Sorting Bias Research Articles

Is There an Energy Paradox in Fuel Economy? A Note on the Role of Consumer Heterogeneity and Sorting Bias

Previous literature finds that consumers tend to undervalue discounted future energy costs in their purchase decisions for energy-using durables. We argue that this finding could result from ignoring consumer heterogeneity in empirical analyses as opposed to true undervaluation. In the context of automobile demand, we show that, if not accounted for, consumer heterogeneity could lead to sorting, which in turn biases toward zero the estimate of marginal willingness to pay for discounted future fuel costs.

Is There an Energy Paradox in Fuel Economy? A Note on the Role of Consumer Heterogeneity and Sorting Bias

Previous literature finds that consumers tend to undervalue discounted future energy costs in their purchase decisions for energy-using durables. We argue that this finding could result from ignoring consumer heterogeneity in empirical analyses as opposed to true undervaluation. In the context of automobile demand, we show that, if not accounted for, consumer heterogeneity could lead to sorting, which in turn biases toward zero the estimate of marginal willingness to pay for discounted future fuel costs.

Are Cleanups a Waste? Housing Market Responses to Brownfield Cleanups

Cleaning up brownfields such as Superfund sites is expected to catalyze neighborhood change in the vicinity. Several previous studies have estimated changes in housing prices associated with Superfund sites, with mixed results. This paper provides new estimates of price effects associated with cleanups of these brownfields and assesses alternative explanations for previous results. Issues such as stigma, sorting and Tiebout bias, and housing supply conditions motivate the analysis. Prominent models of housing market responses to brownfield cleanups (e.g., Greenstone and Gallagher 2008) raise important issues of how timing and location are handled in the research design. This analysis shows the sensitivity of results to alternative specifications using different (and arguably more robust) definitions of neighborhoods and different milestones in the cleanup process. Housing price effects are estimated using first-differenced models with Census data aggregated at the block-group level for all metro areas in the nation (from 1990 to 2000). The remediation treatment variable is defined based on three different phases in Superfund cleanup process, and proximity is defined based on alternative spatial proximity measures. An instrumental variables estimator, where lagged geographic and political factors instrument for Superfund site cleanups is used. The results show substantial policy endogeneity and significant variation across alternative proximity definitions, as expected. The variation in results by cleanup phase offer insights into the timing of market responses to amenity improvements. The initial results show a generally positive causal impact of progress towards cleaning up Superfund sites, although completion of the high-visibility “construction” phase attenuates some of that positive effect. The presence of significant indirect price effects would suggest that Superfund site cleanups can trigger changes in other aspects of the neighborhood – transforming the composition of the housing stock and neighbor mix in the area. Our results point to a small indirect effect of improved environmental quality, indicating that these brownfield cleanups catalyze minimal neighborhood change. Thus, policy endogeneity, timing, and spatial definitions matter greatly to identifying price impacts of brownfield cleanups. Transforming neighborhoods more generally, however, does not appear to play an important role in brownfield redevelopment.

An empirical analysis of teacher spillover effects in secondary school

This paper examines whether educational production in secondary school involves joint production among teachers across subjects. In doing so, it also provides insights into the reliability of value-added modeling. Teacher value-added to reading test scores is estimated for four different teacher types: English, math, science and social-studies. The initial results indicate that reading output is jointly produced by math and English teachers. However, while falsification tests confirm the English-teacher effects, they cast some doubt about whether the math-teacher effects are free from sorting bias. The results offer a mixed review of the value-added methodology, suggesting that it can be useful but should be implemented cautiously.

Mutual Fund Tournaments: The Sorting Bias and New Evidence

Researchers have found conflicting results concerning the risk-taking response of underperforming first half mutual fund managers to economic incentives. We show analytically, numerically and empirically that the sorting process typically used in prior studies drives risk-taking findings. When we correct for this issue using a new methodology, we find that first half underperforming managers increase the risk of their portfolios in the second half of the year. We also find that this second half “tournament behavior” is unrelated to equity market returns in the first half of the year.

Theoretical analysis of the effects of noise on diffusion tensor imaging.

A theoretical framework is presented for understanding the effects of noise on estimates of the eigenvalues and eigenvectors of the diffusion tensor at moderate to high signal-to-noise ratios. Image noise produces a random perturbation of the diffusion tensor. Power series solutions to the eigenvalue equation are used to evaluate the effects of the perturbation to second order. It is shown that in anisotropic systems the expectation value of the largest eigenvalue is overestimated and the lowest eigenvalue is underestimated. Hence, diffusion anisotropy is overestimated in general. This result is independent of eigenvalue sorting bias. Furthermore, averaging eigenvalues over a region of interest produces greater bias than averaging tensors prior to diagonalization. Finally, eigenvector noise is shown to depend on the eigenvalue contrast and imposes a theoretical limit on the accuracy of simple fiber tracking schemes. The theoretical results are shown to agree with Monte Carlo simulations.

The reduction of the sorting bias in the eigenvalues of the diffusion tensor

One of the most intrinsic quantities when measuring the diffusion properties of a system is the set of principal diffusivities, which represents diffusion along the fibre axes. System noise is a well-known cause of systematic sorting bias when closely spaced diffusivities are ordered according to their magnitude and leads to their inaccurate estimation. This paper describes a new method for the ordering of the principal diffusivities in which local fibre directional coherence was used as a basis for sorting. The method was applied and tested in computer simulations and experimental data acquired in an isotropic water phantom and healthy human brain. Our results demonstrate that this method leads to significant reduction in the sorting bias in comparison to other techniques and thus a more accurate estimation of the eigenvalues. The method is advantageous over other proposed alternatives to the conventional magnitude sorting method because it is not reliant on a large region-of-interest averaging scheme.

Financing constraints and firm heterogeneity in investment behaviour: an application of non-nested tests

Estimating an extended qmodel against Canadian panel date it is demonstrated that the usual practice of conditioning tests of financing constraints on the a priorisorting of firms into financially constrained and unconstrained groups may lead to spurious inference about the existence of credit rationing. The sample sorting bias is minimized by empirically determining the best sorting criterion. The results reveal that while liquidity is the most important and robust determinant of corporate investment, the data do not support critical predictions of either the underinvestment or the overinvestment theories.