Presentation and Data Analysis
Bachelor's Degree II - ICS
by BAHLOUL Farouk (to Bartek Szopka, with all my respects)
On this page, you will find the Summary of the Module on presentation and data analysis, along with some annotations and indications. By clicking on each BLOCK of content, you will get more details about the components of each lesson.
Introductory paragraphs provide an overview of the subject matter of each Block. They should be considered along with the objectives and the key concepts related to each Lesson. Finally, videos from various sources offer a different perspective to help you gain another viewpoint on the material taught.
The detailed content is available at the beginning of each session of the teaching Blocks as well as in theversion of the Support Blocks, downloadable at the end of each teaching session.
If you are viewing this page on a smartphone or tablet screen, you can swipe through the slides or use the controls at the bottom of your screen.
* BLOCK I Data Analysis in Social Sciences
| Lessons I, II:
Introduction to Research in Social Sciences
Introduction to Data Analysis
In Brief ....
Research in the humanities and social sciences is a process aimed at understanding within the epistemological sense of the term.
This process is dimensional; it is nomothetic and ideographic, rooted in a long tradition of thought. Our goal is to capture this process and understand its significance in science, this product of human history as A. Chalmers liked to say.
Sampling is the process of defining who can be studied.
We will see that this step is directly related to the analysis of the data that will be collected later. Each research logic imposes a type of sampling, so it will be the responsibility of this chapter to discuss the implications of such a procedure in depth.
Objectives ...
Interview with Dr. Philip Kitcher
- Introduce the reader to the questions and issues that outline the scope of research in social sciences, its specificity, and authenticity;
- Understand the context of research in the humanities and social sciences and its methods;
- Describe the stages of research in the humanities and social sciences and the role of data analysis within it.
Concepts
Science, Academic Research, Theory, Inquiry, Analysis, Report..
Objectives ...
Data Geule - Réseaux sociaux : Flux à lier
- Know the types of sampling in qualitative or quantitative research;
- Understand the different types of sampling (probabilistic and non-probabilistic), as well as considerations related to sample size;
- Understand the advantages and limitations of using sampling in research in the humanities and social sciences.
Concepts
Sample, sampling, sampling plan, sample size, probabilistic sampling, non-probabilistic sampling.
** BLOCK II Descriptive Analysis & Probabilities
| Lessons I, II, III:
Univariate Descriptive Analysis
Descriptive Bivariate Analysis
Finite Probabilities & Combinatorial Analysis
In Brief ....
Data analysis focuses on the characteristics or values of a statistical unit. The sum of these analyses allows the researcher to make an informed decision about their research hypotheses.
Statistics rely on a language of indices to summarize the essential information contained in a dataset. Statistical indices provide an overview of the studied data.
Objectives ...
Statistics, Descriptive and Inferential
- Understand the basic concepts of statistical jargon: the language of statistics helps grasp the fundamentals of data analysis, so it is important to understand its full content;
- Define statistical indices of central tendency, position, and dispersion, interpret the results of these indices, and know when to use them;
- Learn how to write a report on the results of univariate descriptive analysis.
Concepts
Statistics, Population, Individual, Statistical Unit, Character, Modality, Value, Measurement Scales, Mode, Median, Mean, Range, Variance, Standard Deviation, Percentiles, Deciles, Quartiles.
In Brief ....
Bivariate analysis, as the name suggests, involves examining the potential relationship between two variables. In this Block, we will see how to analyze hypotheses that relate two variables (depending on their measurement scale).
The goal of bivariate analysis is to confirm (or not) the analyzed hypotheses, so we will also examine the nature of hypotheses in bivariate analysis.
Finally, a report on bivariate analysis has its own writing rules. We will revisit this essential work to highlight the depth of insights gained from the analyzed data.
Objectives ...
Foundations of Bivariate Analysis
- Identify the types of relationships between variables;
- Know how to construct and analyze a contingency table and a scatter plot;
- Study the correlation between numerical variables; understand the concept of regression in bivariate analysis.
Concepts
Contingency Table, Correlation and Regression, Trend Tests.
| Probabilities and Combinatorial Analysis
In Brief ....
Inferential analyses rely on probability reasoning; probabilities are used to model uncertain situations, where the outcome is not known in advance but all possible outcomes can be enumerated. Combinatorial analysis is often used to calculate probabilities in situations with a finite number of possible outcomes.
Objectives ...
Probabilities and Combinatorial Analysis
- Define probabilities, combinatorial analysis, their objectives, and their scope;
- Aid in decision-making;
- Understand and predict random phenomena.
Concepts
Sample Space, Event, Probability of an Event, Mutually Exclusive Events, Independent Events, Probability Law, Random Variable, Expected Value; Factorial, Permutation, Combination, Arrangement, Additive Principle, Multiplicative Principle.
*** BLOCK III Statistical Inference
| Lessons I, II, III, IV, V, VI :
Sampling and Estimation
The t-test
The \(\chi^2\) test
Analysis of Variance
Correlation & Linear Regression
Non-parametric tests
In Brief ....
Statistical inference is a branch of statistics that allows conclusions about an entire population to be drawn from a representative sample. A parameter is a numerical value that characterizes a specific aspect of the population, while a statistic is a value calculated from the sample, used to estimate this parameter. Estimation involves using an estimator to obtain an approximation of the unknown parameter.
In hypothesis testing, an assertion about a population parameter is evaluated based on sampled data. The power of the test measures the probability of detecting a true effect. The p-value quantifies the strength of evidence against the null hypothesis.
Sample variance and standard error are measures of the variability of estimates around the true parameter, while risk and bias assess the reliability of conclusions drawn from statistical inference.
Objectives ...
Statistical Inference
- Familiarize the reader with the fundamental objectives of statistical inference: Population, Sample, Parameter, Statistic, Estimation, Hypothesis Testing;
- Introduce the student to the themes of Confidence Interval and Non-parametric Tests to ensure coherent analysis;
- Thoroughly address the construction, reconstruction, and implementation of a report based on a set of quantitative survey results.
Concepts
Population, Sample, Parameter, Statistic, Estimation, Estimator, Confidence Interval, Hypothesis Test, Significance Level, Type I and Type II Errors, Test Power, p-value, Test Statistic, Sampling Distribution, Prediction Interval, Sample Variance, Standard Error, Risk and Bias