COMPSTAT

[ms_accordion style=”simple” type=”1″ class=”” id=””] [ms_accordion_item title=”Course unit” color=”#7b89b6″ background_color=”” close_icon=”” open_icon=”” status=”open”]
Computational Statistics
[/ms_accordion_item] [/ms_accordion]
[ms_accordion style=”simple” type=”1″ class=”” id=””]

[ms_accordion style=”simple” type=”1″ class=”” id=””]
[ms_accordion_item title=”Coordination” color=”” background_color=”” close_icon=”” open_icon=”” status=”open”]Pedro Pereira Rodrigues
Teresa Henriques
[/ms_accordion_item]
[/ms_accordion]

[ms_accordion style=”simple” type=”1″ class=”” id=””] [ms_accordion_item title=”Intended learning outcomes of the curricular unit” color=”#7b89b6″ background_color=”” close_icon=”” open_icon=”” status=”open”]
This unit aims at providing students with knowledge, abilities and behaviors which may allow the use of intensive computational methods in statistical analysis.
Specifically, students are expected to:
• identify modern computational methods used in statistics, including methods for simulation, estimation and visualization of statistical data
• acknowledge the role of computation as a tool for health data analysis
• be able to appropriately apply computational methodologies in real world health data science problems.
[/ms_accordion_item] [/ms_accordion]

[ms_accordion style=”simple” type=”1″ class=”” id=””] [ms_accordion_item title=”Syllabus” color=”” background_color=”” close_icon=”” open_icon=”” status=”open”]
Computational Statistics
• Why computation in statistics?
• Tools and software for computational statistics
• Computational statistics using big data infrastructures
Data Synopses
• Sufficient Statistics
• Histograms
• Micro-Clusters
• Fading Statistics
Density Estimation
• Maximum Likelihood
• Expectation-Maximization
• Kernel Estimation
Estimation and Simulation
• Jackknife Methods
• Cross Validation
• Random Number Generation
• Monte Carlo Methods
• Bootstrap Methods
Numerical analysis
• Complex Data Visualization
• Principal component analysis
• Bivariate smoothing
• Splines
[/ms_accordion_item] [/ms_accordion]

[ms_accordion style=”simple” type=”1″ class=”” id=””]
[ms_accordion_item title=”Demonstration of the syllabus coherence with the curricular unit’s intended learning outcomes” color=”” background_color=”” close_icon=”” open_icon=”” status=”open”]
The contents taught will give students the necessary and sufficient concepts to understand and use the modern methods of computational statistics necessary for the analysis of health databases. Specifically, through the content taught students will acquire the knowledge and skills that allow them to apply the methods to the problems of health data science in a transversal way, using a versatile and robust computational statistics tool.
[/ms_accordion_item]
[/ms_accordion]

[ms_accordion style=”simple” type=”1″ class=”” id=””]
[ms_accordion_item title=”Teaching methodologies” color=”” background_color=”” close_icon=”” open_icon=”” status=”open”]
Theoretical-practical classes and laboratory practice with theoretical exposition and discussion of themes, and group and individual assignments. Assessment by group assignment (30%) and final exam (70%)
[/ms_accordion_item]
[/ms_accordion]

[ms_accordion style=”simple” type=”1″ class=”” id=””]
[ms_accordion_item title=”Demonstration of the coherence between the teaching methodologies and learning outcomes” color=”” background_color=”” close_icon=”” open_icon=”” status=”open”]
The theoretical-practical exposition allows to transmit to the students the concepts and the respective skills that allow them to apply advanced methods of computational statistics in a project of data health science. Through individual exercises and group work, students will also develop competencies and mainly adjust behaviors that allow them to integrate these new methods into the daily practice of research.
[/ms_accordion_item]
[/ms_accordion]

[ms_accordion style=”simple” type=”1″ class=”” id=””]
[ms_accordion_item title=”Main bibliography” color=”” background_color=”” close_icon=”” open_icon=”” status=”open”]
Gentle, James E., Härdle, Wolfgang Karl, Mori, Yuichi (2012) Handbook of Computational Statistics. Springer Verlag.
Givens, G., Hoeting, J. (2012) Computational Statistics. Wiley.
[/ms_accordion_item]
[/ms_accordion]