Sample Skills Workshops
EViews tutorials will give you a basic toolkit for analyzing time series data, dealing with trends and seasonality, detrending data and estimating and plotting responses of key macro and finance variables. The goal is to show you how to import data into EViews, familiarize you with the graphing capabilities of the software, go over basic time series regression tools and operators, tests for serial correlation and collinearity as well as unit roots, and go over Band-Pass and HP filtering. These tutorials will be hands on. I would like you to experience EViews and all its intricacies for yourselves. The objective is to give you confidence when using EViews on your own. The tutorial is tailored to the SAIS MIEF program, and will utilize a combination of datasets and examples from various sources.
MATLAB tutorials will give you a basic toolkit for computing business cycle statistics and plotting responses of key macro variables. The goal of the first half is to familiarize you with the matrix capabilities of MATLAB, introduce you to loops using the 'for' command, and discuss the \verb|fzero| and \verb|fsolve| commands for solving systems of equations. These commands are important for solving the steady states of macro models. The goal of the second half is to show you how to import data into MATLAB, familiarize you with the graphing capabilities of the software, go over Band-Pass and HP filtering, compute auto- and cross-correlations of macro variables, and demonstrate how to generate LaTeX formatted tables directly from MATLAB. These tutorials will be hands on. I would like you to experience MATLAB and all its intricacies for yourselves. The objective is to give you confidence when using MATLAB on your own.
This course shows how to use PcGive for both developing econometric models and testing hypotheses of interest. PcGive focuses on modeling dynamic responses in either single or simultaneous models. These responses can be estimated with OLS, IV, and FIML along with test results regarding the properties of the residuals and the constancy of the parameters. In addition, this software provides impulse responses, dynamic and static model simulations, and forecasts’ confidence bands.
This workshop will introduce Stata and illustrate how to use the software for practical applications, with attention to manual coding. We will cover basic applications - such as simple OLS regressions and charting - as well as binary dependent variable modelling, time-series features, and panel data techniques. The theoretical concepts underpinning empirical analyses will also be reviewed.
This workshop provides an introduction to analyzing data using the statistical programming language, R. It covers the fundamentals of the language, along with the essentials of data ingestion, cleaning, manipulation, and visualization. R is an open-source software environment for statistical computing and graphics used by many economists, governments, and privatesector firms (especially consulting firms).
This workshop showcases how R can be leveraged for the MIEF Capstone project using previously submitted capstone work as a case-study. It covers the use of R for setting up end-to-end analytics pipelines, with particular emphasis on data manipulation for plotting, implementations of workhorse econometric models within R, and reporting. All functions and code explored will be provided for future capstone work. Before comping to the workshop, students should have R installed on their laptops, and should come with an understanding of the fundamentals of the R programming language.
This workshop showcases how R can be leveraged for the MIEF Capstone project using previously submitted capstone work as a case-study. It covers the use of R for setting up end-to-end analytics pipelines, with particular emphasis on data manipulation for plotting, implementations of workhorse econometric models within R, and reporting. All functions and code explored will be provided for future capstone work. Before coming to the workshop, students should have R installed on their laptops, and should come with an understanding of the fundamentals of the R programming language.
Machine learning techniques have rapidly advanced to become tremendous tools for predictive analysis. However, many questions that researchers and practitioners wish to answer require an examining and understanding of causal relationships. Some of these questions from academia include; how does an increase in taxes on cigarettes affect smoking behavior? Or how would a change in How does website layout direct traffic towards different products? How does altering packaging impact sales? Over the past decade, econometricians have been exploring how to employ the power of machine learning to answer questions of causal nature. These methods vary in their use cases and this course plans to provide students with exposure to the various algorithms available. Students will also practice employing them so that they can 1) build an intuition around when certain techniques are better suited to their goals, 2) build up a code base of their own to draw on for their future studies and careers.
The emergence of freely available data lead to widespread application of machine learning (ML) in finance. Machine learning methods are used in many areas of finance such as fraud detection, credit card applications, portfolio construction, and stock return prediction. This course will start with the basics of financial forecasting and build up to the cutting edge of machine learning. We will overview the basic process of data science and machine learning techniques for finance. This course will focus on the tools necessary to forecast stock returns and portfolio construction. The ability of learning patterns from data and making accurate predictions with new data is what makes ML a powerful tool for financial forecasting and decision making. This course will touch on the theory of ML algorithms but not dive into the technical details. We will instead focus on the applications of ML. Hands-on applications is an important part of this course. Students will be introduced to some theoretical properties of ML algorithms and immediately will be shown how to implement them. The purpose of this approach is to train the students to develop ML projects independently and confidently.
This workshop provides an introduction to the Python programming language with a particular emphasis on analyzing data in Python. Python is an open-source, general purpose programming language used widely across a number of industries and is arguably one of the most popular programming languages in the world today. This workshop will cover environment setup, Python fundamentals, and the foundations of data analysis using the popular pandas and numpy libraries.
Use finance skills to estimate the behaviors of the various assets classes that large investment portfolios commonly invest in. Discuss issues of strategic and tactical asset allocation within a portfolio and study the process of combining these different asset classes together to create a desired investment portfolio. Discuss issues of long run performance and payout rules as well as methods for measuring portfolio and manager performance.