Statistical training

University modules

COM6509 Machine Learning and Adaptive Intelligence

Open to: By request only

Staff contact: com-teaching@sheffield.ac.uk

When is it taught? Autumn semester

The module is about core technologies underpinning modern artificial intelligence. The module will introduce statistical machine learning and probabilistic modelling and their application to describing real-world phenomena. The module will give students a grounding in modern state of the art algorithms that allow modern computer systems to learn from data.

Academic aims

This unit aims to provide a deep understanding of the fundamental technologies underlying modern artificial intelligence. In particular, it will provide a foundational understanding of:

• probability in artificial intelligence
• supervised learning for classification and regression
• unsupervised learning for data exploration

Learning outcomes

• Give a general understanding of probability theory and how it relates to uncertainty in modern artificial intelligence.
• Understand when and how to implement the appropriate learning paradigm for a given application.
• Have a deep understanding of how to implement a range of supervised and unsupervised learning algorithms. Potential examples include linear regression, linear classification, naive Bayesian classification, principal component analysis, k-means clustering, decision trees.
• Have a broad understanding of more complex technologies, ie when they are applicable and how they are more powerful than simpler techniques. Potential examples include the support vector machine, kernel methods, probabilistic graphical models, E-M algorithms, factor analysis, nonparametric Bayesian methods.

HAR6035 Introduction to Statistics and Critical Appraisal

Open to: ScHARR students only

Staff contact: Stephen Walters, S.J.Walters@sheffield.ac.uk

When is it taught? Autumn semester

The unit introduces students to basic concepts and techniques such as hypothesis testing and confidence interval estimation in statistics. Students will learn some simple statistical methods and the principles behind some advanced methods such as regression. It will equip students with the knowledge and skills necessary to understand and critically appraise statistics in research literature.

The course is not aimed at ‘doers’ of statistics, that is, students who are going to design their own studies to collect and analyse their own data. It will not teach you how to analyse, present and report your own data.

Academic aims:

• To introduce students to fundamental concepts and methods in medical statistics.
• To enable students to apply these concepts to critically appraise research literature.

Learning outcomes

By the end of the unit, a student will be able to

• classify and appropriately display and summarise different types of data
• describe the properties of the Normal distribution
• distinguish between a population and a sample, and describe the precision of a sample estimate of a population parameter
• explain the concept of confidence intervals as applied to means, proportions, differences in means, and differences in proportions
• describe the process of setting and testing a statistical hypothesis
• distinguish between 'statistical significance’ and 'clinical significance’, Evaluate the quality of published research

HAR6042 Introduction to Statistics and Critical Appraisal (online)

Open to: University-wide

Staff contact: Rebecca Simpson, r.simpson@sheffield.ac.uk

When is it taught? Spring semester

The unit, which is delivered online, introduces students to basic concepts and techniques such as hypothesis testing and confidence interval estimation in statistics.

Students will learn some simple statistical methods and the principles behind some advanced methods such as regression. It will equip students with the knowledge and skills necessary to understand and critically appraise statistics in research literature.

Academic aims:

• To introduce students to fundamental concepts and methods in medical statistics.
• To enable students to apply these concepts to critically appraise research literature.

Learning outcomes

By the end of the unit, a student will be able to

• classify and appropriately display and summarise different types of data
• describe the properties of the normal distribution
• distinguish between a population and a sample, and describe the precision of a sample estimate of a population parameter
• explain the concept of confidence intervals as applied to means, proportions, differences in means and differences in proportions
• describe the process of setting and testing a statistical hypothesis
• distinguish between 'statistical significance’ and 'clinical significance’
• evaluate the quality of published research

HAR6045 Further Statistics for Health Science Researchers

Open to: ScHARR students only

Staff contact: Jeremy Dawson, j.f.dawson@sheffield.ac.uk

When is it taught? Spring semester

The unit covers fundamental statistical concepts, both simple statistical methods and the more widely used advanced methods of multiple regression, survival analysis and generalised linear models.

It will be a practical module, including the teaching of the statistical software Statistical Package for the Social Sciences (SPSS). It will equip students with the knowledge and skills necessary to design and analyse a study to answer specific research questions, to understand and critically appraise the literature and to present research findings in a suitable fashion.

Academic aims

Introduce students to fundamental concepts and analysis methods in statistics used by health science researchers. Enable students to apply these concepts to critically appraise research literature. Equip students with the knowledge and skills necessary to appropriately analyse a study using SPSS and to present research findings in a suitable fashion.

These outcomes relate to the following QAA subject-specific skills in health studies including the ability to understand, interpret and critically appraise the statistical information presented in the health and health care literature.

Also, the ability to draw on research and research methodologies to locate, review and evaluate research findings relevant to health and health issues, across a range of disciplines.

• describe and test statistical hypotheses in an appropriate manner
• analyse data appropriate to the particular study design
• understand parametric and non-parametric tests and when they should be used
• understand how to use multiple linear regression
• understand how to use logistic regression and other generalised linear models
• understand how to use survival analysis
• use SPSS to perform all of the above analyses and to manage data
• evaluate the quality of published research from recent papers

Learning outcomes

By the end of the unit, a student will be able to

classify and appropriately display and summarise different types of data

---

Short courses and other resources on statistics

MASH - Maths and statistics help

For further help with choosing the correct method book a 1:1 session with the School of Mathematics and Statistics.

Learn more

---

Visualising and analysing biomedical datasets with R

This unit will teach students how to visualise biomedical data using histograms, scattergrams, line plots, and more sophisticated methods including heatmaps and how to turn these into publication-quality images.

Please email medicine-pgr@sheffield.ac.uk to enquire about this course.