Bias-corrected estimators for dispersion models with dispersion covariates

In this paper we discuss bias-corrected estimators for the regression and the dispersion parameters in an extended class of dispersion models (Jorgensen, 1997b). This class extends the regular dispersion models by letting the dispersion parameter vary throughout the observations, and contains the dispersion models as particular case. General formulae for the O(n(-1)) bias are obtained explicitly in dispersion models with dispersion covariates, which generalize previous results obtained by Botter and Cordeiro (1998), Cordeiro and McCullagh (1991), Cordeiro and Vasconcellos (1999), and Paula (1992). The practical use of the formulae is that we can derive closed-form expressions for the O(n(-1)) biases of the maximum likelihood estimators of the regression and dispersion parameters when the information matrix has a closed-form. Various expressions for the O(n(-1)) biases are given for special models. The formulae have advantages for numerical purposes because they require only a supplementary weighted linear regression. We also compare these bias-corrected estimators with two different estimators which are also bias-free to order O(n(-1)) that are based on bootstrap methods. These estimators are compared by simulation. (C) 2011 Elsevier B.V. All rights reserved.

Bias correction in a multivariate normal regression model with general parameterization

This paper derives the second-order biases Of maximum likelihood estimates from a multivariate normal model where the mean vector and the covariance matrix have parameters in common. We show that the second order bias can always be obtained by means of ordinary weighted least-squares regressions. We conduct simulation studies which indicate that the bias correction scheme yields nearly unbiased estimators. (C) 2009 Elsevier B.V. All rights reserved.

Interfacial Electron Transfer Dynamics Following Laser Flash Photolysis of [Ru(bpy)(2)((4,4 `-PO(3)H(2))(2)bpy)](2+) in TiO(2) Nanoparticle Films in Aqueous Environments

Nanosecond laser flash photolysis has been used to investigate injection and back electron transfer from the complex [(Ru-(bpy)(2)(4,4`-(PO(3)H(2))(2)bpy)](2+) surface-bound to TiO(2) (TiO(2)-Ru(II)). The measurements were conducted under conditions appropriate for water oxidation catalysis by known single-site water oxidation catalysts. Systematic variations in average lifetimes for back electron transfer, - were observed with changes in pH, surface coverage, incident excitation intensity, and applied bias. The results were qualitatively consistent with a model involving rate-limiting thermal activation of injected electrons from trap sites to the conduction band or shallow trap sites followed by site-to-site hopping and interfacial electron transfer, TiO(2)(e(-))-Ru(3+) -> TiO(2)-Ru(2+). The appearance of pH-dependent decreases in the efficiency of formation of TiO(2)-Ru(3+) and in incident-photon-to-current efficiencies with the added reductive scavenger hydroquinone point to pH-dependent back electron transfer processes on both the sub-nanosecond and millisecond-microsecond time scales, which could be significant in limiting long-term storage of multiple redox equivalents.

Evidence for diffusional coupling in electrochemical thin layers: implications for surface coverage calibration via electrochemical infrared spectroscopy

The time dependence of the concentration of CO2 in an electrochemical thin layer cavity is studied with Fourier transform infrared spectroscopy (FTIR) in order to evaluate the extent to which the thin layer cavity is diffusionally decoupled from the surrounding bulk electrolyte. For the model system of CO on Pt(111) in 0.1 M HClO4, it is found that the concentration of CO2, formed by electro-oxidation of CO, equilibrates rapidly with the surrounding bulk electrolyte. This rapid equilibration indicates that there is diffusion out of the thin layer, even on the short time scales of typical infrared experiments (1-3 min). However, since the measured CO2 absorbance intensity as a function of time is reproducible to within 10%, a new time-dependent method for surface coverage calibration using solution-phase species is proposed.

On the apparent lack of preferential site occupancy and electrooxidation of CO adsorbed at low coverage onto stepped platinum surfaces

We report time evolution studies of low coverage CO adsorption (surface hydrogen site blocking < 40%) and oxidative stripping on stepped Pt(776) and Pt(554) surfaces. It was observed that there is no preferential site occupancy for CO adsorption on step or terrace. It is proposed that CO adsorption onto these surfaces is a random process, and after CO adsorption there is no appreciable shift from CO-(111) to CO-(110) sites. This implies that after adsorption, CO molecules either have a very long residence time, or that the diffusion coefficient is much lower than previously thought. After CO electrooxidation the sites released included both terrace (111) and step (110) orientations. For surface hydrogen site blocking > 40%, the lateral interactions might play a role in the preferential CO site occupancy. (C) 2011 Elsevier B.V. All rights reserved.

Likelihood estimate of treatment effects under selection bias

We consider methods for estimating causal effects of treatment in the situation where the individuals in the treatment and the control group are self selected, i.e., the selection mechanism is not randomized. In this case, simple comparison of treated and control outcomes will not generally yield valid estimates of casual effects. The propensity score method is frequently used for the evaluation of treatment effect. However, this method is based onsome strong assumptions, which are not directly testable. In this paper, we present an alternative modeling approachto draw causal inference by using share random-effect model and the computational algorithm to draw likelihood based inference with such a model. With small numerical studies and a real data analysis, we show that our approach gives not only more efficient estimates but it is also less sensitive to model misspecifications, which we consider, than the existing methods.

Media Coverage and Charitable Giving After the 2004 Tsunami

Media coverage of humanitarian crises is widely believed to influence charitable giving, yet this assertion has received little empirical scrutiny. Using Internet donations after the 2004 tsunami as a case study in a tobit framework, we show that media coverage of disasters increases charitable donations, with an additional minute of nightly news coverage increasing donations by 0.036 standard deviations from the mean. We repeat the analysis using instrumental variables in a tobit model to account for endogeneity, and the estimates are unchanged. We also show that the magnitude and sign of media impact vary by news source and relief agency.

LIGHT COVERAGE ON COLBY COLLEGE CAMPUS

http://digitalcommons.colby.edu/atlasofmaine2009/1030/thumbnail.jpg

Light Coverage on Colby College Campus

Outdoor lighting is an essential component for nighttime safety on college campuses. Outdoor lighting on Colby College campus is not uniform, leaving some areas with minimal light. The purpose of this project is to analytically evaluate if and where major walkways on Colby College have inadequate lighting. While we were unable to define inadequate lighting, we found that most paths on campus do appear to be well lit, while in general open spaces on campus have the lowest light levels.

Is there a price puzzle in Brazil? An application of Bias-Corrected Bootstrap

Using data from the United States, Japan, Germany , United Kingdom and France, Sims (1992) found that positive innovations to shortterm interest rates led to sharp, persistent increases in the price level. The result was conÖrmed by other authors and, as a consequence of its non-expectable nature, was given the name "price puzzle" by Eichenbaum (1992). In this paper I investigate the existence of a price puzzle in Brazil using the same type of estimation and benchmark identiÖcation scheme employed by Christiano et al. (2000). In a methodological improvement over these studies, I qualify the results with the construction of bias-corrected bootstrap conÖdence intervals. Even though the data does show the existence of a statistically signiÖcant price puzzle in Brazil, it lasts for only one quarter and is quantitatively immaterial

A panel data approach to economic forecasting: the bias-corrected average forecast

In this paper, we propose a novel approach to econometric forecasting of stationary and ergodic time series within a panel-data framework. Our key element is to employ the (feasible) bias-corrected average forecast. Using panel-data sequential asymptotics we show that it is potentially superior to other techniques in several contexts. In particular, it is asymptotically equivalent to the conditional expectation, i.e., has an optimal limiting mean-squared error. We also develop a zeromean test for the average bias and discuss the forecast-combination puzzle in small and large samples. Monte-Carlo simulations are conducted to evaluate the performance of the feasible bias-corrected average forecast in finite samples. An empirical exercise based upon data from a well known survey is also presented. Overall, theoretical and empirical results show promise for the feasible bias-corrected average forecast.

Inflationary bias and state owned financial institutions

This article explains why the existence of state owned financial institutions makes it more difficult for a country to balance its budget. We show that states can use their financiaI institutions to transfer their deficits to the federal govemment. As a result, there is a bias towards Iarge deficits and high inflation rates. Our model also predicts that state owned financiaI institutions should underperform the market, mainly because they concentrate their portfolios on non-performing loans to their own shareholders, that is, the states. Brazil and Argentina are two countries with a history of high inflation that confirm our predictions .