Estimating and testing beta pricing models: Alternative methods and their performance in simulations

We conduct a simulation analysis of the Fama and MacBeth[1973. Risk, returns and equilibrium: empirical tests. Journal of Political Economy 71, 607–636.] two-pass procedure, as well as maximum likelihood (ML) and generalized method of moments estimators of cross-sectional expected return models. We also provide some new analytical results on computational issues, the relations between estimators, and asymptotic distributions under model misspecification. The generalized least squares estimator is often much more precise than the usual ordinary least squares (OLS) estimator, but it displays more bias as well. A “truncated” form of ML performs quite well overall in terms of bias and precision, but produces less reliable inferences than the OLS estimator.     

Do non-traditional banking activities reduce bank liquidity creation? Evidence from Vietnam

The study analyzes the impact of engaging in non-traditional banking activities on bank liquidity creation. This strand of research has almost gone unnoticed by academics so far. Based on a dataset of Vietnamese commercial banks from 2007 to 2018, we document that the liquidity creation function of banks decreases with the income from non-traditional banking segments. This impact is observed in both on- and off-balance sheets across multiple robustness tests of the static and dynamic panels regressed by the ordinary least squares method and the generalized method of moments. Further decomposing the non-interest income sources, we find that banks that engage more in non-traditional activities for fees and commissions tend to reduce the liquidity creation more compared to other counterparts. The findings offer insightful implications for regulatory agencies and bank managers in the determination of liquidity creation behavior in emerging markets.     

A Semiparametric Method for Valuing Residential Locations: Application to Automated Valuation

This paper is motivated by automated valuation systems, which would benefit from an ability to estimate spatial variation in location value. It develops theory for the local regression model (LRM), a semiparametric approach to estimating a location value surface. There are two parts to the LRM: (1) an ordinary least square (OLS) model to hold constant for interior square footage, land area, bathrooms, and other structural characteristics; and (2) a non-parametric smoother (local polynomial regression, LPR) which calculates location value as a function of latitude and longitude. Several methods are used to consistently estimate both parts of the model. The LRM was fit to geocoded hedonic sales data for six towns in the suburbs of Boston, MA. The estimates yield substantial, significant and plausible spatial patterns in location values. Using the LRM as an exploratory tool, local peaks and valleys in location value identified by the model are close to points identified by the tax assessor, and they are shown to add to the explanatory power of an OLS model. Out-of-sample MSE shows that the LRM with a first-degree polynomial (local linear smoothing) is somewhat better than polynomials of degree zero or degree two. Future applications might use degree zero (the well-known NW estimator) because this is available in popular commercial software. The optimized LRM reduces MSE from the OLS model by between 5 percent and 11 percent while adding information on statistically significant variations in location value.     

ESTIMATING THE MARKET MODEL ROBUSTLY

There is now considerable evidence in the literature that the ordinary least squares assumptions fail to hold when estimating the market model parameters. This paper describes a robust estimation procedure which provides automatic protection against departures from normality. The market model parameters are then estimated for a sample of securities using both the least squares method and the robust procedure. Analysis shows that the results under the two procedures may differ considerably.     

Multivariate GARCH hedge ratios and hedging effectiveness in Australian futures markets

We use the All Ordinaries Index and the corresponding Share Price Index futures contract written against the All Ordinaries Index to estimate optimal hedge ratios, adopting several specifications: an ordinary least squares‐based model, a vector autoregression, a vector error‐correction model and a diagonal‐vec multivariate generalized autoregressive conditional heteroscedasticity model. Hedging effectiveness is measured using a risk‐return comparison and a utility maximization method. We find that time‐varying generalized autoregressive conditional heteroscedasticity hedge ratios perform better than constant hedge ratios in terms of minimizing risks, but when return effects are also considered, the utility‐based measure prefers the ordinary least squares method in the in‐sample hedge, whilst both approaches favour the conditional time‐varying multivariate generalized autoregressive conditional heteroscedasticity hedge ratio estimates in out‐of‐sample analyses.     

COMMERCIAL BANK RISK: MARKET,INTEREST RATE,AND FOREIGN EXCHANGE

Because of recent structural changes in the balance sheets of banks, regulatory changes in the risk-based capital requirements, and the recent adoption of mark-to-market accounting changes, interest rate risk remains an important issue for commercial banks and an important regulatory concern. Market, interest rate, and foreign exchange risk are estimated for a sample of commercial banks using ordinary least squares from 1986 to 1991. Consistent with earlier studies, the estimated coefficients continue to be unstable. We find that interest rate risk decreases and foreign exchange risk increases. Moreover, the results differ depending on practices of the bank (money center, superregional, or regional). We find evidence consistent with earlier studies that theorize foreign exchange risk is explained by unhedged foreign loan exposure.     

BENCHMARK ERROR AND THE SMALL FIRM EFFECT: A REVISIT

In this study benchmark error is tested for as a source of the small firm effect by comparing the results from ordinary least squares and instrumental variable methods. Although the instrument is not perfect, results show that benchmark error could be a cause of the overall (all months) small firm effect. Results from the instrumental variable method indicate that large January abnormal returns are still present, but that they are offset by negative non-January abnormal returns. As a result, the instrumental variable results show that there is no longer a significant overall “effect,” merely a seasonal effect. It is also found that the results are not sensitive to the choice of the market index.     

Portfolio Inefficiency and the Cross-section of Expected Returns

The Capital Asset Pricing Model implies that (i) the market portfolio is efficient and (ii) expected returns are linearly related to betas. Many do not view these implications as separate, since either implies the other, but we demonstrate that either can hold nearly perfectly while the other fails grossly. If the index portfolio is inefficient, then the coefficients and $R^2$ from an ordinary least squares regression of expected returns on betas can equal essentially any values and bear no relation to the index portfolio's mean-variance location. That location does determine the outcome of a mean-beta regression fitted by generalized least squares.     

A Real Estate Price Index for Thin Markets

This article examines a time-series-based method for estimating real estate price indexes for markets that have few transactions. The proposed method is more parsimonious than the conventional repeat sale or hedonic methods. Also, it is potentially more accurate and less prone to outliers. It achieves this by linking current transactions to preceding transactions, thereby increasing the set of comparable transactions on which to base the index. My experiments confirm that the time-series price index fares much better in thin markets than a benchmark hedonic index. It remains close to the true index when there are few transactions and it does not have the volatility of the benchmark index. While the time-series-based index developed in this article does better than the benchmark hedonic index, one surprise result is that the hedonic index is itself quite robust in small samples.     

Combining the Effects of OLS and Spread on Futures Hedging: Evidence from the Taiwan Stock Index

Abstract:

This study proposes a dynamic hedge ratio, the combined ordinary least squares spread (COLSS), which combines the hedge ratio of ordinary least squares and the value of spread. Using this dynamic ratio for hedging with futures contracts, one can replace spot risk with spread risk. The COLSS captures not only the long-run equilibrium between spot and futures returns, but also the short-run deviation from equilibrium. The spread is forecast by one-period lagged stock market factors and high-order moments that are estimated by an options model. In the in-sample and out-of-sample tests, the COLSS strategy achieves significant risk reduction and outperforms the alternative models by a large utility improvement.     

Estimating Real Estate Price Movements for High Frequency Tradable Indexes in a Scarce Data Environment

Indexes of commercial property prices face much scarcer transactions data than housing indexes, yet the advent of tradable derivatives on commercial property places a premium on both high frequency and accuracy of such indexes. The dilemma is that with scarce data a low-frequency return index (such as annual) is necessary to accumulate enough sales data in each period. This paper presents an approach to address this problem using a two-stage frequency conversion procedure, by first estimating lower-frequency indexes staggered in time, and then applying a generalized inverse estimator to convert from lower to higher frequency return series. The two-stage procedure can improve the accuracy of high-frequency indexes in scarce data environments. In this paper the method is demonstrated and analyzed by application to empirical commercial property repeat-sales data.     

Implicit pricing across residential rental submarkets

This paper examines implicit price differences of rental housing characteristics across various property types to measure whether determinants of rents are valued in the aggregate or separately. The results show that hedonic price functions are not identical across property types, which suggests that ordinary least squares is not the appropriate estimation technique when modeling the implicit prices for an aggregate rental market. Generalized least squares estimation of a random coefficient model removes the restriction of fixed parameters imposed by OLS and allows estimation of implicit prices for rental markets containing multiple property types.     

Simple formulas for standard errors that cluster by both firm and time

When estimating finance panel regressions, it is common practice to adjust standard errors for correlation either across firms or across time. These procedures are valid only if the residuals are correlated either across time or across firms, but not across both. This paper shows that it is very easy to calculate standard errors that are robust to simultaneous correlation along two dimensions, such as firms and time. The covariance estimator is equal to the estimator that clusters by firm, plus the estimator that clusters by time, minus the usual heteroskedasticity-robust ordinary least squares (OLS) covariance matrix. Any statistical package with a clustering command can be used to easily calculate these standard errors.     

Insider ownership and firm value in New Zealand

The relationship between insider stock ownership and firm value is examined for a sample of publicly traded companies in New Zealand. Results in this study confirm earlier findings of a curvilinear relationship reported for larger markets. Insider ownership and firm value are positively related for ownership levels below 14% and above 40% and inversely related at intermediate levels of ownership. These results are fairly robust to different measures of firm performance (Tobin's q, market to book ratio and return on equity) and to several different estimation techniques such as ordinary least squares, two stage least squares, seemingly unrelated regressions and fixed effects regressions on panel data over 1994–1998. Findings in this study contribute to the growing body of international evidence that the non-linear cubic relationship between insider ownership and firm value is robust to differences in governance structures across markets.     

The relationship between stock price index and exchange rate in Asian markets: A quantile regression approach

This paper uses the data of six Asian countries to estimate the relationship between stock price index and exchange rate. According to the portfolio balance effect, these two variables should be negatively related. However, since the evidence from traditional ordinary least squares estimation is not favorable, the quantile regression model is adopted to observe the various relationships between stock and foreign exchange markets. The results show an interesting pattern in the relation of these two markets in Asia, which indicates that the negative relation between stock and foreign exchange markets is more obvious when exchange rates are extremely high or low.     

Methodological Considerations in the Statistical Modeling of Catastrophe Bond Prices

The problem of specifying and fitting a statistical model of the pricing of property catastrophe risk is addressed from a methodological perspective. Notable 21st century published efforts to do this are reviewed. The problem is framed in a business context and various strategic and tactical issues are investigated. A naïve application of ordinary least squares regression is seen to have undesirable consequences. Alternative approaches are offered, including weighted least squares with weights inversely proportional to capital requirements, and alternative functional forms. Recommendations are offered.     

公司治理、机构投资者与盈余管理

本文选取沪深两市2003至2005年(非金融类)上市公司的数据,采用最小二乘法和二阶段回归方法,对公司治理、机构投资者与盈余管理三者的关系进行了实证研究。研究发现:机构投资者在一定程度上参与了上市公司的治理,其持股比例与公司治理水平呈正相关关系,说明机构投资者的持股比例越高越有助于提高公司治理水平;公司治理水平与盈余管理程度呈负相关关系;机构投资者的持股比例与盈余管理程度呈负相关关系,说明机构投资者能有效地抑制管理层的盈余管理行为。     

On the Cross-Sectional Relation between Expected Returns, Betas, and Size

In this paper, I set up scenarios where the mean-variance capital asset pricing model is true and where it is false. Then I investigate whether the coefficients from regressions of population expected excess returns on population betas, and expected excess returns on betas and size, allow us to distinguish between the scenarios. I show that the coefficients from either ordinary least squares or generalized least squares regressions do not allow us to tell whether the model is true or false.     

An analysis of contagion among Asian countries using the canonical model of contagion

Understanding the dependence among economies is relevant to policy makers, central banks and investors in the decision-making process. One important issue for study is the existence of contagion among economies. This work considers the Canonical Model of Contagion by Pesaran and Pick (Journal of Economic Dynamics and Control, 2007), which differentiates contagion from interdependence. The ordinary least squares estimator of this model is biased by the endogenous variables in the model. In this study, instrumental variables are used to decrease the bias of the ordinary least squares estimator. The model is extended to the case of heteroskedastic errors, features that are generally found in financial data. We postulate the conditional volatility of the performance indices as instrumental variables and analyze the validity of these instruments using Monte Carlo simulations. Monte Carlo simulations estimate the distributions of the estimators under the null hypothesis. Finally, the canonical model of contagion is used to analyze the contagion among seven Asian countries.     

Systematic risk estimation in the presence of large and many outliers

It is well recognized that the effect of extreme points on systematic risk estimates is not adequately captured through least squares estimation. This article uses the reweighted least median squares (RWLMS) approach, first proposed by Rousseeuw (1984), which accurately detects outlier presence. Using a large sample of 1350 NYSE/AMEX firms, the article demonstrates that least squares does indeed mask several potentially influential points, that this masking is very pervasive over the sample, and that it may persist even after conventional robust estimation techniques are applied. When these masked points are “unmasked” by RWLMS and zero weights assigned to such observations, the resulting RWLMS estimates of beta are on average 10%–15% smaller. However, a Bayesian treatment of such points (assigning a priori nonzero weights) is possible in both one and two factor market models.