Our group, StataProfessor, provides paid help in a variety of empirical methods in finance and large data processing. The following models/methods represent a tentative list of what we offer, which means that our help is not limited only to these models/methods. If you want to apply a specific model/method which is not mentioned below, please feel free to inquire about that through our email address.
Asset Pricing Models
- Testing CAPM using Fama and McBeth cross-sectional regressions
- Testing CAPM using time series regressions and then applying different tests based on regression intercepts
- Liquiditity adjusted capital asset pricing model (LCAPM) of Acharya and Pederson (2005)
- Testing Fama and French three factor model using different tests of the regression intercepts
- Testing Fama and French five factor model using different tests of the regression intercepts
- Testing Carhart four factor model
- Asset pricing models using generalized methods of moments (GMM) technique
- Any other model that requires factor development from portfolios of assets
While testing these models, the most common approach is to use portfolios to reduce noise in asset returns and to isolate effects of different risk factors. Portfolios are created both for the left hand side (LHS) and right hand side (RHS) factors. Such portfolios are created from the intersection of selected variable using dependent and independent sorts of the given variables.
Mutual Funds Performance Evaluation Techniques
Mutual funds research has attracted attention of a large number of research studies. These studies have investigated mutual funds performance from a whole lot of angles such as whether mutual funds returns are predictable? Do mutual funds managers generate higher risk-adjusted returns as compared to naive investors’ portfolio? Is mutual funds performance predictability affected by fund size? Which of the asset pricing models best explains mutual funds returns? While all these areas are interesting, the challenge remains in the way such hypotheses are tested. Specifically, portfolio formation, risk-adjusted returns calculations, measuring momentum in risk-adjusted returns, finding association between measures of fund performance and fund characteristics across portfolio deciles that are formed on different criteria, and so on present a formidable challenge to researchers. We develop easy to use and easy-to-understand codes in Stata language to overcome such challenges.
Momentum and Contrarian Portfolio Strategies
The extant literature reports evidence in support of predictability in equity and mutual funds returns. Studies show that asset prices exhibit short-run momentums and long-run reversals. These in turn provide opportunities to earn higher risk-adjusted profits. How to detect price momentums? What is the duration of momentum? For how long should we hold an asset or portfolio if we find momentum in its return(s)? How test the economic and statistical significance of momentum profits? Do different types of weighting criteria affect momentum profits? How to test for different risk-based explanations of momentum profits? These questions can be answered only empirically. However, the empirical testing methods are complex by nature and require extensive labour work. We have developed several Stata codes for constructing momentum strategies, with lots of variations in estimation techniques. We have also developed a dedicatedprograms that simplifies the development of momentum portfolios.
Besides the above, we also offer paid help in the following models using Stata codes or general advice.
Panel data analysis
Time-series analysis including co-integration, GARCH/ ARACH/ VECM/ VAR etc
Fama and McBeth two-pass regressions
Rolling window regressions
Earning management models such as Jhones model, Kanzik model, Dechow et al, and Kothari model
Generalized methods of moments (GMM)
Endogenous regressions with 2SLS, GMM, and fixed effects models.
Implied Cost of Equity models
Credit risk models, Merton Model, KMV-Merton model