusions of new phenomena? Extracting knowledge from data is about probability and uncertainties. Basic statistical inference knowledge and skills are essential for all professionals dealing with data analysis and interpretation.
This course serves students, researchers and professionals who wish to refresh and deepen their statistical inference skills with a modern peer level approach. Course material is offered as Jupyter notebooks for remote hands-on studies. In person sessions are used for summaries and discussions. You choose your software tool like Graphpad Prism, R or Python for application of the theoretical concepts in the project, but the notebook examples for the selfstudies are in Python.
Learning outcomes
First part of a compact hands-on block course over six half days on statistical data analysis and inference - from basic concepts to parameter estimation and hypothesis testing. The parts 1 and 2 can be attended independently (1+1 ECTS)
About
Statistical inference is the process of deducing properties of an underlying probability distribution (model/theory) by analysis of data. What does it mean when we quantify new measurements, claim findings like discoveries or exclusions of new phenomena? Extracting knowledge from data is about probability and uncertainties. Basic statistical inference knowledge and skills are essential for all professionals dealing with data analysis and interpretation.
This course serves students, researchers and professionals who wish to refresh and deepen their statistical inference skills with a modern peer level approach. Course material is offered as Jupyter notebooks for remote hands-on studies. In person sessions are used for summaries and discussions. You choose your software tool like Graphpad Prism, R or Python for application of the theoretical concepts in the project, but the notebook examples for the selfstudies are in Python.
Learning outcomes
- Manage and plot data with Jupyter notebooks
- Understand probability, typical probability density distributions (binomial, poisson, normal) and their moments
- Understand the meaning of common descriptive statistics (mean, median, variance, mode, skew, kurtosis, covariance, standard deviation, p-value, significance)
- Know statistical and systematic uncertainties
- Understand the meaning of uncertainties in terms of probability
- Perform regression and hypothesis testing with Python
- Perform and present a statistical data analysis project
- Students, researchers and professionals working with data
- Mathematics equivalent to an introductory course at university level
- Basic programming skills
- One may consider attending one of the ScITS crash courses on Python programming in advance
- Inverted classroom with online material and six half day discussion sessions. Project with (own) data. Poster presentation and peer assessment. Debrief and feedback session.
- Examples are in Python. The course uses Jupyter notebooks on a Jupyter hub. Installations on own computer are therefore not needed.
- 80% presence and completed project with presentation is awarded with a 4.0 (passed). Further points (grades 4.5-6.0) are given by students (40%) and lecturer (60%) based on the presentation.
- Certificate with recommended 1 ECTS for each part
- The coaches are local and external experts
Practical information (time, registration, location ...)
Time : 2020-01-14, 2020-01-15 and 2020-02-13 (presentation day), 09:00
Location : Mittelstrasse 43, Room 120, University of Bern
Training language: English
Participants : Max 24
Registration : Mandatory (use the Join button, one has to be logged into Ilias, button in the upper right corner)
Coaches : PD Dr. Sigve Haug
Fee: Free of charge
Certificate: Certificate with 1 ECTS (7 hours of presence + 7 hours selfstudy + ~14 hours project)
Location : Mittelstrasse 43, Room 120, University of Bern
Training language: English
Participants : Max 24
Registration : Mandatory (use the Join button, one has to be logged into Ilias, button in the upper right corner)
Coaches : PD Dr. Sigve Haug
Fee: Free of charge
Certificate: Certificate with 1 ECTS (7 hours of presence + 7 hours selfstudy + ~14 hours project)
Schedule and content
Course preparation
Work with Jupyter notebook on data handling and visualisation (about 3.5 hours)
Notebook will be distributed one week in advance
Optional: Attend Introduction to programming with Python (2020-01-13)
2020-01-14 Tuesday
09:00 Welcome and course overview
09:30 Discussion session on data and data handling
10:30 Break
11:00 Discussion session on data visualisation
12:00 Introduction to the next notebook
12:30 Lunch
13:30 Distant learning wih Jupyter notebook (about 3.5 hours)
2020-01-15 Wednesday
09:00 Discussion session on basic statistical concepts
10:30 Break
11:00 Discussion session on basic statistical concepts
12:00 Feedback and project work organisation
12:30 Lunch
Project work (14 hours)
2020-02-13 (Presentation / Assessment day) - either morning or afternoon
Preferably in teams of two: 15+15 Minutes per team (max 8 slides)
Peer evaluation with grades
If you don't have your own dataset, you may take one here: http://archive.ics.uci.edu/ml/datasets.php
(or somewhere else)
Work with Jupyter notebook on data handling and visualisation (about 3.5 hours)
Notebook will be distributed one week in advance
Optional: Attend Introduction to programming with Python (2020-01-13)
2020-01-14 Tuesday
09:00 Welcome and course overview
09:30 Discussion session on data and data handling
10:30 Break
11:00 Discussion session on data visualisation
12:00 Introduction to the next notebook
12:30 Lunch
13:30 Distant learning wih Jupyter notebook (about 3.5 hours)
2020-01-15 Wednesday
09:00 Discussion session on basic statistical concepts
10:30 Break
11:00 Discussion session on basic statistical concepts
12:00 Feedback and project work organisation
12:30 Lunch
Project work (14 hours)
2020-02-13 (Presentation / Assessment day) - either morning or afternoon
Preferably in teams of two: 15+15 Minutes per team (max 8 slides)
Peer evaluation with grades
If you don't have your own dataset, you may take one here: http://archive.ics.uci.edu/ml/datasets.php
(or somewhere else)
About ScITS
PD Dr. Sigve Haug
Sigve studied physics in Germany, Spain and Norway. He has been involved in neutrino physics experiments and high energy frontier experiments, often with main focus on the computing challenges related to the large and distributed data from these experiments. Today he is working for the Albert Einstein Center for fundamental Physics and the Mathematical Institute of the University of Bern where is leading the Science IT Support unit.
The Science IT Support is there to boost your research by supporting you solving computing challenges.
Your code doesn't compile, you need more computing power, more storage, a data mangament plan, help with some machine learning, a partner for your project and so on - drop an email, call or pass by our office.
Our wepgabe is scits.unibe.ch.
Sigve studied physics in Germany, Spain and Norway. He has been involved in neutrino physics experiments and high energy frontier experiments, often with main focus on the computing challenges related to the large and distributed data from these experiments. Today he is working for the Albert Einstein Center for fundamental Physics and the Mathematical Institute of the University of Bern where is leading the Science IT Support unit.
The Science IT Support is there to boost your research by supporting you solving computing challenges.
Your code doesn't compile, you need more computing power, more storage, a data mangament plan, help with some machine learning, a partner for your project and so on - drop an email, call or pass by our office.
Our wepgabe is scits.unibe.ch.