Course catalogue doctoral education - VT24
-
Startpage
Ansökan kan ske mellan 2023-10-16 och 2023-11-15
Application closed
Print
Title | Practical Introduction to Multilevel Data Analysis: From Data Collection to Results Interpretation |
---|---|
Course number | 5531 |
Programme | 0-Inte del av forskarutbildningsprogram |
Language | English |
Credits | 3.0 |
Date | 2022-03-07 -- 2022-04-01 | Responsible KI department | Institutionen för lärande, informatik, management och etik |
Specific entry requirements | Knowledge of basic statistics (including correlations and regression analysis) and basic ability to use a statistical program, preferably R. Alternatively, familiarity with recommended preparatory reading: A. Field, J. Miles, and Z. Field “Discovering statistics using R” chapters 3 (the R environment), 4 (exploring data with graphs), 6 (correlation) and 7 (regression). |
Purpose of the course | The purpose of this course is to give doctoral students a possibility to acquire practical understanding and hands-on statistical skills required to use multilevel analysis in their research projects. The course also aims at inspiring the students to apply novel data collection designs in their research (e.g., hierarchical and cross-classified data, clustered randomized trials, collecting data with diary and experience sampling designs, using data from tracking and mobile devices). |
Intended learning outcomes | After completing this course doctoral students will be able to:
- Formulate a research question relevant to their research projects that can be answered by the multilevel data analysis. - Describe a range of data collection methods that are suitable for the multilevel data analysis. - Propose a multilevel model suitable for addressing a research question and fit the model using standard statistical software. - Describe and interpret the results of the multilevel data analysis. |
Contents of the course | The course covers those aspects of the multilevel data analysis that are necessary for doctoral students to successfully use this method in their research projects. This includes a complete introduction to selected topics covering both theoretical assumptions behind the method and basic explanation of statistical procedures used to estimate multilevel models. During the first two weeks of the course, students will discuss the research questions that may be answered by the multilevel data analysis, as well as the types of multilevel data designs and methods of data collection. During the third and fourth week, students will work with step-by-step tutorials for analyzing multilevel data using R programming language, and interpreting the results. |
Teaching and learning activities | The course will start with short presentations of students’ research projects, followed by a goal setting workshop. All the teaching materials, including pre-recorded lectures and tutorials, will be available on the course website for students to interact with. The course will be organized in the flipped classroom format, meaning that students will be required to get familiar with available materials before scheduled teaching time (e.g., seminars). The teaching of the course will be coaching-based, which means that the course leader will be available during Q&A seminars at least twice a week (depending on students’ needs). Time not scheduled for lectures, Q&A, and feedback seminars is reserved for students’ own work on the three examination assignments. One of these assignments will require students to run statistical analyses following the provided tutorials available for R and Jamovi (on request Mplus code can also be provided). Students will be able to individually decide whether they want to work on their own data or on an example dataset. Feedback on the assignments will be openly presented for all students’ benefit during the feedback seminars. |
Compulsory elements | The course is equivalent to two weeks of full-time study, but it will run for four weeks and will require students to devote on average 20 hours of work a week. About 10 hours will be scheduled, while remaining 10 hours will be dedicated to own work with flexible schedule. Presence is required during the introduction seminar as well as lectures, Q&A, and feedback seminars at least twice a week. Absences can be compensated for by scheduling additional consultation time with the instructor. |
Examination | The examination consists of two parts. During the first two weeks of the course, students will be required to submit two short assignments regarding an example research question, methods that can be used to collect data suitable for multilevel analyses, and the analysis strategy. During the fourth week of the course, students will be required to submit one longer assignment presenting the results of multilevel analyses that a student has conducted during the course. This assignment will be equivalent to the results section of a scientific article and will be graded pass or fail. |
Literature and other teaching material | Humphrey, S. E., & LeBreton, J. M. (Eds.). (2019). The Handbook of Multilevel Theory, Measurement, and Analysis (First Edition). American Psychological Association.
Tutorials, videos, and annotated code for R and other statistical programs will be linked on the course website (most practical information can be found online for free). |
Number of students | 8 - 20 |
Selection of students | Selection will be based on 1) the relevance of the course syllabus for the applicant's doctoral project (according to written motivation), 2) start date of doctoral studies (priority given to earlier start date) |
More information | The course will require part-time engagement (about 50%) for four weeks. Live sessions will be scheduled two or three times a week, usually in the middle of a day. All lectures, discussions, and seminars will be available for online participation. There will be three assignment deadlines that need to be met. |
Additional course leader | |
Latest course evaluation | Not available |
Course responsible |
Aleksandra Sjöström-Bujacz Institutionen för lärande, informatik, management och etik aleksandra.bujacz@ki.se |
Contact person | - |
![](/katalog/images/ki/postdoc.jpg)