Topics in Econometrics
Study Board of Market and Management Anthropology, Economics, Mathematics-Economics, Environmental and Resource Management
Teaching language: English
EKA: B560005102
Censorship: Second examiner: None
Grading: 7-point grading scale
Offered in: Odense
Offered in: Autumn
Level: Master
Course ID: B560005101
ECTS value: 10
Date of Approval: 19-04-2022
Duration: 1 semester
Course ID
Course Title
Teaching language
ECTS value
Responsible study board
Study Board of Market and Management Anthropology, Economics, Mathematics-Economics, Environmental and Resource Management
Date of Approval
Course Responsible
Offered in
Level
Offered in
Duration
Recommended prerequisites
Familiarity with statistical analysis and regression model analysis. Prior knowledge in working with R.
Aim and purpose
Big data analytics part:
Big data analytics has emerged as the driving force behind critical business decisions and generally its role is growing within the characterization and understanding of individuals and of firms’ behavior. Advances in our ability to collect, store, and process different kinds of data from traditionally unconnected and unstructured sources enables us to answer massively complex, data-driven questions in ways that have never been possible before.
The main purpose of this part of the course is to prepare students to make sense of real-world phenomena and everyday activities by synthesizing and mining big data by uncovering relevant patterns, relationships, and trends with the intention of making better predictive analytics and informed decisions.
The course will provide the student with knowledge about the central methods related to generating, analyzing and processing big data. The students will have the skills to apply these methods to particular, empirical problems. And the course will give the students the competence to predict and evaluate expedient practices in related to a wide range of big data related problems as for instance:
- Businesses can predict future sales results by combining their customers’ preference profiles with website click-stream data, social network interactions, and location data.
- Police and fire departments collaborate with emergency managers to develop more accurate models of automotive and pedestrian traffic by using GPS data from cars, buses, taxis, and mobile phones.
- Emergency room physicians are able to reduce time to initial treatment and, as a result, patient mortality, by fusing aggregate patient histories with the results of up to the minute lab tests.
- Web scraping analytic tools applied to for example twitter can be used to measure real-time international conflict sentiment levels and to measure political tendencies and their movements prior to important elections etc.
- With the development of electronic health records, remote treatment, and the ability to share data online, we have an array of new healthcare solutions available. The use of mobile technologies to collect and distribute information might help significantly with the prevention and treatment of disease.
Multivariate methods part:
Multivariate methods have been developed within different scientific disciplines as a methodological toolbox to handle large data sets in a descriptive and hypothesis generating way, supplemented with formal tests of construct validity and significance.
This part of the course aims at providing the student with knowledge and skills in a number of exploratory, multivariate statistical techniques, including the ability to make a proper choice of method to a specific problem. The course has relevance for students aiming to perform advanced investigations based on large multivariate data, as competences in performing such analyses are obtained.
Multivariate methods are highly applicable within many social scientific disciplines as well as in daily practice, some examples:
- Marketing analyses: How can preferences of customers be identified from a survey? How can customer segments be identified?
- Political science: How can theoretical characteristics of voting behavior be identified using a survey? How can typical taxonomies of voters be revealed from a survey?
- International economics: How can we identify and separate between developed and underdeveloped countries using national account data?
- Public health: How can we identify patients who are potentially at risk of developing Type II Diabetes?
- Law: How can different characteristics of the Danish judges in the 20th century be exposed? Is it possible to provide a classification of such judges?
- Language: How are the relationships between use of digital media and school children’s motivation, competences and attitudes towards language learning?
Content
Throughout the course, the students combine theoretical knowledge with an extensive project work, where they get hands-on experience in accessing and working with big data and multivariate data analytics. The course has two main areas:
- Datafication and data collection: Methods to generate and structure data in an expedient and operable format
- Data analysis and data visualization: Methods to process, analyze and visualize the data within a big data and multivariate data method setup
Description of outcome - Knowledge
After taking the course, the student should be familiar with quantitative modelling and data analysis techniques within Big Data and multivariate methods.
Description of outcome - Skills
The student, should after the course be able to:
- Competently use R to solve the problems based on Big Data Analytics.
- Competently use R and related software to do analyses on large multivariate data sets
- Account for and discuss all three phases of working with big data and specific methods for generating, processing/analyzing and making predictions and informed decisions on the basis of Big Data and multivariate data.
- Identify and assess big data and multivariate data resources relevant in social sciences.
- Identify proper selection of methods for analyzing large multivariate data sets, including cluster analysis, factor analysis and discriminant analysis
Description of outcome - Competences
The student should be able to use quantitative modelling and data analysis techniques to the solution of real world problems in the social sciences, communicate findings, and effectively present results using data visualization techniques.
Literature
Examples:
- James, G., Witten, D., Hastie, T., Tibshirani, R (2013). An Introduction to Statistical Learning with Applications in R. Springer (can be downloaded free of charge from the SDU Library)
- Loebbecke, C. & Picot, A. (2015) Reflections on societal and business model transformation arising from digitization and big data analytics: A research agenda. Journal of Strategic Information Systems, 24, (3) 149-157
- Lycett, M. 2013. 'Datafication': making sense of (big) data in a complex world. European Journal of Information Systems, 22, (4) 381-386
- Sharma, S. (1996). Applied Multivariate Techniques. John Wiley & Sons, 1996.
Teaching Method
Workload
Scheduled classes:
3 lectures weekly for 15 weeks.
Workload:
The students' workload is expected to be distributed as follows:
Lectures - 45 hours
Preparation, lectures – 90 hours
Exercises – 85 hours
Assignment (written report) and exam – 50 hours
This corresponds to an average weekly workload of 13 hours during the semester, including the exam.
Examination regulations
Take-home assignment and an oral exam.
Name
Take-home assignment and an oral exam.
Timing
Exam: January
Reexam: February
Tests
Exam
Name
Exam
Form of examination
Take-home assignment with oral defence
Censorship
Second examiner: None
Grading
7-point grading scale
Identification
Student Identification Card - Date of birth
Language
English
Duration
Oral exam: 20 minutes.
Length
30-40 standard pages.
Examination aids
All exam aids allowed.
Assignment handover
The assignment is handed over in Digital Exam or Itslearning.
Assignment handin
Electronic hand-in via Digital Exam.
ECTS value
10
Additional information
The report is handed out during the semester.
The report is written in groups of 3-4 students (groups are formed by the course instructors). Smaller groups of 1-2 students require permission from the course instructors.
The oral examination takes its starting point in the report and a presentation hereof. The examination also includes supplementary questions on theoretical, methodological and, if relevant, practical topics associated with the submitted report.
The grading is an overall assessment of the report and the performance at the oral exam. The grading is based on the performance of the individual student compared to the learning goals.
For the reexam, a revised report is handed in before the oral exam.
Examination form at the reexam may be changed.
Exchange students will have the opportunity to take the oral exam online in January.
EKA
B560005102
External comment
Courses that are identical with former courses that are passed according to applied rules cannot be retaken.