Guidelines for a structured manuscript: Statistical methods and reporting in biomedical research journals

Use structured summary form (Background, Purpose, Methods, Results, and Conclusion). • Remember to add trial registration if the study was appropriately pre-registered. Introduction • Introduce in short, the topic. • Scientific background for the topic (incl. gaps in knowledge). • Evidence-based research (i.e., what is already known on this topic?). • Rationale for this study (i.e., what are the challenges to be addressed?). • Hypothesis when appropriate, aim and/or key objectives. Methods section (include only what is available when planning) • Structured reporting according to study design like STROBE and CONSORT (i.e., see EQUATOR network guidance). • Study design. • Participant/patient, samples (i.e., eligibility criteria) • Interventions/exposures (i.e., describe groups of importance for statistical testing). • Variables and outcome measures (e.g., the primary and key secondary endpoints). • Sample size and power considerations (i.e., informative even in a retrospective study). • Patient and public involvement in the research (i.e., did the researchers involve patients as research partners at any/all stages?). • Ethics and study registration like Clinicaltrials.gov (i.e., ethics approval obtained and availability of pre-registered protocol). • Statistical methods (e.g., main analyses; handling of missing data and multiplicity issues). Results • Participant flow (i.e., a Figure: a diagram illustrating study flow and attrition). • Baseline characteristics (i.e., a Table format reporting descriptive statistics for all participants in the intention-to-infer from population). • Main findings illustrated (i.e., illustration of the primary findings based on the prespecified objectives rather than chance findings [i.e., not based on significant “P values”]). • Main analyses on the primary and key secondary objectives (i.e., Table(s) reporting statistical measures for each group and difference between them [with 95% confidence intervals]). Discussion • Statement of principal findings based on the aim/key objectives/ hypothesis. • Putting the research into context (to previous studies). • Possible explanation of the results. • Strengths and limitations of the study. • Conclusions are strictly related to the aim/key objectives/ hypotheses. • Perspectives of the study. Avoid recommendation unless the manuscript is a recommendation paper. a “Enhancing the QUAlity and Transparency Of health Research” (EQUATOR) Network is an international initiative that seeks to improve the reliability and value of published health research literature by promoting transparent and accurate reporting and wider use of robust reporting guidelines (www.equator-network.org). Acta Orthopaedica 2023; 94: 243–249 245 mended because they are extremely effective for indicating missing data in epidemiological and clinical research. Randomized trials are not the only type of study to benefit from a transparent format that clearly describes enrollment, intervention/exposure allocation, follow-up, and data analysis. Reporting the Statistics section We encourage authors to recognize the importance of missing data—to embrace this issue and discuss (as part of the Results and Discussion section) how missing data affect the clinical findings. Missing data is unavoidable, but its potential to undermine the validity of research results is frequently ignored in the medical literature. The links between the research question and its answer need to be developed prior to the statistical analysis in the form of a study design, accounted for in the statistical analysis, and explained to the reader of the submitted manuscript. The protocol, developed according to the principles stated in the Helsinki Declaration, should be registered in a clinical studies database such as Clinicaltrials.gov or EU Clinical Trials Register. Alternatively, the original protocol could be registered and made publicly available at the Open Science Framework (https://osf.io/). Registration of register studies is also highly recommended – identifying and documenting the study in a public registry before the study is conducted. Prospective registration of register studies has several benefits, including: (i) reducing publication bias by making it more difficult for researchers to selectively report only the results that support their hypothesis; (ii) improving research quality by encouraging researchers to carefully plan their study design, analysis, and reporting, which can improve the overall quality of research; and (iii) increasing trust in the register research and facilitating replication. All statistical methods should be clearly specified and—when unusual methods are necessary—referenced. For every statistical result, the method used for deriving it should be clearly described. It is also important to address in sufficient detail the assumptions underlying the statistical methods used. No data should be removed, imputed, weighted, adjusted, or trimmed without clearly describing and justifying why and explaining the subsequent effects (i.e., see sensitivity analyses). Descriptive statistics: Descriptive statistics form an indispensable part of medical research manuscripts. Suitable tables should clearly describe the important features of the collected outcome variables and of the key prognostic and demographic variables. The results of the main analyses relating to the objectives of the study should be clearly described and presented, with descriptive statistics detailing both the central tendency and measures of dispersion (spread) of the data. We use means and standard deviations, or medians and interquartile ranges, as well as counts and proportions to inform the reader regarding the distribution of observations in variables for analysis and reporting. Statistical tests: The relation between the studied hypothesis and the presented results from null hypothesis testing (P values) should be clearly explained in the manuscript. The tests should be used with a defined effect size (e.g., estimating treatment effects), and the estimation uncertainty (usually via a confidence interval) should be considered in the results presentation. Unless the use of 1-sided tests is specifically justified (and performed at half the alpha level), the tests should be 2-sided. Authors should present P values with real numbers if these are greater than 0.001, using one digit except zeros. Otherwise, they should use “P 0.05,” or asterisks. We recommend that authors present analysis results with 95% confidence intervals instead of P values. Authors who wish to publish a manuscript with statistical tests must comply with 2 Acta Orthopaedica principles for concluding whether scientifically important differences exist: 1. A statistically non-significant test is not sufficient to claim “no difference.” To show “no difference,” a smallest clinically relevant size of the difference (it might be 0) must be defined. If all clinically relevant differences are excluded from the difference’s confidence interval, a “no difference” or similarity/comparability conclusion is reasonable. 2. A statistically significant test does not necessarily imply a clinically important difference. The importance of the tested null hypothesis depends on the smallest clinically relevant difference that should be defined a priori. If the difference’s confidence interval excludes all clinically irrelevant differences, a conclusion concerning the existence of a clinically important difference is reasonable. Multiple statistical tests: Most manuscripts include and rely on more than 1 set of 95% confidence intervals and P values. However, performing multiple statistical significance tests increase the chance of false-positive test results. When a single statistical test is performed at a 5% significance level, there is just a 5% chance of a false-positive result, but if repeated tests are performed, each at a 5% significance level, a false-positive test result can be expected. Problems related to this inflation of the significance level are known as multiplicity issues, which need to be acknowledged in the interpretation of the research findings. In contrast to hypothesis-generating studies, in which the outcome is a hypothesis, confirmatory studies—designed to provide empirical evidence for a prespecified hypothesis at a specific significance level—need to be designed and analyzed with respect to multiplicity issues—matters requiring multiple testing. Such multiple testing might be “....due to multiple subgroup comparisons, comparisons across multiple treatment arms, analysis of multiple outcomes, and multiple analyses of the same outcome at different times.” The development of a prespecified strategy for addressing multiplicity issues is usually required. Such strategies are often, but not always, based on adjusting P values or significance levels using the Bonferroni method or more refined alternatives such as Bonferroni-Holm’s or Hochberg’s method. HowActa Orthopaedica 2023; 94: 243–249 246 ever, merely performing a post hoc Bonferroni adjustment in a hypothesis-generating study is not sufficient for drawing confirmative conclusions. Although authors are at liberty to choose suitable significance levels, if they deviate from the conventional 5%, they should clarify their motivation and explain whether their ambition is to publish a hypothesis-generating or a confirmative study. In the latter case, and if multiplicity issues exist, they should present the multiplicity strategy they used in the Methods section and provide documentation for its pre-specification. Multiple regression models: Authors should keep in mind when conducting regression analyses and reporting results that such analyses are conducted in different ways, with different aims in mind, depending on the design of the study. The following examples from 3 common study designs illustrate how these analyses may differ. In prognostic