Choice Of Estimation Method Research Articles

A comparison of PM2.5 exposure estimates from different estimation methods and their associations with cognitive testing and brain MRI outcomes

BackgroundReported associations between particulate matter with aerodynamic diameter ≤2.5 μm (PM2.5) and cognitive outcomes remain mixed. Differences in exposure estimation method may contribute to this heterogeneity. ObjectivesTo assess agreement between PM2.5 exposure concentrations across 11 exposure estimation methods and to compare resulting associations between PM2.5 and cognitive or MRI outcomes. MethodsWe used Visit 5 (2011–2013) cognitive testing and brain MRI data from the Atherosclerosis Risk in Communities (ARIC) Study. We derived address-linked average 2000–2007 PM2.5 exposure concentrations in areas immediately surrounding the four ARIC recruitment sites (Forsyth County, NC; Jackson, MS; suburbs of Minneapolis, MN; Washington County, MD) using 11 estimation methods. We assessed agreement between method-specific PM2.5 concentrations using descriptive statistics and plots, overall and by site. We used adjusted linear regression to estimate associations of method-specific PM2.5 exposure estimates with cognitive scores (n = 4678) and MRI outcomes (n = 1518) stratified by study site and combined site-specific estimates using meta-analyses to derive overall estimates. We explored the potential impact of unmeasured confounding by spatially patterned factors. ResultsExposure estimates from most methods had high agreement across sites, but low agreement within sites. Within-site exposure variation was limited for some methods. Consistently null findings for the PM2.5-cognitive outcome associations regardless of method precluded empirical conclusions about the potential impact of method on study findings in contexts where positive associations are observed. Not accounting for study site led to consistent, adverse associations, regardless of exposure estimation method, suggesting the potential for substantial bias due to residual confounding by spatially patterned factors. DiscussionPM2.5 estimation methods agreed across sites but not within sites. Choice of estimation method may impact findings when participants are concentrated in small geographic areas. Understanding unmeasured confounding by factors that are spatially patterned may be particularly important in studies of air pollution and cognitive or brain health.

Accuracy and precision of depth-resolved estimation of attenuation coefficients in optical coherence tomography.

Parametric imaging of the attenuation coefficient using optical coherence tomography (OCT) is a promising approach for evaluating abnormalities in tissue. To date, a standardized measure of accuracy and precision of by the depth-resolved estimation (DRE) method, as an alternative to least squares fitting, is missing. We present a robust theoretical framework to determine accuracy and precision of the DRE of . We derive and validate analytical expressions for the accuracy and precision of determination by the DRE using simulated OCT signals in absence and presence of noise. We compare the theoretically achievable precisions of the DRE method and the least-squares fitting approach. Our analytical expressions agree with the numerical simulations for high signal-to-noise ratios and qualitatively describe the dependence on noise otherwise. A commonly used simplification of the DRE method results in a systematic overestimation of the attenuation coefficient in the order of , where is the pixel stepsize. When , is reconstructed with higher precision by the depth-resolved method compared to fitting over the length of an axial fitting range . We derived and validated expressions for the accuracy and precision of DRE of . A commonly used simplification of this method is not recommended as being used for OCT-attenuation reconstruction. We give a rule of thumb providing guidance in the choice of estimation method.

Regression Analysis of Macroeconomic Conditions and Capital Structures of Publicly Listed British Firms

Using an unbalanced panel of 922 non-financial companies publicly listed on the London Stock Exchange during January 1995 and September 2014, this article tests the predictions of Pecking Order Theory (POT), Trade-off Theory (TOT) and Market Timing Theory (MTT) of capital structure through the lens of macroeconomic conditions. We find strong evidence that leverage is negatively associated with the business cycle but positively related to stock market performance, which is consistent with POT. In addition, leverage is negatively related to financial market risk, as predicted by TOT. Furthermore, leverage is positively related to credit supply, which is in line with both the POT and TOT. Finally, there is no evidence in support of MTT. The above results are robust with respect to the measurement of macroeconomic variables, the choice of estimation methods and the inclusion of a dummy variable to account for the effect of the 2008 financial crisis. An important implication is that, because firms tend to be highly levered during business cycle downturns, expansionary fiscal and monetary policies to encourage more business borrowings may not be effective after all.

A comparative study on the performance of maximum likelihood, generalized least square, scale-free least square, partial least square and consistent partial least square estimators in structural equation modeling

Structural equation modeling offers various estimation methods for estimating parameters. The most used method in covariance-based structural equation modeling (CB-SEM) is the maximum likelihood (ML) estimator. The ML estimator is typically used when fitting models with normally distributed data. The growth of partial least squares path modeling (PLS-PM), including consistent partial least squares (PLSc), has also been noticed by researchers in the SEM fields. The PLSc has elevated interest in the scholastic setting in measuring the performance of various estimation methods in structural equation modeling. The choice of estimation methods has substantial impact in yielding parameter estimates. There could be a trade-off among the estimation methods’ ability to deal with different types of data based on the model tested. Accordingly, this study aims to compare the performance of ML, generalized least squares (GLS), and scale-free least squares (SFLS) for CB-SEM as well as partial least squares (PLS) and consistent partial least squares (PLSc). Multivariate normal data were generated using Monte Carlo simulation with pre-determined population parameters and sample sizes using R Programming packages. To produce the estimated values, data analysis was performed using AMOS and SmartPLS for CB-SEM and PLS-SEM, respectively. The findings illustrate notable similarities between CB-SEM (ML) and PLS-SEM results when the true indicator loading is certainly high.

The marginal cost of track renewals in the Swedish railway network: Using data to compare methods

We analyze the differences between corner solution and survival models in estimating the marginal cost of track renewals. Both approaches describe the renewal process in intuitively similar ways but have several methodological distinctions. Using Swedish data for the 1999–2016 period, results suggest the median marginal costs per gross ton-km from corner solution and survival models are SEK 0.0066 and SEK 0.0031, respectively. Since several European countries use information about marginal costs as a basis for track user charges, the choice of estimation method is obviously important. Our conclusion is that the corner solution model is more appropriate in this case, as this method considers the impact traffic has both on the probability of renewal and on the size of the renewal cost. The survival approach does not consider the latter as part of the estimations, which is problematic when we have systematic cost variations due to traffic and infrastructure characteristics.

International Real Estate Review

One of the fundamental concepts in financial economics is the cost of equity capital. The cost of equity is an important tool often used by a firm as a capital budgeting threshold for the required rate of return. The cost of equity of a firm also represents the compensation the market demands in exchange for owning the asset and bearing the risk of ownership. This paper focuses on the cost of equity capital estimates for a particular U.S. industry, the real estate investment trust (REIT) industry, to highlight the key role played by the choice of estimation method on the distant forecast. By using a comprehensive sample of 51 REITs over the period of January 1997 to December 2014, we compare the ¡§hybrid beta¡¨ approach developed by Cosemans et al. (2016) with the Carhart four-factor model, the REIT-factor model in Chen et al. (2012) and the five-factor model formulated by Fama and French (2015). Our results demonstrate the superiority of the ¡§hybrid beta¡¨ approach, which almost always produces, at the firm and portfolio-levels, absolute forecast errors that are lower than those of the other models implemented in our study.

Analysis of Cost Efficiency of Indian Life Insurers: A comparison of Quantity vs Value based DEA Approach

Abstract In the context of measuring economic performance, efficiency and productivity of Indian life insurance firms, there are studies using the Data Envelopment Analysis (DEA) methodology. In this paper, the difference between the quantity based approach and value based approach is highlighted and elaborated using data of Indian life insurers operational over the period 2005–06 to 2015–16. There are both advantages and disadvantages of using DEA, as highlighted in the theoretical literature. In particular, the efficiency estimates are heavily influenced by the selection of inputs and outputs. This study provides an insight on technical efficiency and innovates in terms of data use and is the first study on the Indian insurance industry to compute cost and allocative efficiencies. Four hypotheses were tested in the study. First, there were initially improvements in efficiency but in recent years, clearly there is stagnation. Second, the results support views of Tone and Sahoo (2005) and Sen (2010), that the public life insurer, the Life Insurance Corporation of India is cost inefficient. The private life insurers need to reallocate resources to improve overall efficiency. LICI was found to be technically efficient but remained cost inefficient. Third, the traditional Farrell based cost efficiency estimates are significantly different from Tone (2002) alternative approach. Therefore, choice of estimation method is important. Fourth, non-discretionary factors such as age, premium growth and size of the insurers along with regulations pertaining to solvency affect cost efficiency. Key financial ratios such as expense ratio, commission ratio, conservation ratio and persistency ratio, and retention ratio are used to statistically establish their relationship with the different efficiency estimates. Results also show that entry of a new insurer may negatively affect cost efficiency of an existing insurer but foreign equity could positively improve cost efficiency.

The use of meta-analysis in research on corporate cash holdings speed of adjustment

In empirical research significant diversity of corporate cash holdings speed of adjustment (SOA) estimates can be observed. It is possible that some of the results are affected by publication selection bias. Articles whose results are clearly in line with economic theories may be preferred by authors and reviewers and, consequently, conclusions from this area can be published more frequently. The aim of this article is to verify whether there is a publication selection bias with respect to studies related to corporate cash holdings adjustments and to investigate the sources of heterogeneity in cash holdings SOA estimates. The statistical method used in the study was meta-analysis, which allows a combined analysis of the results from independent research. Meta-analysis enables to verify the occurrence of the publication selection bias and to explain the heterogeneity of the results presented in articles. The study was based on data collected asa result of a review of the literature published between 2003 and 2017. On the basis of information on 402 estimates from 58 different studies it has been shown that the publication selection bias does not occur. The Bayesian Model Averaging was used for modelling. It was identified that the characteristics associated with the data set used in the study, model specification and the estimation method significantly affect the hetero-geneity of corporate cash holdings SOA estimates. This diversity is determined, among others, by the choice of estimation method, length of the period covered by the analysis and characteristics of the market environment of the concerned entities.

Measures of fit impacts: Application to the causal model of consumer involvement

Using the Monte Carlo simulation method, this study analyzes the impacts on fit indices by the degree of nonnormality of variables, the sample size, and the choice of estimation method. To address these issues, we use the causal model of consumer involvement as elaborated by Mittal and Lee. Results of this study show that adjusted goodness of fit index (AGFI) and goodness of fit index (GFI) are subject to variation in sample size, and their use requires a sample size of at least 300 observations to be reliable. Comparative fit index (CFI) and root mean square error of approximation (RSMEA) are more reliable with the generalized least squares (GLS) compared with maximum likelihood estimation (MLE) method under different settings of sample size and degree of nonnormality. Finally, for the standardized root mean square residual (SRMR), it is recommended that it is used with the MLE method. This study provides prescriptions for the choice of fit indices and the requirements of sample size and estimation method to test the causal model of consumer involvement. The method used here can be extended to any model before fitting it to real data. It helps researchers to prevent conflictual results regarding the choice of fit indices.

Investigating applications of university productivity measurement models using Australian data

ABSTRACTThe paper contributes to the growing and often controversial study of higher education productivity measurement. The paper clarifies core productivity ideas, and considers alternative models for productivity assessment. Results from these models are explored using data from Australian higher education. Findings reveal implications for the technique and the practice of higher education productivity measurement. The paper provides evidence that productivity change estimates in higher education are not robust to the choice of estimation method. The research then demonstrates how the practice of higher education productivity measurement may benefit from approaches different to conventional econometric means of estimating frontier efficiency. Focusing on the drivers of productivity change and on the value weighting of data elements in models may provide more nuanced and actionable information for stakeholders and decision-makers. The paper concludes by urging more work to advance this field.

Matched Comparison Group Design Standards in Systematic Reviews of Early Childhood Interventions.

Systematic reviews assess the quality of research on program effectiveness to help decision makers faced with many intervention options. Study quality standards specify criteria that studies must meet, including accounting for baseline differences between intervention and comparison groups. We explore two issues related to systematic review standards: covariate choice and choice of estimation method. To help systematic reviews develop/refine quality standards and support researchers in using nonexperimental designs to estimate program effects, we address two questions: (1) How well do variables that systematic reviews typically require studies to account for explain variation in key child and family outcomes? (2) What methods should studies use to account for preexisting differences between intervention and comparison groups? We examined correlations between baseline characteristics and key outcomes using Early Childhood Longitudinal Study-Birth Cohort data to address Question 1. For Question 2, we used simulations to compare two methods-matching and regression adjustment-to account for preexisting differences between intervention and comparison groups. A broad range of potential baseline variables explained relatively little of the variation in child and family outcomes. This suggests the potential for bias even after accounting for these variables, highlighting the need for systematic reviews to provide appropriate cautions about interpreting the results of moderately rated, nonexperimental studies. Our simulations showed that regression adjustment can yield unbiased estimates if all relevant covariates are used, even when the model is misspecified, and preexisting differences between the intervention and the comparison groups exist.

The antipoverty effect of public rental housing in Hong Kong

This paper examines the antipoverty effect of public rental housing (PRH) in Hong Kong based on a comparison of estimated imputed rents from PRH through regression-based and stratified rental equivalence methods. Empirical analysis shows that stratified equivalence method tended to generate a larger effect of poverty rate reduction and smaller effect of poverty gap reduction than regression-based method. The study identified a trend towards upwardly biased estimate of public imputed rent in the implementation of stratified equivalence method in Hong Kong where limited strata was available for the estimation. The development of antipoverty measures may be misguided if the stratified equivalence method is used in its current form in Hong Kong. The paper suggests that the choice of estimation method has important implications for evaluating the pros and cons of PRH from both poverty reduction and budgetary perspectives.

Cost Efficiency Analysis Based on the DEA and StoNED Models: Case of Norwegian Electricity Distribution Companies

Our paper applies data envelopment analysis (DEA) and stochastic non-parametric envelopment of data (StoNED) to measure cost efficiency of electricity distribution companies. The data cover 123 Norwegian electricity distribution companies during 2004-2010, and the performance of these companies is compared across the two models with and without environmental variables, i.e., variables that account for local conditions that affect the companies’ costs. The results indicate that the cost efficiency estimates with the StoNED approach are much higher than with the DEA method when we do not consider environmental variables. It shows that the choice of estimation methods is important with respect to the estimated impact of environmental variables on the performance. In addition, the inclusion of the environmental variables has considerable effect on the classification of companies with respect to local returns to scale.

Restoration of Poisson noise corrupted digital images with nonlinear PDE based filters along with the choice of regularization parameter estimation

In this paper, the reconstruction of three nonlinear partial differential equation (PDE) based filters adapted to Poisson noise statistics have been proposed in a variational framework for restoration and enhancement of digital images corrupted with Poisson noise. The proposed and examined PDE based filters include total variation adapted to Poisson noise in L-1 framework; anisotropic diffusion; and complex diffusion based methods adapted to Poisson noise in L-2 framework. The resulting filters contain two terms namely data fidelity and regularization or smoothing function. The data fidelity term is Poisson likelihood term and the regularization functions are PDE based filters. Other choices for the regularization functions have also been presented. The two terms in the proposed filters are coupled with a regularization parameter lambda which makes a proper balance between the two terms during the filtering process. The choice of method for estimation of regularization parameter lambda plays an important role. In this study, the various regularization parameter estimation methods for Poisson noise have also been presented and their suitability has been examined. The resulting optimization problems are further investigated for efficient implementation for large scale problems. For estimating the regularization parameter, three choices are considered for Poisson noise case which are discrepancy principles, generalized cross validations (GCV), and unbiased predictive risk estimate (UPRE). GCV and UPRE functions are further other optimization problems in addition to main image reconstruction problem. For minimizing the GCV and UPRE functions, the methods of Conjugate Gradients (CG) is used. For digital implementations, all schemes have been discretized using finite difference scheme. The comparative analysis of the proposed methods are presented in terms of relative norm error, improvement in SNR, MSE, PSNR, CP and MSSIM for an adaptive value of regularization parameter calculated by every methods in consideration. Finally, from the obtained results it is observed that the anisotropic diffusion based method adapted to Poisson noise gives better results in comparison to other methods in consideration along with choice of GCV for regularization parameter selection.

Empirical Research on Ownership Structure and Corporate Performance Based on the Perspective of Dynamic Endogeneity

Abstract Most previous literatures deem ownership structure as exogenous variables to deal with and believe there only exists a static relationship between ownership structure and corporate performance. In this paper, we choose China's 509 listed companies of Shanghai and Shenzhen during 1999-2008. With dynamic panel model, after controlling effect of past performance, simultaneity, as well as unobservable heterogeneity, we come to the following conclusions: (1) There is a two-way interaction effect between the proportion of largest shareholding and corporate performance; (2)Whether in a static or dynamic model, the proportion of management ownership is uncorrelated with performance; (3)Some weak evidence shows there exists intertemporal effect between ownership structure and corporate performance. However, the relationship is not stable, which depends on the definition of performance and the choice of estimation methods.

Age-related changes in mechanical and metabolic energy during typical gait

The purpose of the study was to investigate and report age-related changes in walking energy expenditure using different methods of energy estimation. For 81 children and 16 adults (3–35 years) energy expenditure was investigated by using the following methods: analysis of energy changes of the centre of body mass (external and internal mechanical work), sum of segmental energies, sum of net joint work and gross and net metabolic cost, as well as net non-dimensional oxygen cost. Different methods of energy estimation not only show different outcome results but also different age-related changes. Significant changes were found for negative net joint work, external mechanical work and recovery as well as sum of segmental energies, until 9, 11 and 19 years respectively. Positive net joint work showed no differences between age groups and the differences for internal work did not suggest development. Metabolic energy showed significant changes until adult age. Gross cost decreases with increasing age in children and, although more gradually, still in adolescents. Net and net non-dimensional cost shows a more constant decrease with increasing age until adulthood. Therefore, the choice of estimation method and the use of age-related reference data when evaluating young patients should be carefully considered. For interpretation of oxygen consumption in children the use of net is superior to gross cost, but even after net non-dimensional normalization, age-related reference data should be used.

Comparison of Parametric, Semi-Parametric and Non-Parametric Methods in Bankruptcy Prediction

This paper compares parametric, semi-parametric and non-parametric methods in prediction of bankruptcy. Special care is devoted to the effect of choice-based sampling. The choice of the sampling and estimation method lead to a similar trade off. Using choice-based sampling and logit model leads to minimization of risk exposure. Samples unbalanced across groups and Klein and Spady (1993) semi-parametric method allow for better overall prediction accuracy and thus profit maximization. Both the choice of sampling method and the choice of estimation method should be thus made conditional on an explicit objective function of the financial institution in assesing credit risk.

Quantile estimation of frontier production function

The purpose of the paper is to provide new information on the performance of frontier estimation methods, using data from Italian hotel industry. Quantile regression is also suggested as solution to frontier production function estimation. It is shown that, while the choice of estimation methods among conventional techniques significantly affects the economic analysis, quantile regression provides valuable new information by estimating the whole spectrum of production functions corresponding to different efficiency levels. In addition, the method makes available a coherent framework to analyze the performance of the conventional techiniques.

Economic Efficiency and Frontier Techniques

Abstract. Most of the literature related to the measurement of economic efficiency has based its analysis either on parametric or on non‐parametric frontier methods. The choice of estimation method has been an issue of debate, with some researchers preferring the parametric and others the non‐parametric approach. The aim of this paper is to provide a critical and detailed review of both core frontier methods. In our opinion, no approach is strictly preferable to any other. Moreover, a careful consideration of their main advantages and disadvantages, of the data set utilized, and of the intrinsic characteristics of the framework under analysis will help us in the correct implementation of these techniques. Recent developments in frontier techniques and economic efficiency measurement such as Bayesian techniques, bootstrapping, duality theory and the analysis of sampling asymptotic properties are also considered in this paper.

The selection of multinational equity portfolios: forecasting models and estimation risk

The problem considered is the selection of a portfolio of international assets, particularly the forecasting of the inputs to a selection algorithm. Four models of the asset return generating process are considered, two of which ignore the international nature of the universe of assets, two which exploit it in different ways. Several estimation methods are considered for each component: expected return, variance and covariance of returns. The combinations of model and estimation method are first evaluated in terms of their forecasting performance for the components mentioned for the individual assets. The universe used is the components of the Financial Times Eurotrack 100 Index. Significant differences were found between the forecasting accuracy of the methods considered for each component. In the final stage of the analysis, a comparison of the returns on portfolios chosen using each combination showed a significant difference. The analysis suggests that the choice of estimation method is more critical than the choice of pricing model.