Data Acquisition and Statistical Analysis

Code:

EMG0025

Acronym:

AAD

Keywords
Classification	Keyword
OFICIAL	Physical Sciences (Mathematics)

Instance: 2024/2025 - 1S

Active?	Yes
Responsible unit:	Mining Engineering Department
Course/CS Responsible:	Bachelor in Mining and Geo-Environmental Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
L.EMG	6	Plano de estudos oficial a partir de 2008/09	3	-	6	52	162

Teaching language

Portuguese

Objectives

This course unit have four main aims:
- to acquire the fundamental technical notions and be capable of handling them;
- to be able to choose the adequate statistical or proto-statistical object considering the particular structure of information;
- to understand the algorithms used in data analysis and be capable of developing them using a simple spreadsheet;
- to understand the relationship between data analysis and traditional empirical research and the subjectivity related to the lack of incorporation of the studied phenomena in a reasoned and comprehensive scientific theory.

Learning outcomes and competences

This course unit have four main aims:
- to acquire the fundamental technical notions and be capable of handling them;
- to be able to choose the adequate statistical or proto-statistical object considering the particular structure of information;
- to understand the algorithms used in data analysis and be capable of developing them using a simple spreadsheet;
- to understand the relationship between data analysis and traditional empirical research and the subjectivity related to the lack of incorporation of the studied phenomena in a reasoned and comprehensive scientific theory.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Previous knowledge:
Probabilities: mathematical expectation, moments, means, characteristic functions, characterization of a distribution using moments, including joint distributions; random convergence and normal law.
Statistics: Underlying principles of estimation theory, Student test;
Matrix Algebra: Matrix multiplication, inversion, determination of eigenvalues, eigenvectors and singular values

Program

The course unit of Data Acquisition and Analysis can be briefly characterized by the introduction of statistical and proto-statistical tools which enable the approach to the:
- Phenomena of qualitative variables expressed in nominal and ordinal scales, being thus necessary training in nonparametric statistics and distribution statistics;
- Sequential data analysis, involving Regression Analysis and stochastic successions and Markov chains;
- Interpretation of experimental results and research planning with the corresponding techniques of maximisation of experimental systematic variance, control of systematic variance and minimisation of error variance, which requires training in Analysis of Variance and some of its applications;
- Complex data analysis expressed by multiple variables, occasionally expressed in different measurement systems, which requires training in multivariable statistics.

The fulfilment of the above mentioned aims is not an easy or innocuous task, since they are not entirely coherent in a practical and intrinsic theoretical point of view. Besides, they comprise subject matters which encompass autonomous theoretical subjects, being that justified by the pragmatism of university training.
It is in fact not possible, at risk of alienating the reality, to create a Masters programme only composed by course units based on a self-constituted theoretical basis. However, an intrinsic coherence between the subject matters should at least always be sought. For that reason, the subject matters of this course unit were organized in coherent groups, from a doctrinal or thematic point of view. The suggested organisation is as follows:
- Interpretation and Research Planning: tests planning and their critical interpretation (Univariate analysis of variance);
- Nonparametric statistics: parametric and nonparametric tests; fundamental concepts: null hypothesis, significance level, sample size, sampling distribution, rejection region, statistical model and measurement scales: One sample tests: binomial, chi-square and Kolmogorov-Smirnov distributions; Run tests; Tests of equality: Wilcoxon-Mann-Whitey; Measures of association (Spearman and Kendall);
- Sequential data analysis and experimental data adjustment: analysis of univariate linear regression, linearization and multivariate and stochastic successions (Markov chain);
- Brief introduction to multivariate data analysis: analysis of the main components, analysis of factors (Q mode and R mode), correspondence analysis.
- Reliability: definitions, statistics and reliability, components and equipment reliability, most common distributions in reliability.

Mandatory literature

Siegel, Sidney; Nonparametric statistics for the behavioral sciences. ISBN: 0-07-100326-6
Davis, John C.; Statistics and Data Analysis in Geology. ISBN: 0-471-83743-1
The Math Works; Using Matlab
Mardia, Kanti V.; Directional statistics. ISBN: 0-471-95333-4
The Math Works; MATLAB
Fiúza, António; Apontamentos para a Disciplina de Aquisição e Análise de Dados, DepMinas - FEUP, 2003

Complementary Bibliography

Johnson, Richard; Applied multivariate statistical analysis. ISBN: 0-13-041807-2
Morrison, Donald F.; Multivariate Statistical Methods. ISBN: 0-07-043187-6
Pestana, Dinis Duarte; Introdução à probabilidade e à estatística. ISBN: 972-31-0954-9

Teaching methods and learning activities

In theoretical-practical classes the subject matters are approached in a mathematical perspective, whereas in practical classes takes place an algorithmic approach. The continuous supervision of the different subject matters is thus indispensible to the course unit teaching.
In practical classes students have to develop a calculation algorithm, although they can use computer tools, which make this task easier. Practical classes take place at CICA rooms at FEUP with the support of PC´s. Students must enrol at Centro de Cálculo in order to have access to the internal network and be able to use the necessary programs for this course unit.

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	75,00
Participação presencial	25,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Frequência das aulas	56,00
Estudo autónomo	106,00
Total:	162,00

Eligibility for exams

According to the rules of this Masters programme.

Calculation formula of final grade

Students have to attend a final exam at the end of the semester. It encompasses a theoretical component (American type) and a practical component.
The practical component is to be done using computer tools, which includes the compulsory development of an algorithm and corresponding results.
The practical component is worth 70% of the grade, whereas the theoretical one the remaining 30%.
The practical component of the final exam comprises the following methodological phases:
1. Critical analysis and conceptual integration of the problem. Theoretical explanation (10%);
2. Development of an algorithm which will be assessed based on the following criteria (70%):
a) Resolution accuracy;
b) General features and flexibility of the algorithm;
c) Aspect of the algorithmic architecture and parcelled solutions;
3. Interpretation of the results (20%)

Examinations or Special Assignments

Not applicable

Internship work/project

Not applicable

Special assessment (TE, DA, ...)

According to General Evaluation Rules of FEUP and Masters programme rules.

Classification improvement

According to General Evaluation Rules of FEUP and Masters programme rules.