Simultaneity Bias Research Articles

Simultaneous Intensity Bias Estimation and Stripe Noise Removal in Infrared Images Using the Global and Local Sparsity Constraints

Infrared (IR) images are often contaminated by obvious intensity bias and stripes, which severely affect the visual quality and subsequent applications. It is challenging to eliminate simultaneously the mixed nonuniformity noise without blurring the fine-image details in low-textured IR images. In this article, we present a new model for simultaneous intensity bias correction and destriping through introducing two sparsity constraints. One is that model fit on the intensity bias should be as accurate as possible. A bivariate polynomial model is built to characterize the global smoothness of the intensity bias. The other constraint is that the unidirectional variational sparse model can concisely represent the direction characteristic of stripe noise. A computationally efficient numerical algorithm based on split Bregman iteration is used to solve the complex optimization problem. The proposed method is fundamentally different from the existing denoising techniques and simultaneously estimates the sharp image, intensity bias, and stripe components. Significant improvement on image quality is achieved on both simulated and real studies. Both qualitative and quantitative comparisons with the state-of-the-art correction methods demonstrate its superiority.

Do Institutions Promote Firm Performance? Evidence from Sub-Saharan Africa

This article examines the roles of institutions in driving firms’ performance using merged Enterprise Panel Survey data sets collected and compiled by World Bank for 23 sub-Saharan Africa (SSA). The study used labour productivity as a proxy of firms’ performance due to its advantages over total factor productivity. To address the problems of multiple sources of heterogeneity and simultaneity biases, the study employed high-dimensional fixed-effects model together with its instrumental variable version to estimate the impacts of institutions on firms’ performance in SSA. The study established that institutions contribute significantly and positively to firms’ performance in SSA. The study infers that control of corruption, government effectiveness, regulatory quality and rule of law are pro-market institutions that effectively create favourable business and investment climates. Other findings of the study include capital–labour ratio, export, high school, average labour costs, research and development (R&D) and capacity utilisation, which all drive the firm’s performance in SSA. Thus, the findings imply that prevailing and future policies on business, trade and investment in SSA should also incorporate institutional reforms as one of the essential measures to rapidly and sustainably boost economic performance in the region.

Flow Effects of Central Bank Asset Purchases on Sovereign Bond Prices: Evidence from a Natural Experiment

AbstractWe estimate the response of sovereign bond prices to net supply shocks caused by purchase operations under the ECB's Public Sector Purchase Programme (PSPP). To avoid simultaneity bias in the estimated relationship between prices and purchases, we exploit a PSPP feature that renders securities temporarily ineligible for reasons unrelated to their prices. Using these purchase restrictions as an instrument to identify exogenous variation in purchase volumes, we find that PSPP causes statistically significant and economically relevant upward price impacts. The impacts are short‐lived and concentrated in securities issued by higher yield jurisdictions and characterized by higher maturity and lower liquidity.

Social transfers and income inequality in OECD countries

In this paper, we estimate the effect of social transfers on disposable income inequality for a large panel of OECD countries. We account for the potential simultaneity bias exploiting an instrumental variable derived using a theoretical model, which identifies the main driver of social transfers from the interaction between electoral systems and partisanship of coalitions winning elections. The empirical analysis shows that a 1% increase in social transfers reduces income inequality by half a percentage point. This analysis also reveals significant heterogeneous results conditional on the level of corruption and appears to be robust to different components of expenditure, alternative model specifications and falsification tests.

Does Innovation Lead to More Productivity? Panel Data Evidence from U.S. Firms

Empirical research on the relationship between innovation and firm level productivity offers conflicting results. We investigate the impact of innovation on labour productivity through the construction of a unique panel data-set that merges information on roughly 5,000 publicly traded U.S. manufacturing firms from 1980-2003 with patent filings over the same time period. The large number of firms and long time span of the data allow us to control for the potentially confounding effects of unobservable firm and/or time specific shocks. While OLS estimates of citation-weighted patent stocks with respect to firm specific labour productivity are positive and statistically significant, corresponding results from instrumental variables (IV) and structural models are larger in magnitude, demonstrating the importance for accounting for potential simultaneity and sample selection bias. We also find that mergers are significantly correlated with a rise in citation weighted patent stocks and research and development (R&D) spending. Our interpretation is that larger firms spend more on research and development (R&D), which results in higher quality patents, and increased labour productivity.

Women directors and performance: evidence from Malaysia

PurposeThe purpose of this paper is to examine the relationship between women on board and the financial performance of Malaysian listed companies.Design/methodology/approachPanel generalised method of moments (GMM) analysis was used over 928 public-listed companies listed on the Malaysian Stock Exchange from 2010 to 2016. GMM overcomes the problem of endogeneity and simultaneity bias. The dependent variable was firm performance, measured by Tobin’s Q. The explanatory variable was gender diversity, proxied by the percentage of women on board, the presence of women and gender heterogeneity indices, Blau and Shannon indices.FindingsMore gender diversification leads to declining firm performance possibly due to issues of tokenism and gender stereotypes.Research limitations/implicationsFurther studies should look into the impact of various types of ownership structures on firm value and also by sectors.Practical implicationsAs women represent half the population in Malaysia, more positive affirmative policies must be introduced to enhance their contributions to society.Social implicationsAs women progress in society, their contributions towards nation building will be significant. Women not only play a nurturing role, but also can shape the destiny of a country.Originality/valueStudies on the relationship between board gender diversity and financial performance have been conducted in the context of a few developed economies. This study contributes to the literature by examining such an issue in a developing economy that has a different environment from that of developed economies.

The effects of offshore production on onshore innovation: Evidence from Japanese multinationals

This paper examines a largely unexplored channel of the effects of offshore production on onshore (domestic) innovation performance. We combine a comprehensive dataset mapping the global operations of Japanese multinational firms with patent statistics to measure innovation. The study finds that increased offshore production have little effects on onshore innovation performance once properly correcting a simultaneity bias. Furthermore, we find some weak evidence of increased offshore production downgrades the quality of innovation, measured by citations. Consistent with other studies, we find that an increase in overseas R&D is the main driver of innovation creation for multinational firms.

Simultaneous spatiotemporal bias and state estimation for asynchronous multi‐sensor system

Elimination of spatiotemporal bias of asynchronous multiple sensors is the foundation of accurate multi-sensor data fusion. In this article, a sequential processing simultaneous spatiotemporal bias and state estimation algorithm for asynchronous multi-sensor system is proposed. The spatiotemporal bias is combined with target state to obtain an augmented state vector, and the augmented state model is formulated. For asynchronous multi-sensor with known but different sampling periods, a sequential processing method is proposed to handle the multiple measurements. The relationship of sensor measurements, target state and spatiotemporal bias is analysed, and the corresponding measurement model is formulated. A novel algorithm, in which the unscented Kalman filter is used to handle the nonlinearity between the augmented measurement and state vectors, is proposed to jointly estimate the spatiotemporal bias and target state. Simulation results verify the effectiveness of the proposed algorithm.

Rough segmentation of coherent local intensity for bias induced 3-D MR brain images

Segmentation of brain MR volumes into different meaningful tissue classes is an essential prerequisite for many clinical analyses. However, intensity inhomogeneity or bias field, present in MR volumes, considerably degrades the quality of segmentation. In this regard, the paper presents a new segmentation algorithm, termed as CoLoRS (Coherent Local Intensity Rough Segmentation), for brain MR volumes corrupted with bias field artifact. It judiciously integrates the merits of coherent local intensity clustering and the theory of rough sets for simultaneous segmentation and bias field correction of brain MR volumes. The proposed algorithm partitions the entire image space into a number of small overlapping neighborhood regions. The bias, in each neighborhood region, is assumed to be constant. For each individual region, an objective function is defined for coherent local intensity rough segmentation. The voxels near the center point have similar influences on local objective function. In addition, the smaller distance between center and neighboring voxels yields more contribution on the voxel of interest. The proposed algorithm uses the dual-region concept to represent the neighborhood structure more efficiently. It makes possible of separate modeling of the voxels within neighborhood, according to their locations. Each region is considered to have several tissue classes, where each tissue class consists of a core region and an overlapping region. The segmentation in fuzzy approximation spaces provides an effective mean for brain MR volume analysis, as it handles overlapping partitions and addresses vagueness in tissue class definition. The effectiveness of the proposed algorithm, along with a comparison with existing approaches, is demonstrated on several publicly available brain MR data.

Innovation responses of Japanese firms to Chinese import competition

AbstractThis paper examines innovation responses of a panel of Japanese firms to the intensified import competition from China in the period 1995–2005. We build a comprehensive firm‐level dataset linking patents and R&D merged to cross‐industry measures of Chinese import competition. Accounting for a simultaneity bias between innovation and importing and the possible heterogeneous effects across firms, we found that patenting has increased in response to an influx of Chinese imports, but it has adversely affected the quality of innovation, measured by forward citations received. These effects are only observed for globally engaged firms, not for firms focusing on the domestic market.

Multiple-Surface-Approximation-Based FCM With Interval Memberships for Bias Correction and Segmentation of Brain MRI

Fuzzy c-means (FCM) is a popular clustering method for image segmentation. However, FCM has difficulties in handling artifacts in brain magnetic resonance imaging (MRI), especially when it comes to bias field and noise. We propose a novel multiple-surface-approximation-based FCM with interval membership method for simultaneous bias correction and segmentation of Brain MRI. First, multiple surface representation of bias field is embedded into FCM to estimate and correct bias field. Then memberships of the improved FCM are extended to intervals. After the extension, clustering centers of different MR brain tissues could be solved more properly by the proposed method. Moreover, the proposed method is less sensitive to noise by introducing effects of neighboring pixels. Experiments conducted on artificial images and synthetic and real clinical Brain MRI show that the proposed method is effective and obtains better results of both bias field correction and segmentation than comparing methods.

Segmentation of bias field induced brain MR images using rough sets and stomped-t distribution

Over the past few decades, automatic segmentation of brain magnetic resonance (MR) images into different tissue classes has remained an important research area, particularly due to the presence of bias field artifact in MR images. In this regard, the stomped normal (StN) distribution is proved to generate an optimal representation of the intensity distribution in brain MR images, by incorporating the properties of rough sets in the probabilistic framework. The StN distribution is capable of successfully modelling the central tendency, dispersion, and width of the intensity distribution. However, it does not take into consideration the kurtosis of the distribution, which controls the concentration of values around the mean and shape of the tail of intensity distribution. In this regard, the paper presents a novel method for simultaneous segmentation and bias field correction in brain MR images. It integrates the concept of rough sets and the merit of a recently introduced probability distribution, called stomped-t (St-t) distribution. The St-t distribution incorporates the property of kurtosis in rough-probabilistic framework, where each tissue class is modelled using a crisp lower approximation and a probabilistic boundary region. The brain MR image is modelled using a mixture of finite number of St-t distributions and one uniform distribution. The uniform distribution takes into account cerebro-spinal fluid, pathologies, and other non-brain tissues. The proposed method employs both expectation-maximization algorithm and hidden Markov random field model for accurate and robust image segmentation. The performance of the proposed approach, along with a comparison with related methods, is illustrated on a set of synthetic and real brain MR images for different bias fields and noise levels.

CRLB for Estimating Time-Varying Rotational Biases in Passive Sensors

In target tracking systems involving data fusion it is common to encounter sensor measurement biases that contribute to the tracking errors. There is extensive research into estimating sensor biases, but very little research into bias estimation in the dynamic case, meaning that biases that change over time are addressed. This paper investigates the means for and necessity of estimating bias rates of change in addition to constant sensor biases to reduce the errors in the state estimates. This is explored by comparing the Cramer–Rao lower bound and root-mean-square error of simultaneous target state and bias estimates for rotational biases with three-dimensional passive sensors with roll, pitch, and yaw biases. The present work models the dynamic biases as linearly varying over time. The iterated least squares method is used for the search of the maximum likelihood estimate, and is shown to be statistically efficient via hypothesis testing.

Bank Credit Shocks and Employment Growth: An Empirical Framework for the Case of Brazil

Existing evidence from the literature on financial intermediaries and economic development suggests that resource-constrained firms can growth faster in the presence of more financial services. With the new macroeconomic environment after 1994 and the institutional reforms in the Brazilian financial sector, there was an important expansion in the availability of bank resources. The process of financial deepening occurred simultaneously to sustained growth in formal employment. This paper studies the relationship between bank credit growth and formal employment growth from 1995 to 2015. The article combines two sets of administrative data: i) private and public banks’s balance sheets collected by the Brazilian Central Bank, and; ii) employment in formal establishments recorded by the Ministry of Labor. The empirical model exploits the large cross-sectional and timeseries variation in financial resources to build a Bartik-instrument for credit growth that interacts the country-wide increase in credit and the participation of different banks in local economies. The identification strategy relies on an auxiliary regression separating supply and demand of credit at the local level. This strategy bypasses some of the concerns with simultaneity bias in articles using aggregate data, and measurement issues of cross-country studies. Regression results indicate that a one percentage point increase in credit growth rates is associated with a 0.12 percentage point increase in employment growth rates. In areas with a prevalence of private banks, an acceleration in credit growth is also associated with a reduced number of establishments and higher average establishment size. The results are consistent with external financing incentivizing establishments to expand, displace other businesses without funds, and increase their size. This study employs aggregated data at the micro-region level, which limits a more detailed characterization of credit shocks effects at the individual establishment level. We have found that the relationship between credit and employment growth is weaker in micro-regions with smaller establishments, suggesting to policy-makers that further reforming the financial system can unleash the potential for more formal jobs in small firms in Brazil. Some microeconomic reforms such as the creation of nation-wide credit score records are already taking place and should possibly bear fruits in the futu

Profitability, capital, and risk in US commercial and savings banks: Re-examination of estimation methods

This study compares the relationships between the three main bank variables i.e., profitability, capital, and risk of US commercial and savings banks for the period 1995Q1-2015Q4. As the literature analyzes the relationship between these variables in pairs, thus suffering from an 'omitted variable bias' and a 'simultaneous equations bias', we examine whether these biases are statistically significant. We compare the common methodology of a three two-equation system with both a three-equation system and three separate OLS regressions. While there are significant differences in the coefficients of the three main variables within the sample period, we could not find substantial differences in out-of-sample forecast estimates.

New method for simultaneous moderate bias correction and image segmentation

This study proposes a new method for simultaneous image segmentation and moderate bias correction. Though many methods are proposed to deal with the image intensity inhomogeneity, some problems still exist and have influenced the segmentation results a lot. In this study, a new model is proposed for image segmentation and correction based on the multiplicative intrinsic component optimization (MICO) model. First, the new model in the level set formulation for gray images has been presented and the split Bregman method for fast minimization has been applied. The proposed model is tested with lots of magnetic resonance images and some medical colour images with promising results. Experimental results show that the proposed model can simultaneously segment images and correct bias field moderately. In the experimental part for gray images, a qualitative comparison between the proposed model and the MICO model in both segmentation and bias-correction results is made. Besides, the proposed model with the Chan-Vese model and the illumination and reflectance estimation model in the experimental part for colour images are compared. Moreover, the proposed model can segment nature colour images successfully. It is clear that the proposed model has a good performance on many characteristics such as accuracy, efficiency, and robustness.

Money market funds, bank loans and interest rate liberalization: Evidence from an emerging market

We report significant effects of the development of money market funds (MMFs) on bank deposits, loans and interest rate liberalization using bank data in China from 2008 to 2014. In particular, the development of MMFs has shifted away bank deposits and reduced banks’ ability to make loans. Furthermore, the yields of bank-guaranteed financial products and MMFs show a significant and positive relation, implying that the development of MMFs has promoted interest rate liberalization in China. These results remain to hold after we control for the potential simultaneity bias.

An Investigation of Item Bias of English Test: The Case of 2016 Year Undergraduate Placement Exam in Turkey

The purpose of this study is to determine whether English test items of Undergraduate Placement Exam (UPE) in 2016 contain differential item functioning (DIF) and differential bundle functioning (DBF) in terms of gender and school type and examine the possible sources of bias of DIF items. Mantel Haenszel (MH), Simultaneous Item Bias Test (SIBTEST) and Multiple Indicator and Multiple Causes (MIMIC) methods were used for DIF analyses. DBF analyses were conducted by MIMIC and SIBTEST methods. Expert opinions were consulted to determine the sources of bias. Data set of the study consisted of responses of 59818 students to 2016 UPE English test. As a result of the analyses carried out on 60 items, it was seen that one item in translation subtest contained DIF favoring male students. In school type based analyses, it was concluded that there were nine DIF items in vocabulary and grammar knowledge subtest, six DIF items in reading comprehension subtest and four DIF items in translation subtest. Experts stated that one item containing DIF by gender was unbiased, and evidence of bias was found in thirteen of nineteen items that contained DIF by school type. According to DBF analyses, it was found that some item bundles contained DBF with respect to gender and school type. As a result of research, it was discovered that there were differences with regard to the number of DIF items identified by three methods and the level of DIF that the items contained; however, methods were consistent in detecting uniform DIF.

Bias Smith Tube Optimization of Drain Voltage and Load Reflection Coefficient to Maximize Power-Added Efficiency Under ACPR Constraints for Radar Power Amplifiers

Reconfigurable transmitter power amplifiers will be necessary in future cognitive radar systems to allow adjustment in operating frequency, spectral output, and other desired operating characteristics while maintaining performance. Circuit optimization algorithms for tuning the amplifier load impedance and bias voltage in real time should maximize power-added efficiency while limiting the adjacent-channel power ratio (ACPR) in order to obtain spectral compliance. This paper presents a fast vector-based three-dimensional optimization for simultaneous bias adjustment and impedance matching for these goals using the bias Smith tube as the optimization space. Simulation and measurement results are presented for this optimization algorithm, and correspondence between the results is examined for several different starting locations in the bias Smith tube. This algorithm will allow simultaneous optimization of bias voltage and load impedance in real time in order to meet changing requirements.

Impact of Formal Climate Risk Transfer Mechanisms on Risk-Aversion: Empirical Evidence from Rural Ethiopia

This study examines the effect of smallholder farmers’ access to a formal climate risk transfer mechanism on their risk preferences. Survey and experimental data were collected from smallholder farmers that have access to weather index-based crop insurance (WICI) in Ethiopia. We use an endogenous switching (ESP) model to address self-selection and simultaneity bias. Results from the ESP model show that farmers who purchased WICI are less likely to be risk-averse compared with non-purchaser farmers. Similarly, non-purchasers would have attained a significant reduction in their risk-aversion if they had taken up the insurance product. We also find that WICI has a positive and statistically significant effect on farmers’ real-life risk-taking behavior as exemplified by mineral fertilizer use. The implication of our findings is that formal climate risk transfer mechanisms can positively influence households’ economic decisions and outcomes, through reducing risk aversion. Therefore, they can possibly contribute to poverty alleviation and economic development within agrarian economies that are exposed to recurrent and severe climate shocks.