Address Selection Bias Research Articles

REMIT: Reirradiation of diffuse midline glioma patients – a NOPHO feasibility study

Diffuse midline glioma (DMG) continues to be an aggressive brain stem cancer among children and young adults. It has a dismal prognosis with less than 10% of patients alive two years after diagnosis. Radiotherapy has been demonstrated to be effectful, albeit transient. Hence, radiotherapy is considered a cornerstone in the treatment. Reirradiation has, in retrospective studies, shown promising overall survival and palliative effect but no pan-European consensus for reirradiation exists. The REMIT (Reirradiation of diffuse Midline glioma paTients) protocol evaluates safety and the palliative efficacy of reirradiation of patients with DMG (clinicaltrials.gov NCT06093165). Patients included in the protocol will be followed with 1) performance status (Karnofsky or Lansky), 2) toxicity monitored with NCI Common Terminology Criteria for Adverse Events (CTCAE), 3) motor and functioning skill with PEDI-CAT (The Paediatric Evaluation of Disability Inventory) and 4) quantification of corticosteroid use. Furthermore, the impact on quality of life and well-being will be assessed qualitatively with interviews as well as with the Pediatric Quality of Life Inventory (PedsQl) Cancer Module questionnaire. The protocol also includes dose accumulation and contouring studies to assess standardization as well as a pre-screening log to address selection bias of patients. The safety and palliative efficacy of reirradiation in DMG will be prospectively evaluated, including qualitative patient reported outcomes, through the REMIT protocol. REMIT is planned to open for inclusion in 2024.

Health implications of cooking energy transition: Evidence from rural China

Abstract The transition towards advanced residential energy sources is a pressing priority for many countries. Despite this, solid fuels remain the dominant form of cooking energy for rural households in developing countries. This study investigates the physical and mental health impacts of cooking energy choices by using endogenous switching models to address selection bias associated with cooking energy adoption and to distinguish the health impacts of different types of cooking energy. Using a country-representative household survey data in China, our results indicate that adopting advanced forms of energy, not only enhances physical health in terms of reducing the rates of chronic diseases but also improves mental health. We further delve into the heterogenous impacts of advanced energy adoption across different groups and find that women, old adults, and economically disadvantaged groups are more likely to experience greater mental health benefits compared to their counterparts, while the opposite results are observed for the physical health. Additionally, we differentiate the health impacts by distinguishing between various energy types. This study provides insights for policy making aimed at improving public health and promoting health equality, contributing to efforts towards achieving sustainable development goals by prioritizing clean and efficient residential energy solutions.

Give a Fish or Teach to Fish? Poverty Alleviation Effect of Government Support Policies and Self-Help Commercial Activities

This study explores the interactive effect of self-help efforts, specifically through household decisions to engage in commercialisation, and external supports provided via government antipoverty policies, on poverty reduction among poor households in northern Vietnam. With observational data from 1383 surveyed households, we use an estimation strategy combining inverse probability weighting, regression adjustment, and two-stage least squares to address selection bias and omitted variable bias in two variables of interest. We find that while these two interventions are individually effective in alleviating poverty, their combination is not necessarily as effective. Our results show that commercialisation only reduces poverty among non-supported households, while government supports are more effective among non-commercial households. This substitution of effects comes from the nature of support targeting and commercialisation. Households receiving supports often have lower capacity, making commercialisation ineffective or even impossible. Furthermore, current support policies are insufficient to enhance the impact of commercialisation. These results suggest that there could be more effective ways to combine external interventions and self-help efforts to better alleviate poverty.

Balancing customer and employee orientations: impact on financial distress and firm value

PurposeThis paper investigates the effect of balanced orientation (BO) toward customers and employees on financial distress and firm valuation. Rooted in stakeholder theory and the attention-based theory of firms, the study aims to understand how a balanced synthesis of employee orientation (EO) and customer orientation (CO) influences the long-term market performance and survivability of firms, particularly in the context of emerging markets.Design/methodology/approachA panel dataset of the top 500 firms listed on the National Stock Exchange of India was analyzed using fixed-effect panel models with robust estimators. The Heckman procedure was employed to address selection bias. Financial data were sourced from the CMIE Prowess database and balanced orientation data were extracted from the annual letters to shareholders.FindingsThe study finds that a balanced approach to EO and CO significantly lowers bankruptcy risk and increases firm valuation. Contrary to the traditional dichotomy of EO and CO, BO emerges as a key driver in reducing financial distress and enhancing long-term market performance. Firms embracing multiple strategic orientations outperform those solely focused on customer orientation.Practical implicationsFor emerging market firms facing resource constraints, developing BO is challenging but crucial. This study suggests adopting a sequential or alternating approach to developing EO and CO, which can alleviate bankruptcy risk and improve market valuation even in competitive environments.Originality/valueThis paper contributes to the existing literature by empirically demonstrating the significance of BO in emerging markets. It offers a novel perspective on strategic management, highlighting the importance of balancing customer and employee needs, especially in resource-constrained environments.

Patient-Centered Economic Burden of Diabetic Macular Edema: Retrospective Cohort Study.

Diabetic macular edema (DME), a leading cause of blindness, requires treatment with costly drugs, such as anti-vascular endothelial growth factor (VEGF) agents. The prolonged use of these effective but expensive drugs results in an incremental economic burden for patients with DME compared with those with diabetes mellitus (DM) without DME. However, there are no studies on the long-term patient-centered economic burden of DME after reimbursement for anti-VEGFs. This retrospective cohort study aims to estimate the 3-year patient-centered economic burden of DME compared with DM without DME, using the Common Data Model. We used medical data from 1,903,603 patients (2003-2020), transformed and validated using the Observational Medical Outcomes Partnership Common Data Model from Seoul National University Bundang Hospital. We defined the group with DME as patients aged >18 years with nonproliferative diabetic retinopathy and intravitreal anti-VEGF or steroid prescriptions. As control, we defined the group with DM without DME as patients aged >18 years with DM or diabetic retinopathy without intravitreal anti-VEGF or steroid prescriptions. Propensity score matching, performed using a regularized logistic regression with a Laplace prior, addressed selection bias. We estimated direct medical costs over 3 years categorized into total costs, reimbursement costs, nonreimbursement costs, out-of-pocket costs, and costs covered by insurance, as well as healthcare resource utilization. An exponential conditional model and a count model estimated unbiased incremental patient-centered economic burden using generalized linear models and a zero-inflation model. In a cohort of 454 patients with DME matched with 1640 patients with DM, the economic burden of DME was significantly higher than that of DM, with total costs over 3 years being 2.09 (95% CI 1.78-2.47) times higher. Reimbursement costs were 1.89 (95% CI 1.57-2.28) times higher in the group with DME than with the group with DM, while nonreimbursement costs were 2.54 (95% CI 2.12-3.06) times higher. Out-of-pocket costs and costs covered by insurance were also higher by a factor of 2.11 (95% CI 1.58-2.59) and a factor of 2.01 (95% CI 1.85-2.42), respectively. Patients with DME had a significantly higher number of outpatient (1.87-fold) and inpatient (1.99-fold) visits compared with those with DM (P<.001 in all cases). Patients with DME experience a heightened economic burden compared with diabetic patients without DME. The substantial and enduring economic impact observed in real-world settings underscores the need to alleviate patients' burden through preventive measures, effective management, appropriate reimbursement policies, and the development of innovative treatments. Strategies to mitigate the economic impact of DME should include proactive approaches such as expanding anti-VEGF reimbursement criteria, approving and reimbursing cost-effective drugs such as bevacizumab, advocating for proactive eye examinations, and embracing early diagnosis by ophthalmologists facilitated by cutting-edge methodologies such as artificial intelligence for patients with DM.

Factors Influencing Attitude towards Adaptation of AI among Business Students

This study examines the attitudes of business students in the Kathmandu Valley towards the adaptation of Artificial Intelligence (AI). A sample of 185 respondents participated in the study. Data analysis included descriptive statistics, correlation, ANOVA, and regression analysis. The research focused on business education due to the critical importance of skills such as critical thinking, research proficiency, and effective communication. The study assessed five factors influencing student attitudes towards AI adaptation: exposure to AI, trust in AI technology, awareness and knowledge of AI, behavioral intentions towards AI use, and personal experiences with AI. The findings confirm a positive relationship between business students’ attitudes toward using AI and the identified influencing factors. The study suggests conducting future research through longitudinal studies to track attitude changes after students enter the workforce. It also recommends expanding the participant pool to include diverse disciplines and universities across Nepal for better generalizability. Additionally, exploring how negative AI experiences impact attitudes, addressing selection bias through varied data collection methods, and assessing AI's effects on psychomotor and critical thinking skills are advised.

Crop Diversification, Household Welfare and Conflict: Afghanistan 2011–2017

We use three waves (2011–2012 to 2016–2017) of nationally representative repeated cross section surveys to study the impact of crop diversification (number of crops grown) on household welfare, measured by real adult equivalent consumption and food expenditure and dietary diversity, in Afghanistan. Diversification is very low (almost half grow only one crop and fewer than a fifth grow three or more crops) but increased during the period. A multinomial endogenous switching regression (MESR) addressing selection bias and endogeneity is used to estimate average treatment effects of moving from one crop to two crops and then to three or more crops. The analysis shows that crop diversification increases household consumption and food spending, and, to a modest extent, dietary diversity compared to undiversified households. This holds irrespective of conflict although the effect varies; households experiencing violence tend to divert spending to food from other consumption spending and only the most diversified are able to increase spending compared to undiversified households. The evidence implies that supporting crop diversification can improve food security (through combined effects on spending and food diversity) and mitigate the negative impacts of conflict.

Debiasing the Conversion Rate Prediction Model in the Presence of Delayed Implicit Feedback.

The recommender system (RS) has been widely adopted in many applications, including online advertisements. Predicting the conversion rate (CVR) can help in evaluating the effects of advertisements on users and capturing users' features, playing an important role in RS. In real-world scenarios, implicit rather than explicit feedback data are more abundant. Thus, directly training the RS with collected data may lead to suboptimal performance due to selection bias inherited from the nature of implicit feedback. Methods such as reweighting have been proposed to tackle selection bias; however, these methods omit delayed feedback, which often occurs due to limited observation times. We propose a novel likelihood approach combining the assumed parametric model for delayed feedback and the reweighting method to address selection bias. Specifically, the proposed methods minimize the likelihood-based loss using the multi-task learning method. The proposed methods are evaluated on the real-world Coat and Yahoo datasets. The proposed methods improve the AUC by 5.7% on Coat and 3.7% on Yahoo compared with the best baseline models. The proposed methods successfully debias the CVR prediction model in the presence of delayed implicit feedback.

Quantitative bias analysis methods for summary-level epidemiologic data in the peer-reviewed literature: a systematic review

ObjectivesQuantitative bias analysis (QBA) methods evaluate the impact of biases arising from systematic errors on observational study results. This systematic review aimed to summarize the range and characteristics of QBA methods for summary-level data published in the peer-reviewed literature. Study Design and SettingWe searched MEDLINE, Embase, Scopus, and Web of Science for English-language articles describing QBA methods. For each QBA method, we recorded key characteristics, including applicable study designs, bias(es) addressed; bias parameters, and publicly available software. The study protocol was preregistered on the Open Science Framework (https://osf.io/ue6vm/). ResultsOur search identified 10,249 records, of which 53 were articles describing 57 QBA methods for summary-level data. Of the 57 QBA methods, 53 (93%) were explicitly designed for observational studies, and 4 (7%) for meta-analyses. There were 29 (51%) QBA methods that addressed unmeasured confounding, 19 (33%) misclassification bias, 6 (11%) selection bias, and 3 (5%) multiple biases. Thirty-eight (67%) QBA methods were designed to generate bias-adjusted effect estimates and 18 (32%) were designed to describe how bias could explain away observed findings. Twenty-two (39%) articles provided code or online tools to implement the QBA methods. ConclusionIn this systematic review, we identified a total of 57 QBA methods for summary-level epidemiologic data published in the peer-reviewed literature. Future investigators can use this systematic review to identify different QBA methods for summary-level epidemiologic data. Plain Language SummaryQuantitative bias analysis (QBA) methods can be used to evaluate the impact of biases on observational study results. However, little is known about the full range and characteristics of available methods in the peer-reviewed literature that can be used to conduct QBA using information reported in manuscripts and other publicly available sources without requiring the raw data from a study. In this systematic review, we identified 57 QBA methods for summary-level data from observational studies. Overall, there were 29 methods that addressed unmeasured confounding, 19 that addressed misclassification bias, six that addressed selection bias, and three that addressed multiple biases. This systematic review may help future investigators identify different QBA methods for summary-level data.

On Frequency and Probability Weights: An In‐Depth Look at Duelling Weights

SummaryProbability weights have been widely used in addressing selection bias arising from a variety of contexts. Common examples of probability weights include sampling weights, missing data weights, and propensity score weights. Frequency weights, which are used to control for varying variabilities of aggregated outcomes, are both conceptually and analytically different from probability weights. Popular software such as R, SAS and STATA support both types of weights. Many users, including professional statisticians, become bewildered when they see identical estimates, but different standard errors and ‐values when probability weights are treated as frequency weights. Some even completely ignore the difference between the two types of weights and treat them as the same. Although a large body of literature exists on each type of weights, we have found little, if any, discussion that provides head‐to‐head comparisons of the two types of weights and associated inference methods. In this paper, we unveil the conceptual and analytic differences between the two types of weights within the context of parametric and semi‐parametric generalised linear models (GLM) and discuss valid inference for each type of weights. To the best of our knowledge, this is the first paper that looks into such differences by identifying the conditions under which the two types of weights can be treated the same analytically and providing clear guidance on the appropriate statistical models and inference procedures for each type of weights. We illustrate these considerations using real study data.

A new technique for handling non-probability samples based on model-assisted kernel weighting

Surveys are going through massive changes, and the most important innovation is the use of non-probability samples. Non-probability samples are increasingly used for their low research costs and the speed of the attainment of results, but these surveys are expected to have strong selection bias caused by several mechanisms that can eventually lead to unreliable estimates of the population parameters of interest. Thus, the classical methods of statistical inference do not apply because the probabilities of inclusion in the sample for individual members of the population are not known. Therefore, in the last few decades, new possibilities of inference from non-probability sources have appeared.Statistical theory offers different methods for addressing selection bias based on the availability of auxiliary information about other variables related to the main variable, which must have been measured in the non-probability sample. Two important approaches are inverse probability weighting and mass imputation. Other methods can be regarded as combinations of these two approaches.This study proposes a new estimation technique for non-probability samples. We call this technique model-assisted kernel weighting, which is combined with some machine learning techniques. The proposed technique is evaluated in a simulation study using data from a population and drawing samples using designs with varying levels of complexity for, a study on the relative bias and mean squared error in this estimator under certain conditions. After analyzing the results, we see that the proposed estimator has the smallest value of both the relative bias and the mean squared error when considering different sample sizes, and in general, the kernel weighting methods reduced more bias compared to based on inverse weighting. We also studied the behavior of the estimators using different techniques such us generalized linear regression versus machine learning algorithms, but we have not been able to find a method that is the best in all cases. Finally, we study the influence of the density function used, triangular or standard normal functions, and conclude that they work similarly.A case study involving a non-probability sample that took place during the COVID-19 lockdown was conducted to verify the real performance of the proposed methodology, obtain a better estimate, and control the value of the variance.

Ownership share in cross-border acquisitions: does high-tech status of the target matter?

PurposeThe purpose of this study is to investigate the influence of the target firm’s high-tech status on the share of ownership decision in cross-border acquisitions (CBAs), which is an under-explored topic in cross-border M&A literature.Design/methodology/approachThe authors used Tobit regression and tested the hypotheses using a sample of 7,011 CBA transactions between 1999 and 2014. Inverse Mills ratio was used to address selection bias, and various robustness tests were performed.FindingsThe authors found that acquirers seek greater ownership share when acquiring high-tech firms, and that this relationship is moderated by various firm and national level factors. Specifically, the positive relationship between the high-tech status of a target firm and ownership share acquired is stronger when the firms’ primary operations are highly related or there is high formal institutional distance between the firms’ home countries, but it is weaker when acquirers have more prior M&A experience or there is high cultural and geographic distance between the firms’ home countries.Originality/valueWhile the topic of ownership strategy in CBAs is advancing, it is still limited, especially when examining acquisitions of high-tech target firms. The authors contribute to the research on CBAs and ownership strategy by focusing on the high-tech status of the target firm, and using a sample of both private and public target firms from 116 countries.

Climate Change Adaptation Strategies and Its Impact on Household Vulnerability to Food Insecurity: A Micro-Level Evidence from Southwest Ethiopia

Smallholder farmers in Ethiopia face increasing challenges from climate change and variability, which threaten their food security and livelihoods. This study examines how adopting single and combined climate change adaptation practices affects their vulnerability to food insecurity in Bench Maji Zone, southwest Ethiopia. Through multistage sampling, data were gathered from 390 rural households in four climate-prone districts. The study examines the impacts resulting from both individual and combined implementations of adaptation techniques. These techniques encompass crop management practices, soil and water conservation measures, and livelihood portfolio diversification strategies. The study employed the multinomial endogenous treatment effect regression model to address selection bias and endogeneity resulting from various sources of heterogeneity, whether observed or unobserved. The results show that farmers who adopted adaptation practices were less vulnerable to food insecurity than those who did not. The study also finds that adopting multiple practices has a more significant impact than adopting single practices. Our findings suggest that implementing climate change adaptation strategies can increase the resilience of smallholder farmers in the study area and decrease their vulnerability to food insecurity. The study recommends supporting farmers in adopting these strategies through research and development, information dissemination, and collaborations among farmers, researchers, and extension services.

A selection of challenges in addressing selection bias.

A selection of challenges in addressing selection bias.

The impact of legal representation in Israeli traffic courts: Addressing selection bias and generalizability problems

AbstractThis study investigates the impact of legal representation on the process and outcomes of legal proceedings, focusing on Israeli traffic courts dealing with simple traffic offenses. It finds that legal representation significantly increased defendants' prospects of obtaining plea bargains and of avoiding demerits points. However, legally represented defendants were also exposed to higher fines compared to self‐represented defendants. Since points are typically the primary concern for defendants, we contend that legal representation improved case outcomes, overall. Considering the simplicity of the process, the minimal legal expertise required, and the low stakes involved, the representation effect was unexpectedly robust. This effect may potentially be even stronger in more complex cases and where the stakes are higher. Unlike previous observational studies, this study reduces the risks associated with selection bias and produces findings that are more credible and potentially generalizable to other contexts.

A unified Bayesian framework for bias adjustment in multiple comparisons from clinical trials.

In clinical trials, multiple comparisons arising from various treatments/doses, subgroups, or endpoints are common. Typically, trial teams focus on the comparison showing the largest observed treatment effect, often involving a specific treatment pair and endpoint within a subgroup. These findings frequently lead to follow-up pivotal studies, many of which do not confirm the initial positive results. Selection bias occurs when the most promising treatment, subgroup, or endpoint is chosen for further development, potentially skewing subsequent investigations. Such bias can be defined as the deviation in the observed treatment effects from the underlying truth. In this article, we propose a general and unified Bayesian framework to address selection bias in clinical trials with multiple comparisons. Our approach does not require a priori specification of a parametric distribution for the prior, offering a more flexible and generalized solution. The proposed method facilitates a more accurate interpretation of clinical trial results by adjusting for such selection bias. Through simulation studies, we compared several methods and demonstrated their superior performance over the normal shrinkage estimator. We recommended the use of Bayesian Model Averaging estimator averaging over Gaussian Mixture Models as the prior distribution based on its performance and flexibility. We applied the method to a multicenter, randomized, double-blind, placebo-controlled study investigating the cardiovascular effects of dulaglutide.

Gender dynamics of the impact of cash transfer on female educational expenditure of informal settlements in Bangladesh

Gender-biased educational investment remains a critical issue for vulnerable households. Despite increased female enrolment in the past decade, motivation to invest on female education remains low. Resource scarcity and low woman empowerment are two major reasons of low educational expenditure on female children of a vulnerable household. As the most vulnerable households in a society, informal settlers (slum households) are supposed to spend less on female children. However, whether there is any gender bias in informally settled households’ spending on education remains a question. Further, Cash Transfer (CT) programs provide resources to vulnerable households for investing on human capital elements like education. This study aims to examine three research questions: whether a informally settled household’s spending on education is gender biased, whether the households in which women receive CT spend more for female education than those in which women do not receive CT, and finally whether the impact of female receipt of CT differs from that of male receipt of CT in terms of female education expenditure. As the assignment of female access to CT is not randomized, the simple comparison between the treated and untreated suffers from selection bias. We employ propensity score matching (PSM) as an identification strategy to address selection bias. Inverse probability weighted regression adjustment (IPWRA) has been applied as a robustness check. The study's policy implications highlight the significance for policymakers in the domains of women's education, empowerment, and the achievement of Sustainable Development Goals.

Impact of scaling up of kangaroo mother care on neonatal mortality among babies born with birth weight

ObjectiveTo assess the impact of scaling up of kangaroo mother care (KMC) on neonatal mortality among babies born with birth weight <2000 g across an entire district in southern India.Design,...

Awe of the blue minds: Location, corporate social responsibility, and firm value

AbstractNeuropsychologists claim that exposure to a massive water scene triggers the feeling of Awe which causes more prosocial behavior. I find that coastal firms have significantly higher corporate social responsibility (CSR) scores than non‐coastal firms. The difference‐in‐difference test shows that CSR engagement erodes when firms relocate away from coasts. These results are robust to the use of propensity score matching and entropy balancing to address selection bias, Oster's test to address omitted variable bias, and control for institutional ownership, social capital, religiosity, CEO and local political orientation, and natural disaster risk. Further analysis shows that CSR creates value only for coastal firms.

The Benefits of Cross-Border Corporate Venture Capital Investment on the Likelihood of a Venture Firm’’s IPO

Purpose - Extant research indicates that CVC investments create value for venture firms and generally enhance the likelihood of a successful venture exit. In particular, despite the globalization of CVC investments, the impact on venture firm exit performance has been largely overlooked. Thus, this study explores the impact of cross-border CVC investments on the likelihood of a venture firm’s IPO. We argue that the foreignness of CVCs increases the likelihood of IPO, but this positive relationship is weakened when CVC units have a tight structure.&#x0D; Design/Methodology/Approach - The hypotheses are tested with 1,874 high-technology venture firms in the U.S. that received CVC investments between 1994 and 2009. A two-stage analysis was employed to address potential selection bias. In the first stage, we employed a probit model to predict the probability of receiving cross-border CVC investment. In the second stage, we conducted a probit regression analysis on the likelihood of IPO, incorporating the inverse Mills ratio to address selection bias.&#x0D; Findings - We found that the foreignness of CVCs increases the likelihood of a venture firm’s IPO. However, this positive impact is weakened when CVCs have a tight governance structure.&#x0D; Research Implications - This study highlights the benefits of cross-border CVC investments and enriches resource dependence theory by reconciling it with institutional theory, depicting the importance of both reducing resource constraints to create value for venture firms and the institutional logic pursued by CVCs. This study suggests that entrepreneurs should be careful with CVC units that prioritize strategic objectives.