NFYK15002U Advanced Methods in Applied Statistics
MSc Programme in Physics
MSc Programme in Environmental Science
The course will offer the practical knowledge and hands-on experience in computational analysis of data in all frontier physics research, with particular relevance for particle physics, astrophysics, and cosmology. Lectures, examples, and exercises will be administered via computer demonstration, mainly using the python or C/C++ coding languages.
A subset of the course will focus on the analysis features relevant to the specific graduate research topics and interests of the enrolled students.
- Be familiar with multiple machine learning algorithms and multivariate analysis techniques
- Understand the biases and impacts of various confidence interval methods
- Understand Bayesian and Frequentist approaches to interpreting data and the limits of assumed priors
- Minimization techniques such as hill climbing methods, flocking algorithms, and simulated annealing
- Maximum Likelihood fitting
- Construction of Confidence Intervals (Poisson, Feldman-Cousins, a priori and a posteriori p-values, etc.)
- Apply computational methods to de-noise data and images
- Code a chi-squared function in the language of the students preference (Python, C/C++, Ruby, JAVA, R, etc)
- Creation and usage of spline functions
- Application of Kernel Density Estimators
This course will provide the advanced computational tools for data analysis related to manuscript preparation, thesis writing, and understanding the methodology and statistical relevance of results in journal articles. The students will have enhanced general coding skills useful in the both academia and industry.
See Absalon for final course material. The following is an example of expected course litterature.
“Statistical Data Analysis” by G. Cowan
Class lecture notes and links to scholarly articles will be posted online.
- The ability and experience to install external software packages, e.g. the MultiNest Bayesian inference package or “emcee” Markov Chain Monte Carlo sampler.
- Completion of “Applied Statistics: From Data to Results”, or equivalent, is strongly encouraged but not strictly required.
There will be an introduction the week before the course begins to address software requirements and any additional course logistics.
- 7,5 ECTS
- Type of assessment
- Continuous assessment, throughout the courseWritten assignment, 28 hoursAssessment will be based on:
1) Continuous evaluation consisting of:
- An in-class short oral presentation (10%)
- Graded problem sets and project(s) centering around the coding, implementation, and execution of a statistical method (50%)
2) Written assignment:
- Take home final exam (40%)
Each part of the exam must be passed separately in order to pass the course.
It is possible to some extent to arrange a different weight in individual cases in agreement between the student and course responsible, if this can be justified. Agreement must be arranged at least 1-week prior to take home final exam date.
- All aids allowed
- Marking scale
- 7-point grading scale
- Censorship form
- No external censorship
More internal examiners
Only the part of the exam (continuous or written assignment) that was not passed can be re-taken. Points from the part of the exam (if any) that was passed, are carried over and count with the same weight as at the regular exam.
If the continuous evaluation was not passed, a number of problem sets can be re-submitted no later than two days before the re-exam.
If the written assignment was not passed, the students should do a new take home exam.
Criteria for exam assesment
see learning outcome
- Practical exercises
- Project work