Statistical Analysis

Garant předmětu:

Lecturer:

Tutor:

Supervisor:

Institute of Economic Studies

Synopsis:

Introduction to intermediate statistical methods. The course follows up on introductory statistic. Knowledge of basic statistical and probabilistic concepts is therefore expected.

Requirements:

Introductory statistics.

Syllabus of lectures:

1. Introduction. Repetition of introductory statistics I: Descriptive statistics - characteristics of location, variability and shape of distribution. Selected probabilistic distributions (discrete and continuous). Statistical inference: point and interval estimates, hypothesis testing.

2. Repetition of introductory statistics II: Hypothesis testing, Basic parametric and non-parametric tests, testing for conformance, independence, normality of distribution.

3. Analysis of variance (Anova). Validating the assumptions of the test: normality, within-group variance, one factor Anova and two factor Anova. Kruskal-Wallis test. Multi-dimensional Anova.

4. Correlation Analysis. Correlation coefficients: Pearson, Spearman, partial and multiple correlation, tetrachoric and biserial correlation. Hypothesis testing and confidence intervals for correlation coefficients.

5. Regression Analysis I. Correlation vs. causality. Simple linear regression model and other types of regression models. Testing hypothesis and construction of confidence intervals for regression coefficients.

6. Regression Analysis II. Post-estimation analysis and evaluation of quality of the model. Non-linear models, which can be transformed into linear models.

7. Regression Analysis III. Multidimensional linear model. Post-estimation analysis and evaluation of quality of the model.

8. Regression Analysis IV. Assumptions of the linear regression model and consequences of their violations. Residual analysis, testing for homoscedasticity, multicollinearity and autocorrelation.

9. Introduction to multivariate statistical methods: clustering methods and cluster analysis, hierarchical and nonhierarchical cluster analysis, principal component analysis.

10. Time series I: Introduction to time series analysis. Description of time series. Basic concepts.

11. Time series II: Basic characteristics of time series, Dynamic characteristics of time series, Decomposition of time series. Time series in economic analysis.

12. Time series III: Identifying the trend, Typical trend curves, choosing the right model for the time trend.

13. Time series IV: Moving averages. Smoothing.

Syllabus of tutorials:

1. Repetition of introductory statistics I: Introduction. Descriptive statistics. Selected probabilistic distributions (discrete and continuous). Introduction of Excel and Gretl.

2. Repetition of introductory statistics II: Statistical inference: point and interval estimates, hypothesis testing. Basic parametric and non-parametric tests.

3. Repetition of introductory statistics III: testing for conformance, independence, normality of distribution.

4. Analysis of variance (Anova). Validating the assumptions of the test: normality, within-group variance, one factor Anova and two factor Anova.

5. Non-parametric Kruskal-Wallis test and its alternatives for analysis of variance.

6. Correlation Analysis I. Correlation coefficients: Pearson, Spearman, partial and multiple correlation, tetrachoric and biserial correlation.

7. Correlation Analysis II. Hypothesis testing and confidence intervals for correlation coefficients.

8. Regression Analysis I. Simple linear regression model and other types of regression models. Estimating SLM in statistical software. Testing hypotheses about and constructing confidence intervals for regression coefficients.

9. Regression Analysis II. Post-estimation analysis and evaluation of quality of the model. Non-linear models, which can be transformed into linear models.

10. Regression Analysis III. Multidimensional linear model. Post-estimation analysis and evaluation of quality of the model.

11. Regression Analysis IV. Assumptions of the linear regression model and consequences of their violations. Residual analysis, testing for homoscedasticity, multicollinearity and autocorrelation.

12. Time series I: Introduction to time series analysis. Description of time series. Basic characteristics of time series.

13. Time series II: Identifying the trend, Typical trend curves, choosing the right model for the time trend.

Study Objective:

The aim of the course is to introduce students to single- and multidimensional statistical datasets, including analysis of correlation analysis, understanding causality, simple and multidimensional linear regression model and time-series models. Apart from theoretical background the students will also get the „hands-on“ experience: they will learn how to get the data, inspect the data and prepare them for analysis, process and analyze the data, evaluate their results and interpret them.

Study materials:

LEVINE, SZABAT, STEPHAN. Business Statistics: A First Course. New York: Pearson Global Edition, 2016. ISBN- 13 9780134196367.

STUDENMUND, A.H. Using econometrics: A practical guide. New York: Pearson Global Edition, 2017. ISBN: 978-01-3136773-9.

More could be added by the instructor throughout the semester. The instructor will always make sure that any additional material is available to the students either in electronic version or a hard-copy.

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Innovation Project Management od 2019/20 (compulsory course)
• IPM Compulsory Courses (compulsory course in the program)