Statistical analysis of experimental data

physics

Lecture addressed to students participating in an academic course on Particle Physics and planning to obtain Master’s degree. It is also open to other interested students - knowledge of particle physics is not required. Courses in an elementary calculus and obligatory laboratory practical on the Bachelor’s level are treated as prerequisite.

Classroom

Course deals with the basic concepts of probability and methods of statistical analysis of data as encountered in the elementary particle physics.

1. Probability

2. Basic probability distributions and their properties

3. Measurement uncertainties

4. Monte Carlo Methods

5. Parameter Inference

6. Maximum likelihood

7. Least square method

8. Test of hypothesis

9. Significance of Evidence

10. Confidence interwals and limit extraction

11. Multivariate analysis methods

12. Introduction to Machine Learning

1. G. Bohm i G. Zech, Introduction to Statistics and Data Analysis for Physicsts, Verlag Deutsches Elektronen-Synchrotron, 3rd edition [free access: https://bib-pubdb1.desy.de/record/389738];

2. L. Lista, Statistical Methods for Data Analysis in Particle Physics, Springer, 2017;

3. G. Cowan, Statistical Data Analysis, Oxford University Press, Oxford, 1998;

4. M. Bonamente, Statistics and Analysis of Scientific Data, Springer 2017;

5. S. Brandt, Data Analysis: Statistical and Computational Methods for Scientists and Engineers, Springer 2014;

6. C. W. Fabjan, H. Schopper (eds.), Particle Physics Reference Library, Vol. 2, Chapter 15 [free access: https://link.springer.com/chapter/10.1007/978-3-030-35318-6_15];

7. Particle Data Group: Review of particle physics: reviews, tables, and plots - Mathematical tools [free access: http://pdg.web.cern.ch/pdg/pdg.html]

Knowledge

Student knows basic methods of statistical analyses of data

Student understands limitations of these methods

Skills

Student identifies problems of data analyses in terms of statistical mathematics

Student is able to implement basic methods of statistical analyses of data in simple cases

Student knows how to interpret results of such analyses

Attitude

Student apreciates importance of deep and thorough analysis problems before drawing conclusions and taking decisions

Assessment: based on home exercises performed during the semester and the final written exam - minimum of 50% of points collected from exercises and exam (with same weights) is required to pass. Assessment in September will rest on written examination only and will require a candidate to gain minimum 50% of points.

none