This Personal View is intended for early-career researchers who are not yet experts in statistics. The Personal View focuses on common but usually avoidable flaws in the context of observational studies. I point out how study design, data collection, and statistical methods impact statistical results and research conclusions. With particular attention to study planning, sample selection, biases, lack of transparency and results misinterpretations.

暂无摘要。

In 2020, during the early days of the COVID-19 pandemic, the British Journal of Psychiatry (BJPsych) established a series of free online teaching sessions called BJPsych Journal Clubs. Their educational purpose is two-fold: (a) to provide junior psychiatrists with a friendly but large-scale platform to evaluate and critically appraise recent articles published in the BJPsych and (b) to present new research findings in an open and accessible manner. In this paper, we discuss our framework, the challenges we encountered, how the original model is evolving based on feedback from trainees, and tips for success when delivering international online journal clubs.

In applied sectors, data modeling/analysis is very important for decision-making and future predictions. Data analysis in applied sectors mainly relies on probability distributions. Data arising from numerous sectors such as engineering-related fields have complex structures. For such kinds of data having complex structures, the implementation of classical distributions is not a suitable choice. Therefore, researchers often need to look for more flexible models that might have the capability of capturing a high degree of kurtosis and increasing the fitting power of the classical models. Taking motivation from the above theory, to achieve these goals, we study a new probabilistic model, which we named a new beta power flexible Weibull (NBPF-Weibull) distribution. We derive some of the main distributional properties of the NBPF-Weibull model. The estimators for the parameters of the NBPF-Weibull distribution are derived. The performances of these estimators are judged by incorporating a simulation study for different selected values of the parameters. Three data sets are used to demonstrate the applicability of the NBPF-Weibull model. The first data set is observed from sports. It represents the re-injury rate of various football players. While the other two data sets are observed from the reliability zone. By adopting certain diagnostic criteria, it is proven that the NBPF-Weibull model repeatedly surpasses well-known classical and modified models.

BACKGROUND: A significant rise in mental health disorders was expected during the COVID-19 pandemic. However, referrals to mental health services dropped for several months before rising to pre-pandemic levels.
OBJECTIVE: To identify trajectories of incidence and risk factors for common mental disorders among the general population during 14 months of the COVID-19 pandemic, to inform potential mental health service needs.
METHODS: A cohort of 33 703 adults in England in the University College London COVID-19 Social Study provided data from March 2020 to May 2021. Growth mixture modelling was used to identify trajectories based on the probability of participants reporting symptoms of depression (Patient Health Questionnaire-9) or anxiety (Generalised Anxiety Disorder-7) in the clinical range, for each month. Sociodemographic and personality-related characteristics associated with each trajectory class were explored.
RESULTS: Five trajectory classes were identified for depression and anxiety. Participants in the largest class (62%) were very unlikely to report clinically significant symptom levels. Other trajectories represented participants with a high likelihood of clinically significant symptoms throughout, early clinically significant symptoms that reduced over time, clinically significant symptoms that emerged as the pandemic unfolded and a moderate likelihood of clinically significant symptoms throughout. Females, younger adults, carers, those with existing mental health diagnoses, those that socialised frequently pre-pandemic and those with higher neuroticism scores were more likely to experience depression or anxiety.
CONCLUSIONS: Nearly 40% of participants followed trajectories indicating risk of clinically significant symptoms of depression or anxiety. The identified risk factors could inform public health interventions to target individuals at risk in future health emergencies.

John Snow, the London doctor who studied cholera in the 1840s and 1850s, argued in Snow (1856) that water exerted an \"overwhelming influence\" on mortality in a region of south London during the 1854 outbreak. In a paper re-assessing Snow\'s analysis, Koch and Denike (2006) claim that \"Snow made not merely minor arithmetic errors but more importantly critical, conceptual mistakes that adversely affected his results.\" The claim of errors and mistakes is incorrect and due to a misreading or misunderstanding of Snow\'s data and analysis. Koch and Denike apply an inappropriate statistical test to Snow\'s original data (and do so incorrectly). More importantly, due to the misreading of the historical record they alter the underlying primary-source data, rendering their results invalid. Analysis of the data following Snow\'s approach but with modern statistical tools strongly supports Snow\'s claim for the primacy of water in accounting for variation in cholera mortality.

BACKGROUND: In early 2021, the Department of Health and Social Care in the UK called for research on the safety and immunogenicity of concomitant administration of COVID-19 and influenza vaccines. Co-administration of these vaccines would facilitate uptake and reduce the number of healthcare visits required. The ComFluCOV trial was designed to deliver the necessary evidence in time to inform the autumn (September-November) 2021 vaccination policy. This paper presents the statistical methodology applied to help successfully deliver the trial results in 6 months.
METHODS: ComFluCOV was a parallel-group multicentre randomised controlled trial managed by the Bristol Trials Centre. Two study statisticians, supported by a senior statistician, worked together on all statistical tasks. Tools were developed to aid the pre-screening process. Automated data monitoring reports of clinic data and electronic diaries were produced daily and reviewed by the trial team and feedback provided to sites. Analyses were performed independently in parallel, and derivations and results of all outcomes were compared.
RESULTS: Set-up was achieved in less than a month, and 679 participants were recruited over 8 weeks. A total of 537 [at least] daily reports outlining recruitment, protocol adherence, and data quality, and 695 daily reports of participant electronic diaries identifying any missed diary entries and adverse events were produced over a period of 16 weeks. A preliminary primary outcome analysis of validated data was reported to the Department of Health and Social Care in May 2021. The database was locked 6 weeks after the final participant follow-up and final analyses completed 3 weeks later. A pre-print publication was submitted within 14 days of the results being made available. The results were reported 6 months after first discussions about the trial.
CONCLUSIONS: The statistical methodologies implemented in ComFluCOV helped to deliver the study in the timescale set. Working in a new clinical area to tight timescales was challenging. Having two statisticians working together on the study provided a quality assurance process that enabled analyses to be completed efficiently and ensured data were interpreted correctly. Processes developed could be applied to other studies to maximise quality, reduce the risk of errors, and overall provide enhanced validation methods.
BACKGROUND: ISRCTN14391248, registered on 30 March 2021.

This technical report serves as a comprehensive guide for conducting a phenome-wide association study (PheWAS) utilizing data extracted from the Nationwide Inpatient Sample 2020. Specifically tailored to individuals diagnosed with pancreatic cysts and lung cancer, the report establishes a step-by-step workflow designed to assist researchers in uncovering potential associations within this specific cohort. The methodology outlined in the report ensures clarity and reproducibility by employing a curated cohort sourced from the GitHub repository and executed using R for robust data analysis. The code encompasses pivotal steps, including the utilization of a QQ plot as a crucial diagnostic tool aimed at identifying systematic biases or associations. Additionally, the report incorporates the creation of a Manhattan plot, delving into essential mathematical considerations to enhance the interpretability of the results. Notably, the report elucidates the handling of the International Classification of Disease version 10 (ICD-10) codes, providing a sample approach for their segmentation to analyze associations by diagnostic categories. The segmentation aligns with the guidelines outlined in the American Medical Association\'s ICD-10-CM 2022, the Complete Official Codebook with Guidelines (American Medical Association Press, 2021), ensuring a standardized and rigorous analytical process. This comprehensive guide equips researchers with the tools and insights needed to navigate the complexities of PheWAS within the context of pancreatic cysts and lung cancer, fostering transparency, reproducibility, and meaningful scientific exploration.

Patients diagnosed with attention-deficit hyperactivity disorder (ADHD) are at an elevated risk for suicide. No prior work has assessed the association between stimulant prescriptions and death by suicide in this population. This retrospective cohort study included Department of Veterans Affairs patients with an active ADHD diagnosis that received stimulant medications between 2016 and 2019. We found that months with active stimulant medication prescription was associated with decreased risk of suicide mortality compared with months without stimulant medication (odds ratio 0.57, 95% CI 0.36-0.88). Our results suggest that prescribing stimulant medications for patients diagnosed with ADHD is associated with decreased risk of suicide mortality.

OBJECTIVE: Adjusting for potential confounders is crucial for producing valuable evidence in outcome studies. Although numerous studies have been published using the Korea National Health Insurance Claim Database, no study has critically reviewed the methods used to adjust for confounders. This study aimed to review these studies and suggest methods and applications to adjust for confounders.
METHODS: We conducted a literature search of electronic databases, including PubMed and Embase, from January 1, 2021 to December 31, 2022. In total, 278 studies were retrieved. Eligibility criteria were published in English and outcome studies. A literature search and article screening were independently performed by 2 authors and finally, 173 of 278 studies were included.
RESULTS: Thirty-nine studies used matching at the study design stage, and 171 adjusted for confounders using regression analysis or propensity scores at the analysis stage. Of these, 125 conducted regression analyses based on the study questions. Propensity score matching was the most common method involving propensity scores. A total of 171 studies included age and/or sex as confounders. Comorbidities and healthcare utilization, including medications and procedures, were used as confounders in 146 and 82 studies, respectively.
CONCLUSIONS: This is the first review to address the methods and applications used to adjust for confounders in recently published studies. Our results indicate that all studies adjusted for confounders with appropriate study designs and statistical methodologies; however, a thorough understanding and careful application of confounding variables are required to avoid erroneous results.