Course: Applied non spatial statistical analysis

Georgios Papadopoulos

Upon completion of this course, the student is expected to be able to:

  • translate a research question into a statistical hypothesis or/and  into a regression model
  • apply estimation and testing methods  in order to make data-based decisions
  • model and investigate relationships between two or more variables within a regression framework
  • apply checks for method’s assumptions
  • comprehend and interpret correctly the statistical significance
  • interpret results correctly, effectively, and in context without relying on statistical jargon
  • comprehend the notion of uncertainty which is always contained in statistical inference critique data-based claims and evaluate data-based decisions
  • complete a research project that employs simple statistical inference
  • use statistical software to summarize data numerically and visually, and to perform data analysis
  • comply to ethical issues.

Course description:

1)   Statistical packages (how to use).

2) Brief overview of (a) the principles of statistical inference and (b) inference about means, proportions and variances (confidence intervals and hypothesis tests for a population mean, proportion or variance and for comparing two population means, proportions or variances; Analysis of variance and multiple comparisons tests ; Goodness-of-fit test; Chi-Square test of independence).

3) How to apply checks for method’s assumptions (tests for Normality, tests for comparing variances, normal probability plots, residuals plots, etc.).

4) Non-parametric tests (Sign test, Mann-Whitney test, Wilcoxon test, Kruskal-Wallis test, Friedman test, etc.).

5) Regression analysis (simple linear regression and correlation; multiple regression; logistic regression).

6) Diagnostic tools for checking the regression assumptions (residuals plots, etc.); data transformations.

Teaching aids: e-books