Tale of Two Cities An Econometric Analysis of East & West Coast Fine Art Galleries
By Daniella Victoria Paretti
Abstract
In a 2021 report published alongside Art Basel and UBS, renowned cultural economist Dr.
Clare McAndrew posited that the value of art sales in 2020 amounted to an impressive $50 billion
(although this actually marks an over 10-year low). It is no secret that the global art markets are
extremely lucrative, attracting the interest of industry magnates and business tycoons alike.
Though it is important to note that art markets are historically quite distinct from their normal good
counterparts — the sector is laden with issues regarding transparency, high barriers to entry, and
hiding of wealth. Amidst the COVID-19 pandemic, however, the tides began to turn; online
platforms for museums, auction houses, and galleries were employed more than ever before,
effectively modernizing the antiquated industry and expanding its reach to new consumers. How
has this trend of digitalization changed and improved art markets? More specifically, how can data
analytics and other technological resources serve the interests of private galleries? Using sales data
from a parent gallery with multiple locations across the United States (each displaying similar
works/artists), I have conducted a number of qualitative and statistical analyses to identify key
differences between the West and East coast locations. In short, the gallery on the West coast sold
more works and at a lower average cost than its counterpart, providing key insights into this local
market’s consumer base. Beyond this, factors like size, medium, and artist gender were found to
have statistically significant effects on the ultimate sale price and turnover rate of works. My
findings suggest that means of data analytics should be utilized by all actors in the art markets to
optimize their approach to business, as well as understand their consumers better than ever before.
Professor Michelle Connolly, Faculty Advisor
Professor Hans Van Miegroet, Faculty Advisor
JEL classification: Z11, C10, J11, O33
Bayesian Non-Parametric Risk Metric
By Kiwan Hyun
Abstract
This thesis constructs completely non-parametric Risk Metric models through Dirichlet process in order to account for both the parametric uncertainty and model uncertainty that a Risk Metric may bring.
Value at Risk (VaR), along with its integrated form Continuous Value at Risk (CVaR) / Expected Shortfall (ES), is one of the most frequently used risk metrics in finance. VaR is a quantile value of forecasted return of a portfolio—linear and non-linear. [Siu, et. al., 2006] According to the Basel 95% and 99% VaR are recommended to be posted by the financial institutions for portfolios and assets; 97.5% CVaR/ES value needs to be set aside when making an investment for “capital buffer”. [Obrenovic & Akhunjonov, 2016] Therefore, an accurate estimation of risk is critical for VaR models and CVaR/ES models.
The traditional approach of a normal approximation to VaR and CVaR/ES has been discredited—especially for daily returns—and even blamed by some for causing the 2008 Financial Crisis [Nocera, 2009] Many advancements have been made to the VaR model including Bayesian inference to the normal model [Siu, et. al., 2006], Generalized Auto-Regressive Conditional Heteroskedasticity (GARCH) VaR model [Bollerslev, 1986], and Conditional Autoregressive Value at Risk (CAViaR) model [Engle & Manganelli, 2004]. When tested against 6 years (Jan, 2001 – Jan, 2005) of daily returns data of 10 different market indexes, the Bayesian CAViaR model has shown to be the most accurate in predicting daily 95% and 99% VaR. [Gerlach, et. al., 2011]
However, there were certain years for certain indexes where the 99% Bayesian CAViaR VaR did not perform well, especially for years that had multiple > 5% daily drops. Moreover, the Bayesian CAViaR models—though are almost non-parametric—follow a Skewed-Laplace distribution. To even account for the uncertainty of the likelihood model, this thesis constructed daily 97.5% VaRs for 7 different country indexes for 7 years (Jan, 2012 – Dec, 2019) using the completely non-parametric Dirichlet Process.
The Dirichlet Process 97.5% VaR outperformed all Bayesian Normal, Bayesian GARCH, and Bayesian CAViaR models of years when CAViaR models underperformed. The model may be inefficient for normal years since it is overly conservative. Nevertheless, the non-parametric model still seems to be significantly more accurate during fluctuant years.
Professor Kyle Jurado, Ph.D., Faculty Advisor,
Assistant Professor Simon Mak, Ph.D., Faculty Advisor
The Impact of Access to Public Transportation on Residential Property Value: A Comparative Analysis of American Cities
By Moses Snow Wayne
This paper develops a consistent model for analyzing the impact of access to public transportation on property value applied to the four cities of Atlanta, Boston, New York, and San Francisco. This study finds a negative relationship between increasing distance to public transit and property value. Additionally, the elicited effects in each city generally align with geographic features and the degree to which a city is monocentric. This study also demonstrates the salience of using actual map-generated distances as proximity measures and characteristics of public
transit systems in modeling the relationship between public transportation and residential property value.
Advisors: Dr. Patrick Bayer and Kent Kimbrough | JEL Codes: C12, R14, R30, R41
The Effect of Federal Regulations on the Outcomes of Auctions for Oil and Gas Leaseholds
By Artur Shikhaleev
This thesis attempts to analyze the impact of the differences in regulatory frameworks that govern state-owned and federally-owned lands on the outcomes of auctions for oil and natural gas leaseholds in the state of New Mexico. The analysis tries to isolate the effect of ownership by controlling for auction structure, leasehold characteristics, and prices of underlying resources. Given past research, the hypothesis is that stricter regulations carry a heavier cost to buyers, so the expectation is that federally-owned leaseholds, which are more regulated, are traded at a discount to state-owned leaseholds. However, the result of this thesis is contradictory to the hypothesis. The conclusion is that stricter regulations do not lead to a discounted auction price for an oil and gas leasehold.
Advisor: James Roberts, Kent Kimbrough | JEL Codes: C12, C21, Q35, Q58 | Tagged: Auction, Education, environment, federal, natural gas, Oil, Regulation, State
Dealing with Data: An Empirical Analysis of Bayesian Black-Litterman Model Extensions
By Daniel Roeder
Portfolio Optimization is a common financial econometric application that draws on various types of statistical methods. The goal of portfolio optimization is to determine the ideal allocation of assets to a given set of possible investments. Many optimization models use classical statistical methods, which do not fully account for estimation risk in historical returns or the stochastic nature of future returns. By using a fully Bayesian analysis, however, this analysis is able to account for these aspects and also incorporate a complete information set as a basis for the investment decision. The information set is made up of the market equilibrium, an investor/expert’s personal views, and the historical data on the assets in question. All of these inputs are quantified and Bayesian methods are used to combine them into a succinct portfolio optimization model. For the empirical analysis, the model is tested using monthly return data on stock indices from Australia, Canada, France, Germany, Japan, the U.K.
and the U.S.
Advisor: Andrew Patton | JEL Codes: C1, C11, C58, G11 | Tagged: Bayesian Analysis Global Markets Mean-Variance Portfolio Optimization
Possibility of Cost Offset in Expanding Health Insurance Coverage: Using Medical Expenditure Panel Survey 2008
By Catherine Moon
The Patient Protection and Affordable Care Act aims to substantially reduce the number of the
uninsured over time and asserts that the financial burden of extending insurance coverage to the
previously uninsured will be offset by the benefit of the attendant improvement in their health.
Motivated by this policy, I explore whether health-insurance status and type affect one’s likelihood of
improving or maintaining health using the Medical Expenditure Panel Survey data. I build a set of
ordered regression models for health-status transitions under the first-order Markov assumption and
estimate it using maximum likelihood estimation. I perform a series of likelihood ratio tests for pooling to determine whether the latent propensity index is the same between adjacent initial health-status groups. Empirical results imply that expanding health care to the unwillingly uninsured due to severe
economic constraints and extending the scope of public insurance to that of private insurance will lead to improvement or maintenance of health for the relatively healthy population, implying the possibility of cost off-set in the expansion of coverage and the extension of scope.
Advisor: Frank Sloan, Michelle Connolly | JEL Codes: C12, C25, I12, I13, I18 | Tagged: Health Insurance, Health Transition, Ordered Regression Model, Patient Protection and Affordable Care Act (PPACA), Self-Assessed Health Status, Test for Pooling Adjacent Ordinal Categories
Time-Varying Beta: The Heterogeneous Autoregressive Beta Model
By Kunal Jain
Conventional models of volatility estimation do not capture the persistence in high-frequency market data and are not able to limit the impact of market micro-structure noise present at very finely sampled intervals. In an attempt to incorporate these two elements, we use the beta-metric as a proxy for equity-specific volatility and use finely sampled time-varying conditional forecasts estimated using the Heterogeneous Auto-regressive framework to form a predictive beta model. The findings suggest that this predictive beta is better able to capture persistence in financial data and limit the effect of micro-structure noise in high frequency data when compared to the existing benchmarks.
Advisor: George Tauchen | JEL Codes: C01, C13, C22, C29, C58 | Tagged: Beta, Financial Markets, Heterogeneous Autoregressive, Persistence
