Regression

Week 1 : Linear Regression

1. Simple linear regression recap
2. Goodness of fit
3. Assumptions in OLS
4. Hypothesis testing
5. Multiple linear regression
6. Model selection

Week 4 : Panel Data

1. Identify panel data and explain why it is useful
2. Explain the fixed effects model and estimate it in R
3. Explain the time fixed effects model and estimate it in R
4. Compare the output from different fixed effects models
5. Explain the random effects model
6. Estimate it in R and perform the Hausman test to select a
fixed or random effects model
Week 5 : Instrument Variable
1. Two stage least squares estimation
2. Demand for cigarettes
3. Poor instrument example
4. General IV regression
5. Model selection
6. Instrument selection

Week 6 : Limited Dependant Variable

1. Identify limited dependent variables and explain why they cannot be estimated using OLS
2. Explain the logit and probit models and estimate them in R
3. Interpret the results from logit and probit models
4. Discuss multinomial LDV models
5. Explain the Poisson model for count variables, estimate it in R and interpret the results

Time Series
Week 7 : ARMA Models (Univariate Models)
1. Autocorrelation , Autocovariance, Stationary Process
2. White noise
3. Moving Average processes
4. Autoregressive processes
5. ARMA processes
6. Box-Jenkins methodology
7. Forecasting
8. Forecast Accuracy

Week 7 : VAR and Stationarity

1. VAR Models with two variables
2. Advantage and Disadvantage of VAR modelling
3. Inference and Selection in VARs
4. Lag Lengths Determination- Information Criteria
5. VAR Forecasting
6. Trends and Random Walk
7. AR(p) Models and Dickey- Fuller Test

Week 8 : Volatility Models

1. Discuss why financial time series don’t tend to have constant volatility
2. Various volatility models (Non-linear models, volatility models)
3. Autoregressive volatility models
4. ARCH model, ARCH effects, limitations
5. Unconditional Variance
6. GARCH model , GARCH as ARMA , example
7. Discuss asymmetric GARCH models
 Data Science
Week 2 : Data Manipulation
1. Introduction to data science

2. Data transformation
o filter() to pick observations by their values
o arrange() to reorder rows
o select() to pick variables by their names
o mutate() to create new variables with functions of existing variables
o summarize() to collapse many values down to a single summary

3. Tidy data
o gather()
o spread()
o separate()
o unite()

Week 3 : Data Visualization

1. Data exploration VS data communication
2. Construction of a variety of plots in R (Scatterplot, Bar chart, Box plot)
3. Analysis of the output
4. Customisation of visualisations for clear communication
5. Data communication: Graphical excellence, Visual deception, Accessibility
6. Ethical use of data visualisations

Week 10 : Application and Ethics

1. Discuss the development of data science in the financial services , 4 example of data science in use
2. Discuss some case studies (BoE & FCA report on use of machine learning in financial services)
3. Consider the risks of data science, regulation.
4. Discuss ways to mitigate those risks, ethical use of data science

Tut Checklist:

[] Tut.1
[] Tut.2
[] Tut.3
[] Tut.4
[] Tut.5
[] Tut.6
[] Tut.7
[] Tut.8
[] Tut.9
[] Tut.10

Mock Exam :

[] Teacher provided
[] Mock 1
[] Mock 2
[] Mock 3