Use of genetic correlations to examine selection bias.

Observational studies are rarely representative of their target population because there are known and unknown factors that affect an individual's choice to participate (the selection mechanism). Selection can cause bias in a given analysis if the outcome is related to selection (conditional on the other variables in the model). Detecting and adjusting for selection bias in practice typically requires access to data on nonselected individuals. Here, we propose methods to detect selection bias in genetic studies by comparing correlations among genetic variants in the selected sample to those expected under no selection. We examine the use of four hypothesis tests to identify induced associations between genetic variants in the selected sample. We evaluate these approaches in Monte Carlo simulations. Finally, we use these approaches in an applied example using data from the UK Biobank (UKBB). The proposed tests suggested an association between alcohol consumption and selection into UKBB. Hence, UKBB analyses with alcohol consumption as the exposure or outcome may be biased by this selection.

Interpreting disease genome-wide association studies and polygenetic risk scores given eligibility and study design considerations.

Genome-wide association studies (GWAS) have been helpful in identifying genetic variants predicting cancer risk and providing new insights into cancer biology. Increasing use of genetically informed care, as well as genetically informed prevention and treatment strategies, have also drawn attention to some of the inherent limitations of cancer genetic data. Specifically, genetic endowment is lifelong. However, those recruited into cancer studies tend to be middle-aged or older people, meaning the exposure most likely starts before recruitment, as opposed to exposure and recruitment aligning, as in a trial or a target trial. Studies in survivors can be biased as a result of depletion of the susceptibles, here specifically due to genetic vulnerability and the cancer of interest or a competing risk. In addition, including prevalent cases in a case-control study will make the genetics of survival with cancer look harmful (Neyman bias). Here, we describe ways of designing GWAS to maximize explanatory power and predictive utility, by reducing selection bias due to only recruiting survivors and reducing Neyman bias due to including prevalent cases alongside using other techniques, such as selection diagrams, age-stratification, and Mendelian randomization, to facilitate GWAS interpretability and utility.

Mendelian randomization for causal inference accounting for pleiotropy and sample structure using genome-wide summary statistics.

Mendelian randomization (MR) is a valuable tool for inferring causal relationships among a wide range of traits using summary statistics from genome-wide association studies (GWASs). Existing summary-level MR methods often rely on strong assumptions, resulting in many false-positive findings. To relax MR assumptions, ongoing research has been primarily focused on accounting for confounding due to pleiotropy. Here, we show that sample structure is another major confounding factor, including population stratification, cryptic relatedness, and sample overlap. We propose a unified MR approach, MR-APSS, which 1) accounts for pleiotropy and sample structure simultaneously by leveraging genome-wide information; and 2) allows the inclusion of more genetic variants with moderate effects as instrument variables (IVs) to improve statistical power without inflating type I errors. We first evaluated MR-APSS using comprehensive simulations and negative controls and then applied MR-APSS to study the causal relationships among a collection of diverse complex traits. The results suggest that MR-APSS can better identify plausible causal relationships with high reliability. In particular, MR-APSS can perform well for highly polygenic traits, where the IV strengths tend to be relatively weak and existing summary-level MR methods for causal inference are vulnerable to confounding effects.

Effect of case and control definitions on genome-wide association study (GWAS) findings.

Genome-wide association studies (GWAS) have significantly advanced our understanding of the genetic underpinnings of diseases, but case and control cohort definitions for a given disease can vary between different published studies. For example, two GWAS for the same disease using the UK Biobank data set might use different data sources (i.e., self-reported questionnaires, hospital records, etc.) or different levels of granularity (i.e., specificity of inclusion criteria) to define cases and controls. The extent to which this variability in cohort definitions impacts the end-results of a GWAS study is unclear. In this study, we systematically evaluated the effect of the data sources used for case and control definitions on GWAS findings. Using the UK Biobank, we selected three diseases-glaucoma, migraine, and iron-deficiency anemia. For each disease, we designed 13 GWAS, each using different combinations of data sources to define cases and controls, and then calculated the pairwise genetic correlations between all GWAS for each disease. We found that the data sources used to define cases for a given disease can have a significant impact on GWAS end-results, but the extent of this depends heavily on the disease in question. This suggests the need for greater scrutiny on how case cohorts are defined for GWAS.

A note on "Simple graphical rules to assess selection bias in general-population and selected-sample treatment effects" by M. B. Mathur and I. Shpitser.

This short note is a commentary on the paper by Mathur and Shpitser (2024), with the aim to enlarge the class of graphs for which the conditional Average Treatment Effect is nonparametrically identified, by allowing the outcome to be on the pathway between the treatment and the selection indicator. A first straightforward generalization is possible when (i) the outcome Y is binary, and (ii) the population prevalence of Y is known a priori, or can be made the object of a sensitivity analysis. Furthermore, identification of the effect is possible also for Y having any nature, provided that a selection bias breaking node  V exists and the population prevalence of V is known.

It's not all about residual confounding: a plea for QBA for epidemiologic researchers and educators.

We spend a great deal of time on confounding in our teaching, in our methods development and in our assessment of study results. This may give the impression that uncontrolled confounding is the biggest problem that observational epidemiology faces, when in fact, other sources of bias such as selection bias, measurement error, missing data, and misalignment of zero time may often (especially if they are all present in a single study) lead to a stronger deviation from the truth. Compared to the amount of time we spend teaching how to address confounding in a data analysis, we spend relatively little time teaching methods for simulating confounding (and other sources of bias) to learn their impact and develop plans to mitigate or quantify the bias. We review a paper by Desai et al that uses simulation methods to quantify the impact of an unmeasured confounder when it is completely missing or when a proxy of the confounder is measured. We use this article to discuss how we can use simulations of sources of bias to ensure we generate better and more valid study estimates, and we discuss the importance of simulating realistic datasets with plausible bias structures to guide data collection. If an advanced life form exists outside of our current universe and they came to earth with the goal of scouring the published epidemiologic literature to understand what the biggest problem epidemiologists have, they would quickly discover that the limitations section of publications would provide them with all the information they needed. And most likely what they would conclude is that the biggest problem that we face is uncontrolled confounding. It seems to be an obsession of ours.

Selection Bias Requires Selection: The Case of Collider Stratification Bias.

In epidemiology, collider stratification bias, the bias resulting from conditioning on a common effect of two causes, is oftentimes considered a type of selection bias, regardless of the conditioning methods employed. In this commentary, we distinguish between two types of collider stratification bias: collider restriction bias due to restricting to one level of a collider (or a descendant of a collider) and collider adjustment bias through inclusion of a collider (or a descendant of a collider) in a regression model. We argue that categorizing collider adjustment bias as a form of selection bias may lead to semantic confusion, as adjustment for a collider in a regression model does not involve selecting a sample for analysis. Instead, we propose that collider adjustment bias can be better viewed as a type of overadjustment bias. We further provide two distinct causal diagram structures to distinguish collider restriction bias and collider adjustment bias. We hope that such a terminological distinction can facilitate easier and clearer communication.

Impact of Quitline Services on Tobacco Cessation: An Application of Modern Epidemiological Methods.

This study investigated the effectiveness of quitline service intensity (high vs. low) on past 30-day tobacco abstinence at 7-months follow-up, using observational data from the Oklahoma Tobacco Helpline (OTH) between April 2020 and December 2021. To assess the impact of loss to follow-up and non-random treatment assignment, we fit the parameters of a marginal structural model to estimate inverse probability weights for censoring (IPCW) and treatment (IPTW) and combined (IPCTW). The Risk Ratio (RR) was estimated using modified Poisson regression with robust variance estimator. Of the 4,695 individuals included in the study, 64% received high-intensity cessation services, and 53% were lost to follow-up. Using the conventional complete case analysis (responders only), high-intensity cessation services were associated with abstinence (RR=1.18; 95 CI: 1.04, 1.34). The effect estimate was attenuated after accounting for censoring (RR=1.14; 95% CI: 1.00, 1.30). After adjusting for both baseline confounding and selection bias via IPTCW, high-intensity cessation services were associated with 1.23 times (95% CI: 1.08, 1.41) the probability of abstinence compared to low-intensity services. Despite relatively high loss to follow-up, accounting for selection bias and confounding did not notably impact quit rates or the relationship between intensity of quitline services and tobacco cessation among OTH participants.

The Evolution of Selection Bias in the Recent Epidemiologic Literature-A Selective Overview.

Selection bias has long been central in methodological discussions across epidemiology and other fields. In epidemiology, the concept of selection bias has been continually evolving over time. In this issue of the Journal, Mathur and Shpitser (Am J Epidemiol. XXXX;XXX(XX):XXXX-XXXX) present simple graphical rules for using a Single World Intervention Graph (SWIG) to assess the presence of selection bias when estimating treatment effects in both the general population and a selected sample. Notably, the authors examine the setting in which the treatment affects selection, an issue not well-addressed in the existing literature on selection bias. To place the work by Mathur and Shpitser in context, we review the evolution of the concept of selection bias in epidemiology, with a primary focus on the developments in the last 20-30 years since the introduction of causal directed acyclic graphs (DAGs) to epidemiologic research.

Improving prevalence estimates of mental health and well-being indicators among Sexual Minority Men: A Propensity Weighting Approach.

The prevalence and relative disparities of mental health outcomes and well-being indicators are often inconsistent across studies of Sexual Minority Men (SMM) due to selection biases in community-based surveys (non-probability sample), as well as misclassification biases in population-based surveys where some SMM often conceal their sexual orientation identities. The current paper estimated the prevalence of mental health related outcomes (depressive symptoms, mental health service use [MHSU], anxiety) and well-being indicators (loneliness and self-rated mental health) among SMM, broken down by sexual orientation using the Adjusted Logistic Propensity score (ALP) weighting. We applied the ALP to correct for selection biases in the 2019 Sex Now data (a community-based survey of SMMs in Canada) by reweighting it to the 2015-2018 Canadian Community Health Survey (a population survey from Statistics Canada). For all SMMs, the ALP-weighted prevalence of depressive symptoms is 15.96% (95% CI: 11.36%, 23.83%), while for MHSU, it is 32.13% (95% CI: 26.09, 41.20). The ALP estimates lie in between the crude estimates from the two surveys. This method was successful in providing a more accurate estimate than relying on results from one survey alone. We recommend to the use of ALP on other minority populations under certain assumptions.

Attention-deficit hyperactivity disorder symptoms and brain morphology: Addressing potential selection bias with inverse probability weighting.

The goal of this study was to examine what happens to established associations between attention deficit hyperactivity disorder (ADHD) symptoms and cortical surface and thickness regions once we apply inverse probability of censoring weighting (IPCW) to address potential selection bias. Moreover, we illustrate how different factors that predict participation contribute to potential selection bias. Participants were 9- to 11-year-old children from the Generation R study (N = 2707). Cortical area and thickness were measured with magnetic resonance imaging (MRI) and ADHD symptoms with the Child Behavior Checklist. We examined how associations between ADHD symptoms and brain morphology change when we weight our sample back to either follow-up (ages 9-11), baseline (cohort at birth), or eligible (population of Rotterdam at time of recruitment). Weights were derived using IPCW or raking and missing predictors of participation used to estimate weights were imputed. Weighting analyses to baseline and eligible increased beta coefficients for the middle temporal gyrus surface area, as well as fusiform gyrus cortical thickness. Alternatively, the beta coefficient for the rostral anterior cingulate decreased. Removing one group of variables used for estimating weights resulted in the weighted regression coefficient moving closer to the unweighted regression coefficient. In addition, we found considerably different beta coefficients for most surface area regions and all thickness measures when we did not impute missing covariate data. Our findings highlight the importance of using inverse probability weighting (IPW) in the neuroimaging field, especially in the context of mental health-related research. We found that including all variables related to exposure-outcome in the IPW model and combining IPW with multiple imputations can help reduce bias. We encourage future psychiatric neuroimaging studies to define their target population, collect information on eligible but not included participants and use inverse probability of censoring weighting (IPCW) to reduce selection bias.

Survival Analysis of Conversion Surgery in Borderline Resectable and Locally Advanced Unresectable Pancreatic Ductal Adenocarcinoma Addressing Selection and Immortal Time Bias: A Retrospective Single-Center Study.

BACKGROUND: The purpose of this study was to provide a detailed evaluation of the oncological advantages of surgery following neoadjuvant chemotherapy (NAC) for patients with borderline resectable (BR) or unresectable (UR) pancreatic ductal adenocarcinoma (PDAC), with a focus on minimizing biases. Recently, NAC has become the standard care for BR or UR locally advanced (UR-LA) PDAC, however, many studies have assessed survival benefits and favorable variables without consideration for biases, particularly immortal time bias. PATIENTS AND METHODS: This study included patients diagnosed with BR or UR-LA PDAC at Juntendo University Hospital from 2019 to 2022. To mitigate bias, we applied methods such as propensity score matching (PSM), time-dependent covariate Cox proportional hazard regression analysis (TDC), landmark analysis, and multivariable Cox proportional hazards regression model. RESULTS: The study analyzed 124 patients, dividing them into a surgery group (n = 57) and a chemotherapy-only group (n = 67). After PSM, there were 21 matched pairs. Survival analysis using TDC analysis showed that the surgery group had significantly better overall survival compared with the chemotherapy-only group in both the entire cohort and the matched pairs. Cox regression analysis of the entire cohort also revealed a similar superiority of surgery, while the landmark analysis showed varying results depending on the landmark setting. CONCLUSIONS: After careful adjustment for selection and immortal time biases, surgery following NAC appears to significantly extend survival in patients with BR or UR PDAC.

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.

Understanding an impact of patient enrollment pattern on predictability of central (unstratified) randomization in a multi-center clinical trial.

In a multi-center randomized controlled trial (RCT) with competitive recruitment, eligible patients are enrolled sequentially by different study centers and are randomized to treatment groups using the chosen randomization method. Given the stochastic nature of the recruitment process, some centers may enroll more patients than others, and in some instances, a center may enroll multiple patients in a row, for example, on a given day. If the study is open-label, the investigators might be able to make intelligent guesses on upcoming treatment assignments in the randomization sequence, even if the trial is centrally randomized and not stratified by center. In this paper, we use enrollment data inspired by a real multi-center RCT to quantify the susceptibility of two restricted randomization procedures, the permuted block design and the big stick design, to selection bias under the convergence strategy of Blackwell and Hodges (1957) applied at the center level. We provide simulation evidence that the expected proportion of correct guesses may be greater than 50% (i.e., an increased risk of selection bias) and depends on the chosen randomization method and the number of study patients recruited by a given center that takes consecutive positions on the central allocation schedule. We propose some strategies for ensuring stronger encryption of the randomization sequence to mitigate the risk of selection bias.

Using instruments for selection to adjust for selection bias in Mendelian randomization.

Selection bias is a common concern in epidemiologic studies. In the literature, selection bias is often viewed as a missing data problem. Popular approaches to adjust for bias due to missing data, such as inverse probability weighting, rely on the assumption that data are missing at random and can yield biased results if this assumption is violated. In observational studies with outcome data missing not at random, Heckman's sample selection model can be used to adjust for bias due to missing data. In this paper, we review Heckman's method and a similar approach proposed by Tchetgen Tchetgen and Wirth (2017). We then discuss how to apply these methods to Mendelian randomization analyses using individual-level data, with missing data for either the exposure or outcome or both. We explore whether genetic variants associated with participation can be used as instruments for selection. We then describe how to obtain missingness-adjusted Wald ratio, two-stage least squares and inverse variance weighted estimates. The two methods are evaluated and compared in simulations, with results suggesting that they can both mitigate selection bias but may yield parameter estimates with large standard errors in some settings. In an illustrative real-data application, we investigate the effects of body mass index on smoking using data from the Avon Longitudinal Study of Parents and Children.

Developing survey weights to ensure representativeness in a national, matched cohort study: results from the children and young people with Long Covid (CLoCk) study.

BACKGROUND: Findings from studies assessing Long Covid in children and young people (CYP) need to be assessed in light of their methodological limitations. For example, if non-response and/or attrition over time systematically differ by sub-groups of CYP, findings could be biased and any generalisation limited. The present study aimed to (i) construct survey weights for the Children and young people with Long Covid (CLoCk) study, and (ii) apply them to published CLoCk findings showing the prevalence of shortness of breath and tiredness increased over time from baseline to 12-months post-baseline in both SARS-CoV-2 Positive and Negative CYP. METHODS: Logistic regression models were fitted to compute the probability of (i) Responding given envisioned to take part, (ii) Responding timely given responded, and (iii) (Re)infection given timely response. Response, timely response and (re)infection weights were generated as the reciprocal of the corresponding probability, with an overall 'envisioned population' survey weight derived as the product of these weights. Survey weights were trimmed, and an interactive tool developed to re-calibrate target population survey weights to the general population using data from the 2021 UK Census. RESULTS: Flexible survey weights for the CLoCk study were successfully developed. In the illustrative example, re-weighted results (when accounting for selection in response, attrition, and (re)infection) were consistent with published findings. CONCLUSIONS: Flexible survey weights to address potential bias and selection issues were created for and used in the CLoCk study. Previously reported prospective findings from CLoCk are generalisable to the wider population of CYP in England. This study highlights the importance of considering selection into a sample and attrition over time when considering generalisability of findings.

Bias analyses to investigate the impact of differential participation: Application to a birth defects case-control study.

BACKGROUND: Certain associations observed in the National Birth Defects Prevention Study (NBDPS) contrasted with other research or were from areas with mixed findings, including no decrease in odds of spina bifida with periconceptional folic acid supplementation, moderately increased cleft palate odds with ondansetron use and reduced hypospadias odds with maternal smoking. OBJECTIVES: To investigate the plausibility and extent of differential participation to produce effect estimates observed in NBDPS. METHODS: We searched the literature for factors related to these exposures and participation and conducted deterministic quantitative bias analyses. We estimated case-control participation and expected exposure prevalence based on internal and external reports, respectively. For the folic acid-spina bifida and ondansetron-cleft palate analyses, we hypothesized the true odds ratio (OR) based on prior studies and quantified the degree of exposure over- (or under-) representation to produce the crude OR (cOR) in NBDPS. For the smoking-hypospadias analysis, we estimated the extent of selection bias needed to nullify the association as well as the maximum potential harmful OR. RESULTS: Under our assumptions (participation, exposure prevalence, true OR), there was overrepresentation of folic acid use and underrepresentation of ondansetron use and smoking among participants. Folic acid-exposed spina bifida cases would need to have been ≥1.2× more likely to participate than exposed controls to yield the observed null cOR. Ondansetron-exposed cleft palate cases would need to have been 1.6× more likely to participate than exposed controls if the true OR is null. Smoking-exposed hypospadias cases would need to have been ≥1.2 times less likely to participate than exposed controls for the association to falsely appear protective (upper bound of selection bias adjusted smoking-hypospadias OR = 2.02). CONCLUSIONS: Differential participation could partly explain certain associations observed in NBDPS, but questions remain about why. Potential impacts of other systematic errors (e.g. exposure misclassification) could be informed by additional research.

Global mismatches between threat mapping research effort and the potential of threat abatement actions to reduce extinction risk.

Threat mapping is a necessary tool for identifying and abating direct threats to species in the ongoing extinction crisis. There are known gaps in the threat mapping literature for particular threats and geographic locations, and it remains unclear if the distribution of research effort is appropriately targeted relative to conservation need. We aimed to determine the drivers of threat mapping research effort and to quantify gaps that, if filled, could inform actions with the highest potential to reduce species' extinction risk. We used a negative binomial generalized linear model to analyze research effort as a function of threat abatement potential (quantified as the potential reduction in species extinction risk from abating threats), species richness, land area, and human pressure. The model showed that threat mapping research effort increased by 1.1 to 1.2 times per standardized unit change in threat abatement potential. However, species richness and land area were stronger predictors of research effort overall. The greatest areas of mismatch between research effort and threat abatement potential, receiving disproportionately low research effort, were related to the threats to species of agriculture, aquaculture, and biological resource use across the tropical regions of the Americas, Asia, and Madagascar. Conversely, the threat of linear infrastructure (e.g., roads and rails) across regions, the threat of biological resource use (e.g., hunting or collection) in sub-Saharan Africa, and overall threats in North America and Europe all received disproportionately high research effort. We discuss the range of methodological and sociopolitical factors that may be behind the overall trends and specific areas of mismatch we found. We urge a stronger emphasis on targeting research effort toward those threats and geographic locations where threat abatement activities could make the greatest contribution to reducing global species extinction risk.

Disparidades mundiales entre la investigación sobre el esfuerzo de mapeo de amenazas y la potencial amenaza de las acciones de abatimiento para reducir el riesgo de extinción Resumen El mapeo de amenazas es una herramienta necesaria para identificar y abatir las amenazas directas para las especies en la actual crisis de extinción. Existen vacíos conocidos en la literatura del mapeo de amenazas para amenazas particulares y ubicaciones geográficas, y todavía no está claro si la distribución de los esfuerzos de investigación está enfocada de forma apropiada en relación con las necesidades de conservación. Buscamos determinar los factores que influyen sobre el esfuerzo de investigación del mapeo de amenazas y cuantificar los vacíos que, si se cierran, podrían guiar las acciones con el potencial más alto para reducir el riesgo de extinción de las especies. Usamos un modelo binomial lineal negativo generalizado para analizar el esfuerzo de investigación como función del potencial de abatimiento de amenazas (cuantificado como la reducción potencial en el riesgo de extinción a partir del abatimiento de amenazas), la riqueza de especies, el área del suelo y la presión humana. El modelo mostró que el esfuerzo de investigación del mapeo de amenazas incrementó entre 1.1 y 1.2 veces por unidad estandarizada de cambio en el potencial de abatimiento de amenazas. Sin embargo, la riqueza de especies y el área del suelo fueron pronósticos más sólidos del esfuerzo de investigación generalizado. Las principales áreas de disparidad entre el esfuerzo de investigación y el potencial de abatimiento de amenazas, las cuales reciben un esfuerzo de investigación desproporcionalmente bajo, estuvieron relacionadas con las amenazas para las especies de agricultura, acuacultura y recursos biológicos que se usan en las regiones tropicales de América, Asia y Madagascar. Al contrario, la amenaza de la infraestructura lineal (p. ej.: carreteras y vías férreas) en las regiones, la amenaza del uso de recursos biológicos (p. ej.: caza o recolección) en la África subsahariana y las amenazas generales en América del Norte y en Europa recibieron un esfuerzo de investigación desproporcionalmente alto. Abordamos el rango de factores metodológicos y sociopolíticos que pueden estar detrás de las tendencias generales y las áreas específicas de disparidad que encontramos. Instamos a un mayor énfasis en el enfoque del esfuerzo de investigación hacia aquellas amenazas y ubicaciones geográficas en donde las actividades de abatimiento de amenazas podrían brindar una mayor contribución para reducir el riesgo mundial de extinción de especies.

Assessing the validity of a Parkinson's care evaluation: the PRIME-NL study.

INTRODUCTION: The PRIME-NL study prospectively evaluates a new integrated and personalized care model for people with parkinsonism, including Parkinson's disease, in a selected region (PRIME) in the Netherlands. We address the generalizability and sources of selection and confounding bias of the PRIME-NL study by examining baseline and 1-year compliance data. METHODS: First, we assessed regional baseline differences between the PRIME and the usual care (UC) region using healthcare claims data of almost all people with Parkinson's disease in the Netherlands (the source population). Second, we compared our questionnaire sample to the source population to determine generalizability. Third, we investigated sources of bias by comparing the PRIME and UC questionnaire sample on baseline characteristics and 1-year compliance. RESULTS: Baseline characteristics were similar in the PRIME (n = 1430) and UC (n = 26,250) source populations. The combined questionnaire sample (n = 920) was somewhat younger and had a slightly longer disease duration than the combined source population. Compared to the questionnaire sample in the PRIME region, the UC questionnaire sample was slightly younger, had better cognition, had a longer disease duration, had a higher educational attainment and consumed more alcohol. 1-year compliance of the questionnaire sample was higher in the UC region (96%) than in the PRIME region (92%). CONCLUSION: The generalizability of the PRIME-NL study seems to be good, yet we found evidence of some selection bias. This selection bias necessitates the use of advanced statistical methods for the final evaluation of PRIME-NL, such as inverse probability weighting or propensity score matching. The PRIME-NL study provides a unique window into the validity of a large-scale care evaluation for people with a chronic disease, in this case parkinsonism.

Using the global randomization test as a Mendelian randomization falsification test for the exclusion restriction assumption.

Mendelian randomization may give biased causal estimates if the instrument affects the outcome not solely via the exposure of interest (violating the exclusion restriction assumption). We demonstrate use of a global randomization test as a falsification test for the exclusion restriction assumption. Using simulations, we explored the statistical power of the randomization test to detect an association between a genetic instrument and a covariate set due to (a) selection bias or (b) horizontal pleiotropy, compared to three approaches examining associations with individual covariates: (i) Bonferroni correction for the number of covariates, (ii) correction for the effective number of independent covariates, and (iii) an r2 permutation-based approach. We conducted proof-of-principle analyses in UK Biobank, using CRP as the exposure and coronary heart disease (CHD) as the outcome. In simulations, power of the randomization test was higher than the other approaches for detecting selection bias when the correlation between the covariates was low (r2 < 0.1), and at least as powerful as the other approaches across all simulated horizontal pleiotropy scenarios. In our applied example, we found strong evidence of selection bias using all approaches (e.g., global randomization test p < 0.002). We identified 51 of the 58 CRP genetic variants as horizontally pleiotropic, and estimated effects of CRP on CHD attenuated somewhat to the null when excluding these from the genetic risk score (OR = 0.96 [95% CI: 0.92, 1.00] versus 0.97 [95% CI: 0.90, 1.05] per 1-unit higher log CRP levels). The global randomization test can be a useful addition to the MR researcher's toolkit.