Data Analysis and Mapping - JPM443

• Anglický název: Data Analysis and Mapping
• Zajišťuje: Katedra politologie (23-KP)
• Fakulta: Fakulta sociálních věd
• Platnost: od 2023
• Semestr: letní
• E-Kredity: 5
• Způsob provedení zkoušky: letní s.:
• Rozsah, examinace: letní s.:1/1, Zk [HT]
• Počet míst: neomezen / neurčen (10)
• Minimální obsazenost: neomezen
• 4EU+: ne
• Virtuální mobilita / počet míst pro virtuální mobilitu: ne
• Stav předmětu: vyučován
• Jazyk výuky: angličtina
• Způsob výuky: prezenční
• Způsob výuky: prezenční
• Další informace: https://moodle.cuni.cz/course/view.php?id=614
• Poznámka: předmět je možno zapsat mimo plán; povolen pro zápis po webu
• Garant: Mgr. Lukáš Hájek, M.A., Ph.D.
• Vyučující: Mgr. Lukáš Hájek, M.A., Ph.D.

Anotace

Poslední úprava: Mgr. Lukáš Hájek, M.A., Ph.D. (20.01.2024)

The course acquaints students with advanced tools in the field of data analysis and quantitative political science research, both at the theoretical and especially practical levels. Given that quantitative methods are becoming increasingly important in contemporary political science, their knowledge is a precious and essentially necessary skill.
After completing the seminar, students will be able to work passively with existing research based on quantitative methods and critically evaluate the results of such research. At the same time, they will be sufficiently experienced to actively use the basic statistical tools that are most used in modern political science. In addition, knowledge of the R programming environment will open up other possibilities for students to work with data and, in general, will undoubtedly increase their opportunities for employment.

Cíl předmětu

Poslední úprava: Mgr. Lukáš Hájek, M.A., Ph.D. (20.01.2024)

The course has the following objectives:

• to acquaint students with basic (description) and advanced (correlation, linear regression, nonlinear, and spatial analysis) tools of data analysis,
• to teach students to work with quantitative data using statistical software R.

Podmínky zakončení předmětu

Poslední úprava: Mgr. Lukáš Hájek, M.A., Ph.D. (08.02.2024)

It is strongly advised to attend all the seminars – nonetheless, attendance is not mandatory, so students do not have to apologise for an absence. 

The final grade for completing the seminar will be based on meeting the following criteria:

1. Homework (50 %) – Seminars 2–5 will be followed by homework assignments, which will recapitulate the procedures learned in the seminar. Groups of 2–3 students will be created for the joint performance of tasks. The aim is to support the cooperation of students and their mutual education. Each task will have a share of 15% in the final grade.
2. Final paper (50 %) – Each student will individually prepare a final practical work, which will be assigned in the second half of the semester. The aim of the work will be to test the knowledge of skills learned throughout the semester. The final work will consist of programmed research and also a short textual description of this analysis.

Importantly, late submissions will be penalised by decreasing the initial grade by 4% for each commenced hour of late submission. Every student that starts to fulfil the course’s requirements will be graded at the end of the semester. The course uses the following grading scale of the Faculty of Social Sciences:

• 90.01–100.00% (A – excellent),
• 80.01–90.00% (B – very good),
• 70.01–80.00% (C – good),
• 60.01–70.00% (D – satisfactory),
• 50.01–60.00% (E – sufficient),
• 0.00–50.00% (F – fail).

Possible plagiarism, including using artificial intelligence contrary to the recommendations of Charles University, will lead to a lower grade, failure to complete the course or disciplinary proceedings.

Literatura

Poslední úprava: Mgr. Lukáš Hájek, M.A., Ph.D. (20.01.2024)

The most important source in teaching the course is a textbook presenting the teaching of quantitative research methods using statistical software R:

• Field, A. P., Miles, J., & Field, Z. (2012). Discovering Statistics Using R. Sage.

In case of further interest, the following literature is recommended:

• Gerring, J., & Christenson, D. (2017). Applied Social Science Methodology: An Introductory Guide. Cambridge University Press.
• James, G., Witten, D., Hastie, T., & Tibshirani, R. (2017). An Introduction to Statistical Learning with Applications in R. Springer.
• Meys, J., & De Vries, A. (2012). R For Dummies. Wiley.
• Monogan III, J. E. (2015). Political Analysis Using R. Springer.
• Rumsey, D. (2007). Intermediate Statistics for Dummies. Wiley.

Metody výuky

Poslední úprava: Mgr. Lukáš Hájek, M.A., Ph.D. (23.01.2024)

The course is focused as much as possible on the practical use of quantitative methods of political science research. For this reason, teaching is conducted in the form of seminars. The seminars are held once every two weeks, in block form, always lasting 160 minutes. Only thanks to this teaching format it is possible to discuss the required material first theoretically and then immediately present it in a practical form. Therefore, the seminars themselves typically consist of an introductory presentation of the topic, which is followed by a practical exercise of the application of a specific analytical method with the help of real examples, data and calculations from the field of political science research. Therefore, especially in their practical part, seminars require the active participation of all students.

Students are required to prepare for each seminar by reading the required literature. Its knowledge is key to working during the seminar. The relevant literature will be available in electronic form in the Moodle information system as much as possible. Students are also expected to complete homework, which is used to practice the methods taught.

Access to literature and materials from seminars, assignments and assignments and group communication will take place through Moodle.

The work in the seminars will be conducted in the programming environment R. Its advantage is free availability and variability. A well-known disadvantage of the program is its relative complexity for beginners - but this is the price for a wide range of uses. Still, in the case of a thorough study, this initial complexity can be overcome relatively quickly.

R can be installed for free from the following source: https://www.r-project.org/. The easiest way to work with the R programming environment is within the graphical interface for R, which is (for example) RStudio. RStudio can be downloaded for free here: https://posit.co/. It is with this program that we will work in seminars, and all students must therefore have both R and RStudio installed on their laptops. Before the last seminar, it is also necessary to have LaTeX downloaded in the laptop as we will work with the software. 

In the seminars, students will be acquainted with all the commands that are needed to master R and apply quantitative methods for political science research - therefore, no prior knowledge of this programming environment is required. In addition, students are allowed to use the help of the above-mentioned literature or various websites, such as https://www.statmethods.net/, in seminars, but also for homework.

Sylabus

Poslední úprava: Mgr. Lukáš Hájek, M.A., Ph.D. (20.01.2024)

1. Introduction, Working in RStudio (February 21)

Students will be introduced to the content of the course. The R programming environment will be introduced, especially the individual types of information used; commands for saving and uploading data files, their sorting, editing and basic descriptive analysis; work with variables; creation of functions. Students will be introduced to the main advantages of R over other programs, as well as the pitfalls that may occur when working with it.

Reading:

• Field, A. P., Miles, J., & Field, Z. (2012). Discovering Statistics Using R. Sage. Chapter 3 – The R Environment.
• Gerring, J., & Christenson, D. (2017). Applied Social Science Methodology: An Introductory Guide. Cambridge University Press. Chapter 18 – Univariate Statistics.

2. Data Visualisation (March 6)

Students will be introduced to different ways of visualising data and outputs of quantitative analyses. Ways of data analysis will be revealed through their visualisation. Students will be acquainted with the mistakes that should not be committed in data visualisation. The creation of these visualisations will be practically practised in R.

Reading:

• Field, A. P., Miles, J., & Field, Z. (2012). Discovering Statistics Using R. Sage. Chapter 4 – Exploring data with graphs.
• Gerring, J., & Christenson, D. (2017). Applied Social Science Methodology: An Introductory Guide. Cambridge University Press. Chapter 19 – Probability Distributions.

3. Statistical Inference and Basic Instruments (March 20)

The logic of statistical inference will be described with an emphasis on meeting the relevant assumptions. Students will get acquainted with the principle of the central limit theorem and acquire the skills of constructing confidence intervals in R. Furthermore, correlation analysis will be presented, especially through situations suitable for its use, the specific form of application and the method of interpretation of results. Students will practically try statistical reasoning and basic analysis in the programming environment R (correlation analysis, t-test).

Reading:

• Field, A. P., Miles, J., & Field, Z. (2012). Discovering Statistics Using R. Sage. Chapter 2 – Everything You Ever Wanted to Know About Statistics (Well, Sort of).
• Gerring, J., & Christenson, D. (2017). Applied Social Science Methodology: An Introductory Guide. Cambridge University Press. Chapter 20 – Statistical Inference.

4. Linear Regression Analysis (April 3)

The method of regression analysis, which is the leading quantitative method in political science research, will be characterised. Emphasis will be placed on the assumptions of regression analysis, the analysis itself and the interpretation of its results. Students will practically try the application of regression analysis and presentation of results in tabular and graphical form in R. Students will be introduced to the technique of data transformation so that the classic regression analysis can be used.

Reading:

• Field, A. P., Miles, J., & Field, Z. (2012). Discovering Statistics Using R. Sage. Chapter 7 – Regression.
• Gerring, J., & Christenson, D. (2017). Applied Social Science Methodology: An Introductory Guide. Cambridge University Press. Chapter 22 – Regression.

5. Nonlinear Analysis (April 17)

In some specific cases, it is necessary to proceed to non-linear data analysis. Students will be introduced to logistic regression, especially the application conditions, the analysis itself and the presentation and interpretation of the results. Next, we will focus on the application of negative binomial analysis. The use of all tools will be practised in R.

Reading:

• Field, A. P., Miles, J., & Field, Z. (2012). Discovering Statistics Using R. Sage. Chapter 5 – Exploring Assumptions.
• Field, A. P., Miles, J., & Field, Z. (2012). Discovering Statistics Using R. Sage. Chapter 8 – Logistic Regression.

6. R Markdown, Mapping (May 15)

Maps are becoming increasingly important in data analysis. Students will therefore get acquainted with the role of spatial analysis in the field of political science research. Practical training will then be carried out using the R Markdown tool, which enables the direct export of analyzes in RStudio to commonly known text documents, PDF files or presentations. Students will learn about the practical use of this tool using the example of creating a regular report for the minister.

Reading:

• Lysek, J., Pánek, J., & Lebeda, T. (2020). Who are the voters and where are they? Using spatial statistics to analyse voting patterns in the parliamentary elections of the Czech Republic. Journal of Maps, 17(1), 33–38.

After the seminar:

• Xie, Y., Allaire, J. J., & Grolemund, G. (2018). R markdown: The definitive guide. CRC Press. Chapter 2 – Basics.

Vstupní požadavky

Poslední úprava: Mgr. Lukáš Hájek, M.A., Ph.D. (20.01.2024)

No special programming knowledge is required to enrol in the course. The teaching of the course is conducted in an intensive form with the requirement of high commitment of students, but only such a procedure will ensure the sufficient acquisition of quantitative methods in political science.