Teaching
Data Analysis: Full Time Program
A main learning outcomes for this course are:
- To become extremely proficient in Excel.
- To have thought carefully about performance measurement and how these can be used. The relevant technical content includes measures of location and scale, z-scores and r-scores
- To know how to assess a change in performance. The relevant technical content includes t-values, p-values, the two-sample t-test and matched pairs test
- To realize that all conclusions from a data set involve uncertainty, some of which can be quantified. The relevant technical content includes standard error, adjusted r-squared, model error, trend error and prediction error
- To know how to model the relationship between a performance measure and the other variables that influence it
- To realize that all conclusions from a data set involve uncertainty, some of which can be quantified. The relevant technical content includes standard error, adjusted r-squared, model error, trend error and prediction error.
All computations are entirely with Excel, either using a custom add-in StatproGo or templates that emulate the StatproGo output. There is no prescribed textbook. Instead, full lecture notes will be provided
Causal Analytics: Masters of Business Analytics
A main learning outcomes for this course are:
- Understand the key reasons that associations in non-experiment data may be spurious and to critique analyses that do not take this into account.
- Be able to control for confounders and explain why the estimates obtained are more likely to be causal.
- Be familiar with the key principles of experimental design and how to analyse the results.
- Understand difference in difference designs and regression discontinuity methods and the assumptions that support these methods.
- Understand alternative methods of causal analysis that do not require measurement of confounders and the assumptions that support these methods.
- All computations are entirely with Excel, either using a custom add-in StatproGo or templates that emulate the StatproGo output. There is no prescribed textbook. Instead, full lecture notes will be provided.