Statistics and Modeling in Environmental Studies

Statistics and modeling in environmental studies course takes basic statistical concepts and extends them to topics of special relevance in environmental studies. The course is intended to provide an insight what is needed to successfully analyze data in environmental sciences. The program emphasizes statistical modeling.

Methods of Teaching and Learning

Lectures, classes, class discussion, guided self study.

Lectures

1. Science, observations, and statistics. Research methods, data structures, measurement, and statistics. Frequency distributions.

2-3. Central tendency and the shape of distribution. Variability and measures of variability.

4. Probability and the normal distribution.

5-6. Hypothesis tests with t-statistics. The t-tests for two independent samples. The t-tests for two related samples.

7-8. Linear relationship. Linear regression model Testing the significance of the regression equation.

9-10. Measures of relationship. Pearson Correlation – interpreting the measure. Hypothesis tests with the Pearson Correlation. Other measures of relationship.

11-12. The logic of analysis of variance. Post hoc tests. The relationship between analysis of variance and t-tests.

13-14. Statistical models and their purposes. Statistical model formulas.

15. Confidence in statistical models. The logic of hypothesis testing.

16. Model and natural phenomenon. Modeling and models. Types of models used in environmental science.

17. Use of models in environmental science.

18-19. Structure of deterministic model. Parameters identification.

Boundary and initial conditions. Verification. Model quality measures.

20. Use of neural networks in environmental processes modeling.

Classes

1. Frequency distributions.

2-3. Central tendency and the shape of distribution. Variability and measures of variability.

4. Standardized distributions. Z-scores. Probability and the normal distribution.

5-7. Inferences about means and means differences. The logic of hypothesis testing. Hypothesis tests with t-statistics. The t-tests for two independent samples. The t-tests for two related samples.

8-9. Linear relationship. Linear regression model Testing the significance of the regression equation.

10-11. Measures of relationship. Pearson Correlation – interpreting the measure. Hypothesis tests with the Pearson Correlation. Other measures of relationship.

12-13. The logic of analysis of variance. Post hoc tests. The relationship between analysis of variance and t-tests.

14. Statistical model formulas. The logic of hypothesis testing of statistical models.

15-16. Universal equation of soil water movement and its use.

17-18. Models rainfall-discharge in basin.

19-20. Erosion modeling. Use of the USLE model.

21. Evapotranspiration process modeling.

22. Model of water movement in the soil-plant-atmosphere system.

23-24. Modeling bases of pollutant dissemination in environment.

25. Subject assessment.

Subject statistic

1. Number of hours and ECTS credits - compulsory subject Hours: 100; ECTS: 4

2. Number of hours and ECTS credits - facultative subject Hours: -; ECTS: -

3. Total number of hours and ECTS credits, a student must earn by direct contact with academics (lectures, classes, seminars....) Hours: 45; ECTS: 1,8

4. Total number of hours and ECTS credits, a student earns in the course of a practical nature, such as laboratory, field trips and design classes Hours: 0; ECTS: 0,0

5. Expected personal workload (without or with academics participation during consultations) necessary for realization of subject objectives. Hours: 55; ECTS: 2,2

Cohen P., Cohen J., West S.G., Aiken L.S., Applied Multiple Regression/Correlation Analysis for the Behavioral Sciences, Lawrence Erlbaum Associates Inc., New Jersey, 2002.

Freedman D.A., Statistical Models: Theory and Practice, Cambridge University Press, New York, 2005.

Gotelli N.J., Ellison A.M., A primer of ecological statistics, Sinauer Associates, Sunderland, 2004.

Krishnaiah P. R., Analysis of variance, Elsevier, Amsterdam, 1980.

Rees D. G., Essential statistics, Chapman & Hall, London, 1995.

Sokal R., Rohlf F.J., Biometry: the principles and practice of statistics in biological research, W. H. Freeman and Company, New York, 1998.

Knowledge

Student can prepare and analyze simple environmental data.

Student acquires knowledge about basic statistical methods.

Skills

Student can prepare data.

Student can analyze datasets.

Student can interpret outcome of the analysis.

Social competences

Student has the ability to gather and interpret relevant data.

Student can communicate information, ideas, and solutions.

Student is conscious of the necessity to enhance unceasingly knowledge.

Written examination.

Potential examination question topics will cover the entire subject curriculum.

Consisting of 6 questions from the entire range of the subject.

with four response options)

The marking system:

Four questions must be attempted; candidates will fail the written exam if three or more questions are not

attempted.

Each question is scored using a 11-point scale ranging from 0 through 10. Negative marking is not used.

The pass mark is 50%.

Grade E (2.0) Very low level of understanding , score below 50%

Grade D (3.0) Basic information about the lectures and lab labs, score 50-60%

Grade C (3.5) Ability to solve any problem at the intermediate level, score 61-70%

Grade B (4.0) Good understanding of the subject, ability to discuss different issues, score 71-80%

Grade B+ (4.5) Very good knowledge about the subject, score 81-90%

Grade A (5.0) Excellent understanding, full discussion, score more than 90%