## Statistical Experiment Design – Design of Experiment (DoE)

### Establishment of research hypotheses

#### What is the population?

- Scale levels: Nominal scale, Ordinal scale, Interval scale, Ratio scale
- Development of experimental plans: screening plans (complete experimental plans, partial factor plans), response surface plans
- Conception of surveys / questionnaires / tests
- Specify sample size / number of subjects / number of groups & control groups
- Conducting surveys / online surveys / experiments / experiments
- Save test results
- Documentation / logging of test results
- Cleanup of data / incorrect data
- Technical implementation of online surveys
- Import / export of data
- Convert data / various file formats
- Recognize first trends with descriptive / descriptive stat.
- Representation of data: histogram, boxplot, scatterplot, pie chart, Q-Q plot, etc.

## Absolute and relative frequencies

Calculation of measures / position parameters: arithmetic mean, median, mode, sums of squares, standard errors, variance, empirical variance, span, quantiles, empirical covariance, correlation coefficient, etc.

- Linear regression
- cluster analysis
- Data Analysis / Data Evaluation (Inductive Stat.)
- Formulate research hypotheses as null hypotheses and alternative hypotheses
- Set significance level
- Choice of statistical test
- Verification of distribution assumptions (eg, normal distribution assumption): chi2 fit test, Kolmogorov-Smirnow test, Shapiro-Wilk test, Anderson-Darling test, etc.
- Confidence intervals / Confidence areas / Confidence intervals / Expected ranges
- Decision rule: interpretation of test size / test statistic, critical value / p-value
- Power analysis, test strength
- Parametric hypothesis tests: t-test, z-test, F-test, chi2 homogeneity test, etc.
- Nonparametric Hypothesis Tests: Wilcoxon Mann Whitney Test, Kruskal Wallis Test, Wilcoxon Sign Rank Test, Friedman Test, etc.
- One-Factor Variance Analysis and Multi-Variance Analysis of Variance (ANOVA), Multivariate Analysis of Variance (MANOVA)
- Correlation, partial correlation, pseudo-correlation, rank correlation, Pearson chi2 test
- Linear Regression, Nonlinear Regression, Logistic Regression, Multiple Regression, Moderator Analysis, Mediator Analysis, Generalized Linear Models, Multi-Level Analysis, Path Analysis / Structural Equation Models
- Factor analysis / main axis model / main component model, correspondence analysis
- Time series analysis
- Statistical Modeling
- Basics / background knowledge about stochastics
- Combinatorics, Bernoulli chains
- Random variables, events, probabilities, conditional probabilities, z-values, tabulation of probabilities
- Statistical independence and dependence
- Discrete distributions: binomial distribution, uniform distribution, Poisson distribution
- Continuous distributions: normal distribution, exponential distribution
- Test distributions: distribution, distribution, F distribution

### Law of large numbers and the meaning of the central limit theorem

### Courses for Statistical Data Analysis with SPSS, R, Stata, SAS & Excel

If you would like to learn how to deal with data analysis software more frequently or perhaps “only” for the thesis (bachelor thesis, master thesis, diploma thesis, project work) or dissertation, you will find the right partners with Mentorium. For the most commonly used software packages, we offer courses for SPSS, R, Stata, SAS, STATISTICA and MS Excel to students, doctoral students, as well as employees of companies, institutes, government agencies and higher education institutions. Either case related, e.g. Calculations, location parameters or tests and corresponding visualizations with the respective data analysis software performed or determined, or it is systematically learned how to handle the respective software. Our experts lead courses in:

- SPSS
- Stata
- SAS
- STATISTICA
- MS Excel
- Course Forms – Data Analysis Software Courses
- Group courses (small groups)
- Single course (very individual one-to-one course)
- Online Courses (Most Used)