Science
SCIENCE
FCSC DIPLOMA PROFESSIONAL PROFILE 4:
Synopses
DATA SCIENCE
FCSC Diploma Module 4.1
FCSC DIPLOMA
Machine learning
• Introduction to data science and machine learning
• Data science methodology and data exploration
• Working with data preprocessing and data visualisation - data pre-processing and error estimates, metrics for numeric and categorical data, technical standards, the problem with missing values, estimates of error of regression and classification systems, and techniques for feature extraction and projections
• Unsupervised learning models - market basket analysis, recency-frequency-monetary (RFM) analysis, clustering algorithms (K means, self-organising maps (SOMs), additional topics on clustering)
• Supervised learning models - decision theory and Bayesian learning systems (general concepts, optimal Bayesian decisions), learning and classification based on instances (nearest neighbour algorithm, variants of nearest neighbour, selective choice), induction of decision trees (general principles, discrete-diffraction-transform (DDT) algorithm, others), ensemble classifiers, neural networks (single perceptron, multi-layer perceptron (MLP), introduction to deep learning neural networks), and support vector machines
FCSC Diploma Module 4.2
Business intelligence - data warehousing and analytics
• Business intelligence (BI) - introduction to BI - a framework for BI, intelligence creation and use, BI governance, the major theories and characteristics of BI, towards competitive intelligence and advantage, successful BI implementation, and BI today and tomorrow
• Data warehousing (DW) - DW definitions and concepts, DW process overview, DW architectures, data integration and the extraction-transformation-load (ETL) processes, DW development, real-time DW, and DW administration and security issues
• Business analytics (BA) and data visualisation - introduction to the field of BA, online analytical processing (OLAP), reports and queries, multidimensionality, advanced business analytics, data visualisation, geographic information systems, BI real-time decision support and automated competitive intelligence, web analytics, web intelligence, and use-benefits-results of BA
• Information dashboard design - introduction to dashboards, dashboard design challenges, dashboard design best practices, and data visualisation tips
• Future trends in business intelligence and data warehousing
FCSC Diploma Module 4.3
Computational statistics
• Collecting, describing, and plotting data - cases and variables, samples and population, sources of bias, categorical variables, one quantitative variable, boxplot, identifying outliers, one qualitative and one quantitative variable, two quantitative variables, and relationships between multiple variables
• Confidence intervals - sampling distributions, introduction to confidence intervals, introduction to bootstrapping, bootstrap confidence intervals, paired samples, impact of sample size on confidence intervals
• Hypothesis testing - introduction to hypothesis testing, writing hypotheses, p-values, type I and type II errors, significance levels, issues with multiple testing, the power of a test
• Normal distributions - standard normal distribution, computing probabilities and quantiles, and central limit theorem
• Inference for one sample - one sample mean, one sample proportion, and paired means
• Inference for two samples - two independent proportions, and two independent means
• Correlation and regression - linear correlation, simple linear regression, coefficient of determination, cautions, and multiple linear regression
• Non-parametric methods - one sample sign test, one sample Wilcoxon signed rank test, Friedman test, Goodman-Kruska's Gamma, Kruskal-Wallis test, Mann-Kendall trend test, Mann-Whitney test, Mood's median test, and Spearman rank correlation
FCSC Diploma Module 4.4
Big data in official statistics
• Big data and digital trails
• Overview of big data sources
• Main challenges of storing and modelling big data
• Approaches for data modelling and database management
• The use of big data in official statistics
• Examples of the use of big data in the production of official statistics
• Methodological challenges of big data
• Big data tools overview
Data Science
DATA SCIENCE
PROFILE 4:
Synopses
DATA SCIENCE
FCSC Diploma Module 4.1
Machine learning
• Introduction to data science and machine learning
• Data science methodology and data exploration
• Working with data preprocessing and data visualisation - data pre-processing and error estimates, metrics for numeric and categorical data, technical standards, the problem with missing values, estimates of error of regression and classification systems, and techniques for feature extraction and projections
• Unsupervised learning models - market basket analysis, recency-frequency-monetary (RFM) analysis, clustering algorithms (K means, self-organising maps (SOMs), additional topics on clustering)
• Supervised learning models - decision theory and Bayesian learning systems (general concepts, optimal Bayesian decisions), learning and classification based on instances (nearest neighbour algorithm, variants of nearest neighbour, selective choice), induction of decision trees (general principles, discrete-diffraction-transform (DDT) algorithm, others), ensemble classifiers, neural networks (single perceptron, multi-layer perceptron (MLP), introduction to deep learning neural networks), and support vector machines
FCSC Diploma Module 4.2
Business intelligence - data warehousing and analytics
• Business intelligence (BI) - introduction to BI - a framework for BI, intelligence creation and use, BI governance, the major theories and characteristics of BI, towards competitive intelligence and advantage, successful BI implementation, and BI today and tomorrow
• Data warehousing (DW) - DW definitions and concepts, DW process overview, DW architectures, data integration and the extraction-transformation-load (ETL) processes, DW development, real-time DW, and DW administration and security issues
• Business analytics (BA) and data visualisation - introduction to the field of BA, online analytical processing (OLAP), reports and queries, multidimensionality, advanced business analytics, data visualisation, geographic information systems, BI real-time decision support and automated competitive intelligence, web analytics, web intelligence, and use-benefits-results of BA
• Information dashboard design - introduction to dashboards, dashboard design challenges, dashboard design best practices, and data visualisation tips
• Future trends in business intelligence and data warehousing
FCSC Diploma Module 4.3
Computational statistics
• Collecting, describing, and plotting data - cases and variables, samples and population, sources of bias, categorical variables, one quantitative variable, boxplot, identifying outliers, one qualitative and one quantitative variable, two quantitative variables, and relationships between multiple variables
• Confidence intervals - sampling distributions, introduction to confidence intervals, introduction to bootstrapping, bootstrap confidence intervals, paired samples, impact of sample size on confidence intervals
• Hypothesis testing - introduction to hypothesis testing, writing hypotheses, p-values, type I and type II errors, significance levels, issues with multiple testing, the power of a test
• Normal distributions - standard normal distribution, computing probabilities and quantiles, and central limit theorem
• Inference for one sample - one sample mean, one sample proportion, and paired means
• Inference for two samples - two independent proportions, and two independent means
• Correlation and regression - linear correlation, simple linear regression, coefficient of determination, cautions, and multiple linear regression
• Non-parametric methods - one sample sign test, one sample Wilcoxon signed rank test, Friedman test, Goodman-Kruska's Gamma, Kruskal-Wallis test, Mann-Kendall trend test, Mann-Whitney test, Mood's median test, and Spearman rank correlation
FCSC Diploma Module 4.4
Big data in official statistics
• Big data and digital trails
• Overview of big data sources
• Main challenges of storing and modelling big data
• Approaches for data modelling and database management
• The use of big data in official statistics
• Examples of the use of big data in the production of official statistics
• Methodological challenges of big data
• Big data tools overview
