ASOK22103U Advanced Quantitative Data Analysis

Volume 2023/2024
Education

Mandatory MA course 1. Semester

 

The course is closed for credit- and exchange students.

Content

On this course, the students are introduced to advanced statistical techniques that help them analyse complex data or answer causal questions. A specific feature of advanced quantitative analyses is that they deal with at least one of three challenges. Firstly, contemporary data often entail complex relations between observations that differ from how traditional surveys are set up. Examples are network data, spatial data, data of students who visit the same school or data with repeated observations of the same unit over time. Such relations between observations make the data more relevant and interesting from a sociological point of view, but violate core assumptions of standard statistical techniques taught on the Bachelor’s degree programme. Secondly, contemporary data, especially digital data, frequently come in semi-structured or unstructured formats unlike standardised survey or administrative data. This is especially true of natural-language text data, such as blog posts or newspaper articles. At the same time, the huge quantities of such data make hand-coding impractical. Thirdly, advanced quantitative analyses often aim to test causal claims entailed in sociological theories, which requires more sophisticated statistical techniques than the analyses of associations taught in the Bachelor’s degree programme.

 

The Advanced Quantitative Data Analysis course puts varying focus on one of these three challenges and introduces students to topics such as network analysis, spatial regression, multilevel modelling, panel data analysis, quantitative text analysis or causal identification strategies. As an important element, students learn to apply these techniques by analysing several different datasets in practical exercises throughout the semester. Gaining facility with handling these data is just as much a goal of the course as learning the advanced statistical techniques themselves.

Learning Outcome

On completion of the course, students will be able to:

Knowledge

  • account for different types of complex data.
  • account for methodologies that can be applied to complex data.
  • account for the relevance of these data and methods in sociological analyses.
  • account for the relation to other types of methodologies, including qualitative methods.
  • account for the prerequisites for what constitutes a causal connection.

 

Skills

  • handle complex data.
  • use specialised quantitative methods to analyse complex data, and also justify the choice of methodologies in relation to specific data types.
  • apply specialised quantitative methodologies to perform causal analyses.
  • reflect on the possibilities and limitations associated with the application of advanced methodologies for data analysis and causal conclusions in sociological research.
  • interpret and communicate the results/output of such analyses in relation to a given problem.

 

Competencies

  • evaluate critically and reflect on their empirical analysis in relation to a given problem in a way that demonstrates their understanding of the possibilities and limitations of the methodologies used, and
  • read and relate critically to sociological research literature that analyses complex data using quantitative methodologies.
  • translate and transfer their knowledge and skills for research and advisory purposes by being able to plan and perform analyses involving complex data.
  • understand and assess the use of the specific data analysis tools in other sociological studies and advise stakeholders wanting to use a plurality of complex data and methodologies.

Readings are comprised of peer-reviewed journal articles and one basic textbook.

Students should have a solid understanding of statistics, especially linear regression, as taught in the three statistics courses of the BA program, such as linear regression.
type of instruction is a combination of conventional lectures and practical exercises in standard statistical software, such as R or Stata. In connection with selected exercises, learning activities are organised where the students provide feedback to each other on their performance of the exercises. In addition, the students are asked to prepare feedback on another student’s performance. The feedback is provided in groups of three, where one student provides feedback, another receives the feedback and a third notes the content of the feedback and the recipient’s response (feedback triads).
  • Category
  • Hours
  • Lectures
  • 28
  • Preparation
  • 78
  • Project work
  • 100
  • Total
  • 206
Peer feedback (Students give each other feedback)

We will systematically use student peer-feedback on the three research proposals.

Credit
7,5 ECTS
Type of assessment
Portfolio, -
Type of assessment details
portfolio assignment, individually or in groups of max. four students.
A portfolio assignment is defined as a series of short assignments that address one or more set questions. The exam is based on the course syllabus. The assignments can be written as the course progresses. Provided students submit their assignments by the stipulated deadlines, feedback is offered during the course. Assignments can be reworked on the basis of the feedback. All of the assignments are submitted together for assessment at the end of the course.
The scope of the combined portfolio assignments is a maximum of 10 pages. For group assignments, an extra 5 pages are added per additional student.
Exam registration requirements

You need to be registered for the course.You need to be registered for the course.

Aid
All aids allowed

Policy on the Use of Generative AI Software and Large Language Models in Exams

The Department of Sociology prohibits the use of generative AI software and large language models (AI/LLMs), such as ChatGPT, for generating novel and creative content in written exams. However, students may use AI/LLMs to enhance the presentation of their own original work, such as text editing, argument validation, or improving statistical programming code. Students must disclose in an appendix if and how AI/LLMs were used; this appendix will not count toward the page limit of the exam. This policy is in place to ensure that students’ written exams accurately reflect their own knowledge and understanding of the material.

Marking scale
7-point grading scale
Censorship form
No external censorship
Exam period

Find more information on your study page at KUnet.

 

Re-exam

If the re-exam is taken during the ordinary exam period: see ordinary exam form

If the re-exam is taken during the re-exam period:

The re-exam consists of a written take-home assignment based on one or more set questions individually or in a group of max four students. The scope of the written take-home assignment is a maximum of 10 pages. For group assignments, an extra 5 pages are added per additional student.

 

Abovementioned applies to course registrations in Spring 2023 and onward.

If you have been registered for the course before Spring 2023, please write to the study administration: soc-studieadm@soc.ku.dk.

 

NOTE!

This is a mandatory course, and it is therefore only possible to take the exam during the fall, as the course is not offered in the spring

 

Criteria for exam assesment

Please see learning outcome