|
Lecturer(s)
|
-
Berec Luděk, doc. Ing. Dr.
-
Boukal David, prof. Ing. MgA. Ph.D.
-
Hais Martin, RNDr. Ph.D.
|
|
Course content
|
Topics of individual lectures and corresponding practicals: 1. Random event, concept of probability, definition, combinatorics, conditional and total probability, Bayes formula, independence of random events 2. Random variable, distribution function, probability density, numerical characteristics of random variables, examples 3. Random vector, marginal distribution, independence, numerical characteristics of random vectors, correlation, examples 4. Random process, types, properties and numerical characteristics of random processes autocorrelation, examples 5. Linear and non-linear regression with a single explanatory variable, their assumptions and interpretation, method of least squares; basic examples in Excel and R 6. Different approaches to multivariate regression, maximum likelihood methods, model selection using information criteria; examples in R 7. Distribution of the dependent variable and its impact on regression, generalized linear models (GLM); examples in R 8. Non-independent and repeated measures, mixed linear and generalized linear models (LMM, GLMM); examples in R 9. Basics of semiparametric regression, generalized additive models (GAM); examples in R 10. Interpolation and spatial interpolation 11. Geostatistics - spatial autocorrelation, theoretical and experimental semivariograms, kriging (GIS environment) 12. Time series, moving averages models (MA), autoregressive models (AR), autoregressive moving average models (ARMA) 13. Presentation of projects which are based on data processing using quantitative methods
|
|
Learning activities and teaching methods
|
Monologic (reading, lecture, briefing), Demonstration, Practical training
- Preparation for classes
- 28 hours per semester
- Semestral paper
- 8 hours per semester
- Class attendance
- 42 hours per semester
|
|
Learning outcomes
|
The course will introduce basic quantitative statistical methods, explain their main principles, and provide their applications for typical geographic data (e.g., demographic, meteorological and hydrological datasets). Common software Excel, R and ArcGIS will be used in practical tutorials. The graduate of the course will be able to analyze relevant data, interpret the results and use these methods in teaching geography at secondary schools. The course will also provide students with basic knowledge of data analysis required for their bachelor's or master's theses.
Student will understand basics of probability and mathematical statistics, selected regression models and basic geostatistical methods. Student will be able to apply this theoretical knowledge when working with real data. Student will be able to use these methods when teaching geography on a high school.
|
|
Prerequisites
|
Knowledge of high-school mathematics
|
|
Assessment methods and criteria
|
Oral examination, Seminar work
75% participation on practicals, small semestral project.
|
|
Recommended literature
|
-
Lepš, J., Šmilauer, P. Biostatistika. Č. Budějovice, Episteme, 2016. ISBN 978-80-7394-587-9.
-
Pekár, S., Brabec, M. Moderní analýza biologických dat Zobecněné lineární modely v prostředí R, Scientia, Praha 2009.
-
Pekár, S., Brabec, M. Moderní analýza biologických dat Zobecněné lineární modely v prostředí. Scientia, Praha, 2009.
-
S. Pekár, M. Brabec. Moderní analýza biologických dat. Nelineární modely v prostředí R, 3 díl. MUNI Press, Brno. 2019.
|