Search Results
Report
On binscatter
Binscatter is a popular method for visualizing bivariate relationships and conducting informal specification testing. We study the properties of this method formally and develop enhanced visualization and econometric binscatter tools. These include estimating conditional means with optimal binning and quantifying uncertainty. We also highlight a methodological problem related to covariate adjustment that can yield incorrect conclusions. We revisit two applications using our methodology and find substantially different results relative to those obtained using prior informal binscatter methods. ...
Working Paper
New Estimates of the Lerner Index of Market Power for U.S. Banks
The Lerner index is widely used to assess firms' market power. However, estimation and interpretation present several challenges, especially for banks, which tend to produce multiple outputs and operate with considerable inefficiency. We estimate Lerner indices for U.S. banks for 2001-18 using nonparametric estimators of the underlying cost and profit functions, controlling for inefficiency, and incorporating banks' off-balance-sheet activities. We find that mis-specification of cost or profit functional forms can seriously bias Lerner index estimates, as can failure to account for ...
Report
Option-implied term structures
This paper proposes a nonparametric sieve regression framework for pricing the term structure of option spanning portfolios. The framework delivers closed-form, nonparametric option pricing and hedging formulas through basis function expansions that grow with the sample size. Novel confidence intervals quantify term structure estimation uncertainty. The framework is applied to estimating the term structure of variance risk premia and finds that a short-run component dominates market excess return predictability. This finding is inconsistent with existing asset pricing models that seek to ...
Working Paper
Traffic Noise in Georgia: Sound Levels and Inequality
Using Lorenz-type curves, means tests, ordinary least squares, and locally weighted regressions (LWR), we examine the relative burdens of whites, blacks, and Hispanics in Georgia from road and air traffic noise. We find that whites bear less noise than either blacks or Hispanics and that blacks tend to experience more traffic noise than Hispanics. While every Metropolitan Statistical Area (MSA) showed that blacks experienced relatively more noise than average, such a result did not hold for Hispanics in roughly half of the MSAs. We find much heterogeneity across Census tracts using LWR. For ...
Working Paper
Forecasting US Inflation Using Bayesian Nonparametric Models
The relationship between inflation and predictors such as unemployment is potentially nonlinear with a strength that varies over time, and prediction errors error may be subject to large, asymmetric shocks. Inspired by these concerns, we develop a model for inflation forecasting that is nonparametric both in the conditional mean and in the error using Gaussian and Dirichlet processes, respectively. We discuss how both these features may be important in producing accurate forecasts of inflation. In a forecasting exercise involving CPI inflation, we find that our approach has substantial ...
Working Paper
Nonparametric Estimation of Lerner Indices for U.S. Banks Allowing for Inefficiency and Off-Balance Sheet Activities
The Lerner index is widely used to assess firms' market power. However, estimation and interpretation present several challenges, especially for banks, which tend to produce multiple outputs and operate with considerable inefficiency. We estimate Lerner indices for U.S. banks for 2001-18 using nonparametric estimators of the underlying cost and profit functions, controlling for inefficiency, and incorporating banks' off-balance-sheet activities. We find that mis-specification of cost or profit functional forms can seriously bias Lerner index estimates, as can failure to account for ...