Andreas C. Rapp – Teaching

University of Amsterdam

» Master Thesis Supervision (Financial Econometrics) (2017, 2018)

» Computational Finance using Python (MIF – 2018)

Reading material:

○ Hilpisch (2014) "Python for Finance"

○ Hull (2012) "Options, Futures and Other Derivatives"

» Mathematical and Empirical Finance (B.Sc. Econometrics – 2017)

Reading material:

○ Luenberger (2013) "Investment Science"

» Financial Econometrics (M.Sc. Econometrics & M.Sc. Actuarial Science/Mathematical Finance – 2018)

Reading material:

○ Tsay (2010) "Analysis of Financial Time Series"

Tilburg University

» Bachelor Thesis Supervision (Finance) (2013, 2014, 2015)

» Financial Analysis and Investor Behavior (M.Sc. Finance (CFA track) – 2014, 2015, 2016)

Reading material: Selection of research papers, e.g.,

○ Black and Litterman (1991) "Asset Allocation: Combining Investor Views with Market Equilibrium"

○ Brandt, Santa-Clara, and Valkanov (2009) "Parametric Portfolio Policies: Exploiting Characteristics in the Cross Section of Equity Returns"

» Information Economics (Research Master Course – 2014, 2015, 2016, 2017)

Awarded as the Best Teaching Assistant in the CentER Graduate Program (Business) in 2016-2017

Reading material:

○ Mas Colell, Whinston, and Green (1995) "Microeconomic Theory"

○ Bolton and Dewatripont (2005) "Contract Theory"

» Empirical Methods in Finance (M.Sc. Finance – 2013, 2014, 2015, 2016, 2017, 2018)

Reading material: ;

○ Verbeek (2008) "A Guide to Modern Econometrics"

○ Brooks (2014) "Introductory Econometrics for Finance"

Please find all .do-files and data sets on the Tilburg University Blackboard.

Lecture 1.1 – Getting started with Stata (11:58)

This video covers: the Stata GUI, Stata's command syntax (explained using the command summarize), opening the .do-file editor
Commands used: sysuse, display, summarize, doedit

Lecture 1.2 – Getting started with Stata (13:30)

This video covers: working in the .do-file editor, commenting in a .do-file, setting up a .do-file environment (e.g. to create log-files), Stata's help resources
Commands used: capture log close, log using, mkdir, cd, clear all, version, set more off, set seed, describe, summarize, list, log close

Lecture 2.1 – Managing and editing data (18:25)

This video covers: Importing data into Stata (here: a .xls file), inspecting your dataset (e.g., describe, or simple line graphs), editing your dataset (e.g., labelling, generating variables), Stata's operators and functions in the context of generating variables, Stata's system variables (_n and _N), stored information (so-called r-class results), generating a categorical variable using the by-pefix
Commands used: import, label var, graph twoway, generate, return list, drop, bys, sort

Lecture 2.2 – Managing and editing data (14:11)

This video covers: the forvalues loop (i.o. to sum variables), addressing specific values in a variable vector (e.g. display m_CDAX[1]), generating log-returns, the foreach loop (e.g. to generate log-returns for several variables)
Commands used: tab, forvalues, foreach, drop, keep

Lecture 2.3 – Managing and editing data (17:28)

This video covers: generating variables using the egen command (e.g. to find extreme returns), plot a histogram of returns, generating excess returns (using the foreach command), generating a table with summary statistic, merging two datasets, the preserve and restore commands, saving a dataset (with a .dta extension)
Commands used: egen, histogram, foreach, rename, tabstat, merge, order, save, preserve, restore

Lecture 3.1 – Regression analysis (19:31)

This video covers: loading a Stata dataset, time-setting your data (here: time-series data), understanding the CAPM as a regression model, using the regress command, interpreting a regression output
Commands used: use, tsset, regress

Lecture 3.2 – Regression analysis (18:38)

This video covers: installing user-written packages (here: estout), running regressions with heteroskedasticity consistent (so-called robust) standard errors, testing the significance of coefficients, using the if qualifier with the regress command (e.g. to use a date restriction), time-variability of estimates using sub-samples
Commands used: ssc install estout, replace, robust, vce(robust), est store, test, regress if

Lecture 3.3 – Regression analysis (23:08)

This video covers: visual inspection of the CAPM (using a scatter and lfit plot), predicting fitted values from a regression, stored post-estimation results (so-called e-class returns), predicting residuals, leads and lags of variables, running Newey-West regressions with heteroskedasticity and auto-correlation consistent (or HAC) standard errors, generating i.i.d. random variables
Commands used: predict, resid, estat bgodfrey, L., F., drawnorm, scalar, newey, lag

Lecture 3.4 – Regression analysis (07:11)

This video covers: running multiple regression analysis (here: the Carhart four-factor model), using local macros as a tool to store variable lists, interpreting a multiple regression output
Commands used: local, regress, newey

Lecture 4.1 – Panel data techniques (07:11)

This video covers: Loading a panel data set (here: a .xls file) and xtsetting the data, using “xt” panel commands, editing your dataset (e.g., labelling, generating variables), generating variables using the by-prefix and the gen and egen commands in combination with a firm-specific identifier, checking the correlation of variables with each other, generating a sub-samples of observations and testing mean-differences (using the ttest command)
Commands used: use, xtset, xtdescribe, xtsum, label var, by, bysort, generate, egen, corr, tabstat, by(...), ttest, by()

Lecture 4.2 – Panel data techniques (24:36)

This video covers: Executing pooled-OLS regression analysis, using cluster-robust standard errors, using robust regression analysis (using rreg), running a Least-Square-Dummy-Variable model (using a set of dummy-variables as well as the areg command), running a fixed-effects regression model (using the xtreg, fe command)
Commands used: reg, robust cluster(), rreg, matrix matlist, areg, absorg(), xtreg, fe i()

Lecture 4.3 – Panel data techniques (22:30)

This video covers: Predicting the estimated fixed-effects, using the dfadj option (degree-of-freedom adjustment) in the areg and the xtreg command using cluster-robust standard errors, including time-fixed effects in a fixed-effects model (using the variable/indicator prefix i.), running a random effects model, using the Hausman test to decide between the FE and RE model, comparing results for survivors and non-survivors
Commands used: xtreg, fe i() vce(cluster gvkey), djadj, i.year, xtreg, re i(), hausman

Lecture 5.1 – Times-series analysis (24:57)

This video covers: Working with Stata's date function (transforming a string date variable to a numeric date variable), using ts time-series commands, plotting data with tsline, recognizing recession periods, investigating the correlation and cross-correlation between bivariate time-series
Commands used: use, tsset, quarterly(...,...), dofq(...), quarter(...), year(...), tsline, corr, D.

Lecture 5.2 – Times-series analysis (28:18)

This video covers: Working with Stata's time-series operators (L., D., S., and F.), estimating an AR(1), stationarity vs. non-stationarity in a time series, trend and cyclical component of a series, tsfiltering (Hodrick-Prescott and/or Baxter-King), Dickey-Fuller unit root tests, investigating the autocorrelation structure of a time series using the corrgram, ac, and pac commands, optimal lag selection using the varsoc command, estimating AR(p) and MA(q) with the arima command
Commands used: L., D., S., and F., reg, newey, arima, dfuller, tsfilter, corrgram, ac, pac, varsoc

Lecture 5.3 – Times-series analysis (12:46)

This video covers: Static and dynamic point-forecasting with Stata using the predict command after an arima regression model, appending a dataset with additional observations, working with the dynamic(...) option, using the r-class results after tsset, plotting the forecasting results and the forecasting error
Commands used: tsappend, tsset, return list, local, arima, predict, dynamic(...), merge 1:1, _n, tsline

Additional reading material (related to Stata):

○ Cameron and Trivedi (2010) "Microeconometrics using Stata"

○ Baum (2006) "An Introduction to Modern Econometrics Using Stata"

○ Baum (2009) "An Introduction to Stata Programming"