QEM WS24_Wdh

Page 1

  • Copyright Notice

    • Any form of reproduction and dissemination requires explicit permission from the author.

    • Contact: Dr. Franziska Pfannerstill MSc, fpfannerstill.lba@fh-salzburg.ac.at

Page 2 - Descriptive Statistics Overview

  • Descriptive Statistics

    • Key focus on statistical measures of frequency and distribution.

    • Important terms include Percentiles, Quartiles, and various Statistical Methods.

  • Components Listed

    • Descriptive Statistics for the Population

    • Exploratory Data Analysis

    • Cross Tables

    • Measures of Central Tendency: Mean, Median, Mode

    • Variability: Standard Deviation, Variance, Range

    • Percentiles: Essential for understanding distribution.

Page 3 - Normal Distribution Testing

  • Normal Distribution Analysis

    • Tests for normality: Kolmogorov-Smirnov and Shapiro-Wilk tests used to assess data normality.

    • Statistical measures include degrees of freedom (df) and significance levels (Statistik).

Page 4 - IBM SPSS Data Editor Features

  • Data Editing Features

    • Sorting and transposing data

    • Identifying and validating unusual cases

    • Defining variable properties and attributes

Page 5 - Analysis Techniques Overview

  • Key Analysis Techniques

    • Differences:

      • Independent T-Test, Dependent T-Test, ANOVA

      • Non-parametric Tests: Mann-Whitney, Friedman’s ANOVA

      • Regression and Correlation methods such as Pearson’s r

Page 6 - Differences in Group Scores

  • Testing Differences

    • Focus on comparing means and variances between groups/ time points using tests such as T-Test or ANOVA.

    • Always report Mean and Standard Deviation.

Page 7 - Reporting Results Example

  • Statistical Reporting Template

    • Example structure for reporting differences among groups:

      • Includes M (Mean), SD (Standard deviation), T-Statistic, degrees of freedom (df), and p-values.

Page 8 - General Statistical Models

  • Comparative Models

    • Various statistical methods to compare means and proportions such as T-Tests and General Linear Models (GLM).

    • Incorporates both independent and dependent samples testing.

Page 9 - Mann-Whitney U Test Results

  • Mann-Whitney U Test Statistics

    • Provides specific values such as Mann-Whitney U, Wilcoxon W, and significance.

Page 10 - Test Assumptions Overview

  • Requirements for Testing Procedures

    • Covers conditions such as data distribution (normality) and homogeneity of variances for T-Tests and ANOVA.

Page 11 - ANOVA Assumptions

  • Anova Testing

    • Reiterates requirements: normal distribution and homogeneity of variance using Kolmogorov-Smirnov and Levene's Test.

Page 12 - Analyzing Differences and Relationships

  • Analytical Procedures

    • Focuses on correlation and regression analysis to establish relationships between variables.

Page 13 - Relationship Testing Techniques

  • Correlation and Chi-Square Analysis

    • Describes correlation coefficients and their significance levels using statistical measures.

Page 14 - Correlation Statistics Overview

  • Correlations and their Interpretation

    • Notes on significant bivariate correlations, including confidence intervals.

Page 15 - Summary of Relationships

  • Reporting Weak Relationships

    • Example on presenting correlational findings and Chi-Square results with relevant statistics.

Page 16 - Relationship Testing Requirements

  • Statistical Requirements for Relationships

    • Discusses conditions for Pearson’s r and contingency analysis affects correlation results.

Page 17 - Implications of Regression Analysis

  • Purpose of Regression

    • Explains the impact of independent variables on a dependent variable including significance of results.

Page 18 - Model Summary in Regression

  • Regression Model Example

    • Core statistics such as R Square to indicate variance explained by predictors.

Page 19 - Reporting Regression Results

  • Template for Regression Reporting

    • Includes structure for stating the contribution of predictors in influencing the dependent variable.

Page 20 - Regression Assumptions

  • Assumptions for Regression Analysis

    • Continuation of normality and variance homogeneity as fundamental requirements for meaningful results.