|
|
|
HDPO1231 - Computer science for social sciences
[1 Q. • 45 Th. • 8 ECTS - credits]
| Lecturer :
|
|
Huynen Philippe |
|
|
|
| Language of instruction :
|
|
French |
|
|
|
| Learning outcomes :
|
|
The objective of the course is to enable a multidisciplinary approach to the theoretical, methodological and technical aspects of creation, manipulation and analysis of quantitative data.
Within the framework of the statistical approach, the main methods of univariate and bivariate descriptive statistics will be discussed; a brief introduction to calculating probabilities will allow us to develop elements of statistical inference: sampling distributions, hypothesis tests (chi-square, Student-t).
As part of the IT approach, the foundations of a methodology of analysis and programming are central to the course. |
|
|
|
| Prerequisites :
|
|
None |
|
|
|
| Course contents :
|
|
Descriptive statistics:
This part of the course, after having discussed the concept of measurement levels of variables, examines different univariate and bivariate statistical procedures: the tabular and graphical representations of each of these procedures will be discussed in a presentation supported by the introduction of mathematical formulas specific to each analysis.
Computer science:
After a short introduction, the course will examine, through the concepts related to data construction, the notions of entity, attribute, data, variable, value, etc. The introduction to analysing and programming will follow, with notions such as algorithm, problem analysis, step by step description of the solution and formalisation of this approach. After a description of the syntax of the software that will be used (SPSS), we will successively study the following points:
Assignment and transformation instructions
Conditional structure;
Repetitive structure;
Procedures;
Selection, sorting and weighting of entities;
Data files and their reading/writing;
Variables and their documentation;
Data Analysis:
To address the notion of inference, a short methodological detour through the terms of population, sample frame and sample is required. This will allow us to address issues of sampling methods, representativeness, error and bias.
Basic notions of probabilities can intuitively introduce the concepts of random variables and the chi-square distribution. Hypothesis tests based on the chi-square and Student-t are finally approached and put into practice in analyses based on a file of actual data.
|
|
|
|
| Mode of delivery :
|
|
Each theoretical ex cathedra lecture is based on examples discussed with students. After the theoretical introduction, students are invited to solve problems by implementing the methods studied in class. The exercises are solved using the SPSS software, allowing the students to make use of their computer skills as well as their data analysis skills. The course is taught is a room equipped with microcomputers, which allows this flexibility between theoretical lectures and practical exercises. |
|
|
|
| Assessment methods and criteria :
|
|
The time spent on exercise solving on the computers should allow the students to continuously self-assess. The final assessment includes a three-hour written examination. This examination is - in part - an open book examination. The evaluation will assess on one hand the theoretical skills and on the other hand on ability to analyse and implement an IT solution and the capacity to correctly use tables of statistical results.
|
|
|
|
| Recommended or required reading :
|
|
Mentioned in the lecture notes
|
|
|
|
| Other information :
|
|
The lecture notes prepared by the teacher contain a structured and concise presentation of the course material, a syntactic summary and examination examples. Included with this, is a questionnaire and the data dictionary. Course notes are available at the copy service from the first week of class.
Finally, a data file is used to support the tutorials.
|
|
|
|
|
