This course provides a comprehensive survey of the core vocabulary and methods of data science, data analytics, and machine learning.
5 day intensive programme running 10 - 14 June and 4 - 8 November 2019
Data science is a rapidly spreading field that combines statistical analysis, data management, computation, and substantive expertise, with the goal of improving decision-making in business, government, administration, law, and just about every other field.
One of the key challenges for decision-makers and managers is to understand what makes for good data science, and how the evidence from this field should be used in evaluation and decision-making.
The focus of this course is on examples of good and bad data science, with real-world applications from government, business, and law. By the end of the course, students will be familiar with the concepts of data science and will have learned how to evaluate quantitative evidence and how to design new studies using big data and data scientific tools.
Tuition Fee: £5,995
Includes all LSE tuition, course materials, daily lunches, and networking events. You will also be awarded an LSE certificate of completion at the end of the five days.
Part of LSE Executive Education Courses
Day 1: Data de-mystified: The infrastructure of our emerging data society
- The vocabulary of data
- Creating data: From raw to structured information
- Beyond spreadsheets: A guide to data and databases
- Benefits and risks from data linkage
- Core issues in data security
- Data anonymity
- Legal frameworks for data protection
- Understanding blockchains
- A guide to common tools used in data management.
Day 2: How to Lie with Statistics: Understanding varieties of quantitative evidence
- The vocabulary of statistical analysis
- Core concepts in statistical methods
- Descriptive statistics
- Key issues in sampling
- Understanding variance: when different numbers are the “same”
- Association measures
- Regression analysis
- Measurement models
- A guide to the common tools used in statistical analysis.
Day 3: Everything you always wanted to know about machine learning (but were afraid to ask)
- The vocabulary of machine learning
- Machine learning versus statistical methods
- Supervised versus un-supervised machine learning
- Core methods in supervised machine learning
- Core methods in unsupervised machine learning
- Neural networks and “deep learning”
- Evaluating performance in machine learning: understanding precision, recall, accuracy, and cross-validation
- A guide to common tools used in machine learning.
Day 4: Decision-making with quantitative evidence
- Understanding hypothesis tests, p-values, and statistical significance
- Type I and Type II errors
- Understanding prediction error and misclassification
- Bayesian reasoning and probability
- How to read plots and data visualizations
- Correlation versus causation
- How to design research for evaluation
- The vocabulary of statistical decision-making, causal inference, programme evaluation.
Day 5: Completing the circle: integrating qualitative with statistical evidence
- Overview and vocabulary guide to qualitative research methods
- Confirming versus exploring: Using qualitative evidence to design analytics
- Supplementing analytics with focus groups and interviews
- The Delphi method: Group decisions making and prediction
- Expert surveys to estimate unobservables
- Crowdsourcing to tap human judgment or conduct experiments
- Text mining and sentiment analysis
- A guide to analytic tools for qualitative analysis.
- A comprehensive top-level understanding of the core concepts and methods of data science, including data management, data analysis, machine learning, and statistical learning.
- The ability to evaluate evidence from statistical learning and data science, in order to make informed decisions.
- A thorough awareness of the core issues in designing new data scientific studies.
- Practical and applied knowledge of the core material through applications drawn from business, government, and law, including at least one presentation from a practitioner in one or more of these areas.
This course will be taught by: