Statistics and Data Analysis

A course run within TIB PAN PhD School

Lectures

  1. Probability distributions and moments
  2. Central tendency and spread measures
  3. Dependence and correlations
  4. Data analyst's toolbox
  5. Hypothesis testing
  6. Design of experiments
  7. Consolidated standards for reporting trials
  8. Bootstrap
  9. Inductive method
  10. Regression as optimization

Practicals

  1. Central measures, code.
  2. Introduction to R: code, CSV file.
  3. Estimator properties: task, spreadsheet template; solution: code, filled table.
  4. Correlations: task; solution: Task 1 (scatterplots), Task 2 (correlations).
  5. Autocorrelation: task; solution: code.
  6. Image processing with robust statistics: task; snippet: code; solution: code.
  7. Fixing CSV formatting: task; solution: regular expressions.
  8. Statistical tests (simulations): task; solution: code.
  9. Statistical tests (CEC data): task; solution: code.
  10. Power analysis: task; solution: code.
  11. Formulating a statistical task: a case study on depression monitoring.
  12. Text processing: task; solution: code.
  13. Non-linear regression for missing data: task; solution: code.
  14. Computing the accuracy of quantiles using bootstrap task; solution: code.
  15. Designing an experiment to compare taste of two liquids task.

Projects (autumn 2023/2024)

The first task is individual while the remaining two are to be done in groups.

  1. Analysis of a paper describing an RCT according to the CONSORT 2010 Explanation and Elaboration document: task. Deadline 2023-12-19.
  2. Presentations about power analysis. Deadline 2024-01-19.
  3. Practical data analysis bike manoeuvre detections. Deadline for all groups 2024-02-02.

Projects (autumn 2022/2023)

The first task is individual while the remaining two are to be done in groups.

  1. Analysis of a paper describing an RCT according to the CONSORT 2010 Explanation and Elaboration document: task. Deadline 2022-11-24.
  2. Presentations about power analysis. Deadline 2023-01-09.
  3. Practical data analysis bike manoeuvre detections. Deadline for all groups 2023-02-02.

Projects (autumn 2021/2022)

All projects are supposed to be done in groups. Division into groups is given in the spreadsheet.

  1. Presentations about power analysis.
    • Group A: 2022-01-27
    • Group B: 2022-02-03
    • Group C: 2022-02-10
  2. Analysis of a paper describing an RCT according to the CONSORT 2010 Explanation and Elaboration document: task. Deadline for all groups 2022-02-03.
  3. Task: processing and analysis of diffraction images. Deadline for all groups 2022-02-10.

Grades: assessment of the projects and feedback.

Survey about the course

Projects (autumn 2020/2021)

  1. Exploration of COVID-19 spread data: task.
  2. Analysis of a paper describing an RCT according to the CONSORT 2010 Explanation and Elaboration document: task.
  3. Designing an experiment: task.

Old projects (spring 2019/2020)

  1. Task: processing and analysis of diffraction images; summary document.
  2. Task: stylometric analysis of feuilletons; dataset: archive.