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.     

Sticky Valuations,Aggregation Effects,and Property Indices

Previous studies on real estate smoothing have generally focused on the second moment of returns for individual properties. Although this body of research has developed plausible reasons for explaining the observed lower risk associated with real estate, no explanation has, however, been offered to account for the large difference in serial correlation at the individual property level compared with the index level. This article addresses this issue and also offers an explanation for the difference in serial correlation observed with different frequency real estate indices. Employing the framework developed by Holbrook Working (1960), we argue that the high levels of serial correlation typically observed in real estate indices results from a combination of random and sticky appraisals that induce cross-correlations between the component returns. Using the concept of sticky values we question the results of Lai and Wang (1998) in which they argue that the variance of appraisal-based returns should always be greater than true returns. We argue that a pragmatic conclusion regarding volatility should be conditioned on the underlying stochastic processes. We draw a distinction between serial cross-sectional and temporal sticky appraisal processes that influence smoothing at the index and individual property levels. Our results indicate that smoothing does not appear to be a serious issue at the individual property level. However, when different appraisal processes are aggregated into an index the underlying cross-correlation between those processes can induce high levels of smoothing.     

The Impact of SFAS No. 114 on the Linear Information Dynamic for Commercial Banks

Increase (decrease) in loan loss provisions would decrease (increases) bank earnings, but increase (decreases) regulatory capital. Previous studies have separately documented earnings and capital management behavior via loan loss provisions by commercial banks. However, it is difficult to isolate a bank's demand for increasing earnings from its demand for regulatory capital because earnings is a source of capital. Based on the objective bank function, this study investigates the impact of SFAS No. 114 on the information content of loan loss provisions in relation to both earnings quality and capital adequacy in a linear information dynamic framework. Test results show that the association between market value with loan loss provisions became significantly stronger for commercial banks in the post- than in the pre-adoption period. As a result, SFAS No. 114 is also found to positively affect the association of market value with both bank earnings and regulatory capital through the clean surplus relation because of the higher value relevance of loan loss provisions. The findings thus provide empirical evidence that SFAS No. 114 has significantly complemented banking regulations in enhancing (reducing) the (dispersion from the) accounting measurement construct of loan loss provisions.     

Earnings Smoothing,Cash Flow Volatility,and CEO Cash Bonus

Prior studies generally relate managers’ decisions to smooth earnings to their desire to maximize their overall compensation and to smooth their consumption. However, earnings smoothing could also be driven by the firm's expected benefits from reporting a smooth earnings stream. Our paper provides empirical support for the latter explanation of earnings smoothing. Specifically, we find that while CEO bonus on average increases with earnings smoothing, the increase is larger when the firm's cash flow volatility is higher. Further, CEO bonus is shielded from the negative effects of lower earnings arising from the need to report a smoother earnings stream.     

Lognormal Approximation of Complex Path-Dependent Pension Scheme Payoffs

Abstract

This paper analyzes an explicit return smoothing mechanism which has recently been introduced as part of a new type of pension savings contract that has been offered by Danish life insurers. We establish the payoff function implied by the return smoothing mechanism and show that its probabilistic properties are accurately approximated by a suitably adapted lognormal distribution. The quality of the lognormal approximation is explored via a range of simulation-based numerical experiments, and we point to several other potential practical applications of the paper's theoretical results.     

Income smoothing from a Census X-12 perspective

Corporate income smoothing has been the focus of much attention, yet relatively little is known about the key characteristics of income-smoothing firms. To address this issue, the current study uses quarterly data with Census X-12 analysis in a novel way to identify firms where the degree of random variability in earnings is less than the degree of random variability in sales (EVAR < SVAR). Prior research views such firms as effective smoothers, since most firms have scale-free variability profiles in the opposite direction (EVAR > SVAR). Large-sample US results identify these exceptions throughout a broad cross section of firms, but smaller and less profitable firms tended to have a higher incidence rate. Results also indicate that effective smoothers exhibited higher earnings persistence.     

Production smoothing in a serial supply chain: A laboratory investigation

The purpose of this paper is to examine production smoothing in supply chains. Using the controlled setting of the laboratory, we systematically investigate supply chain features that lead to production smoothing. In contrast to prior laboratory studies of the bullwhip effect, we find that the bullwhip effect disappears in several of our experiments. More importantly, our study shows that when customer demand has a predictable seasonal component, retailers smooth orders. This behavior is more pronounced when changing order levels is costly. The results demonstrate how simplifying the structure of the supply chain leads to production smoothing behavior.     

Inside Agency: The Rise and Fall of Nortel

By employing the theoretical template provided by agency theory, this article contributes a detailed clinical analysis of a large multinational Canada-headquartered telecommunications company, Nortel. Our analysis reveals a twenty-first century norm of usual suspects: a CEO whose compensation is well above those of his peers, a dysfunctional board of directors, acts of income smoothing to preserve the confidence of volatile investors, and revelations of financial irregularities followed by a downfall. In many ways, the spectacular rise and – sudden – fall of Nortel illustrates excesses of actors within, and contradictions of the system of corporate governance implied by the agency model. Furthermore, this case illustrates limitations of the agency framework in complex situations with short-term oriented investors.     

A white-boxed ISSM approach to estimate uncertainty distributions of Walmart sales

We present our solution for the M5 Uncertainty competition. Our solution ranked sixth out of 909 submissions across all hierarchical levels and ranked first for prediction at the finest level of granularity (product-store sales, i.e. SKUs). The model combines a multi-stage state-space model and Monte Carlo simulations to generate the forecasting scenarios (trajectories). Observed sales are modelled with negative binomial distributions to represent discrete over-dispersed sales. Seasonal factors are handcrafted and modelled with linear coefficients that are calculated at the store-department level.     

Simultaneous borrowing of information across space and time for pricing insurance contracts: An application to rating crop insurance policies

Changing climate and technology can often lead to nonstationary losses across both time and space for a variety of insurance lines including property, catastrophe, health, and life. As a result, naive estimation of premium rates using past losses will tend to be biased. We present three successively flexible data‐driven methodologies to nonparametrically smooth across both space and time simultaneously, thereby appropriately incorporating possibly nonidentically distributed data into the rating process. We apply these methodologies in estimating U.S. crop insurance premium rates. Crop insurance, with global premiums totaling $4.1 trillion in 2018, is an interesting application as losses exhibit both temporal and spatial nonstationarity. We find significant borrowing of information across both time and space. We also find all three methodologies improve both the stability and accuracy of crop insurance premium rates. The proposed methods may be of relevance for other lines of insurance characterized by spatial and/or temporal nonstationary losses.