Typicality of Level Change (TLC) as an Additional Effect Measure to NAP and Tau-U in Single Case Research.

Single case research is a viable way to obtain evidence for social and psychological interventions on an individual level. Across single case research studies various analysis strategies are employed, varying from visual analysis to the calculation of effect sizes. To calculate effect sizes in studies with few measurements per time period (<40 data points with a minimum of five data points in each phase), non-parametric indices such as Nonoverlap of All Pairs (NAP) and Tau-U are recommended. However, both indices have restrictions. This article discusses the restrictions of NAP and Tau-U and presents the description, calculation, and benefits of an additional effect size, called the Typicality of Level Change (TLC) index. In comparison to NAP and Tau-U, the TLC index is more aligned to visual analysis, not restricted by a ceiling effect, and does not overcompensate for problematic trends in data. The TLC index is also sensitive to the typicality of an effect. TLC is an important addition to ease the restrictions of current nonoverlap methods when comparing effect sizes between cases and studies.

A benchmark study on current GWAS models in admixed populations.

OBJECTIVE: The performances of popular genome-wide association study (GWAS) models have not been examined yet in a consistent manner under the scenario of genetic admixture, which introduces several challenging aspects: heterogeneity of minor allele frequency (MAF), wide spectrum of case-control ratio, varying effect sizes, etc. METHODS: We generated a cohort of synthetic individuals (N = 19 234) that simulates (i) a large sample size; (ii) two-way admixture (Native American and European ancestry) and (iii) a binary phenotype. We then benchmarked three popular GWAS tools [generalized linear mixed model associated test (GMMAT), scalable and accurate implementation of generalized mixed model (SAIGE) and Tractor] by computing inflation factors and power calculations under different MAFs, case-control ratios, sample sizes and varying ancestry proportions. We also employed a cohort of Peruvians (N = 249) to further examine the performances of the testing models on (i) real genetic and phenotype data and (ii) small sample sizes. RESULTS: In the synthetic cohort, SAIGE performed better than GMMAT and Tractor in terms of type-I error rate, especially under severe unbalanced case-control ratio. On the contrary, power analysis identified Tractor as the best method to pinpoint ancestry-specific causal variants but showed decreased power when the effect size displayed limited heterogeneity between ancestries. In the Peruvian cohort, only Tractor identified two suggestive loci (P-value $\le 1\ast{10}^{-5}$) associated with Native American ancestry. DISCUSSION: The current study illustrates best practice and limitations for available GWAS tools under the scenario of genetic admixture. Incorporating local ancestry in GWAS analyses boosts power, although careful consideration of complex scenarios (small sample sizes, imbalance case-control ratio, MAF heterogeneity) is needed.

Mitos y realidad en el cálculo del tamaño muestral / Myths and reality about calculating sample size

Cuando decidimos hacer un estudio, una de las primeras cuestiones que se plantea es ¿qué número de individuos debo incluir en la muestra para que sea ‘representativa’ y el estudio sea ‘válido’? Como en otros ámbitos de la vida, hay muchas cuestiones para las que no hay una cantidad ‘adecuada’ y son válidas diferentes cantidades. Aquí ocurre lo mismo. La pregunta ‘¿cuántos euros costó esta bicicleta?’ tiene como respuesta un número concreto. Pero la pregunta ‘¿cuántos euros necesito para comprar una bicicleta?’ admite muchas cifras distintas como respuesta, dependiendo del tamaño y otras características de la bicicleta. Los libros de estadística contienen fórmulas que relacionan el tamaño de la muestra con ciertos parámetros y la mayoría de los médicos cree que una de ellas les dará el tamaño ‘adecuado’ para su investigación, y que usándolas queda ‘justificado el tamaño de la muestra’ ante posibles revisores. En este documento se hace una reflexión sobre el verdadero peso que tienen dichas fórmulas y cuál debe ser el uso adecuado que el investigador haga de ellas. Es necesario mostrar errores y simulaciones que no benefician a nadie y perjudican a muchos restando tiempo y energía.(AU)

When we decide to conduct a study, one of the first questions that arises is what number of individuals should be included in the sample for it to be ‘representative’ and for the study to be ‘valid’? As in other areas of life, there are many matters for which there is no ‘right’ amount and different quantities are valid. The same applies here. When asked the question ‘How many euros did this bicycle cost?’, the answer is a definite number. But the question ‘How many euros do I need to buy a bicycle?’ can be answered in many different ways, depending on the size and other characteristics of the bicycle. Statistics textbooks contain formulas relating sample size to certain parameters and most doctors believe that one of these will give them the ‘right’ size for their research, and that by using them their choice of sample size will be justified in the eyes of potential reviewers. This document reflects on the true value of these formulas and how researchers should make proper use of them. It is necessary to show errors and simulations that benefit no one and hinder many by taking up large amounts of time and energy.(AU)

Methods to increase response to postal and electronic questionnaires.

BACKGROUND: Self-administered questionnaires are widely used to collect data in epidemiological research, but non-response reduces the effective sample size and can introduce bias. Finding ways to increase response to postal and electronic questionnaires would improve the quality of epidemiological research. OBJECTIVES: To identify effective strategies to increase response to postal and electronic questionnaires. SEARCH METHODS: We searched 14 electronic databases up to December 2021 and manually searched the reference lists of relevant trials and reviews. We contacted the authors of all trials or reviews to ask about unpublished trials; where necessary, we also contacted authors to confirm the methods of allocation used and to clarify results presented. SELECTION CRITERIA: Randomised trials of methods to increase response to postal or electronic questionnaires. We assessed the eligibility of each trial using pre-defined criteria. DATA COLLECTION AND ANALYSIS: We extracted data on the trial participants, the intervention, the number randomised to intervention and comparison groups and allocation concealment. For each strategy, we estimated pooled odds ratios (OR) and 95% confidence intervals (CI) in a random-effects model. We assessed evidence for selection bias using Egger's weighted regression method and Begg's rank correlation test and funnel plot. We assessed heterogeneity amongst trial odds ratios using a Chi2 test and quantified the degree of inconsistency between trial results using the I2 statistic. MAIN RESULTS: Postal We found 670 eligible trials that evaluated over 100 different strategies of increasing response to postal questionnaires. We found substantial heterogeneity amongst trial results in half of the strategies. The odds of response almost doubled when: using monetary incentives (odds ratio (OR) 1.86; 95% confidence interval (CI) 1.73 to 1.99; heterogeneity I2 = 85%); using a telephone reminder (OR 1.96; 95% CI 1.03 to 3.74); and when clinical outcome questions were placed last (OR 2.05; 95% CI 1.00 to 4.24). The odds of response increased by about half when: using a shorter questionnaire (OR 1.58; 95% CI 1.40 to 1.78); contacting participants before sending questionnaires (OR 1.36; 95% CI 1.23 to 1.51; I2 = 87%); incentives were given with questionnaires (i.e. unconditional) rather than when given only after participants had returned their questionnaire (i.e. conditional on response) (OR 1.53; 95% CI 1.35 to 1.74); using personalised SMS reminders (OR 1.53; 95% CI 0.97 to 2.42); using a special (recorded) delivery service (OR 1.68; 95% CI 1.36 to 2.08; I2 = 87%); using electronic reminders (OR 1.60; 95% CI 1.10 to 2.33); using intensive follow-up (OR 1.69; 95% CI 0.93 to 3.06); using a more interesting/salient questionnaire (OR 1.73; 95% CI 1.12 to 2.66); and when mentioning an obligation to respond (OR 1.61; 95% CI 1.16 to 2.22). The odds of response also increased with: non-monetary incentives (OR 1.16; 95% CI 1.11 to 1.21; I2 = 80%); a larger monetary incentive (OR 1.24; 95% CI 1.15 to 1.33); a larger non-monetary incentive (OR 1.15; 95% CI 1.00 to 1.33); when a pen was included (OR 1.44; 95% CI 1.38 to 1.50); using personalised materials (OR 1.15; 95% CI 1.09 to 1.21; I2 = 57%); using a single-sided rather than a double-sided questionnaire (OR 1.13; 95% CI 1.02 to 1.25); using stamped return envelopes rather than franked return envelopes (OR 1.23; 95% CI 1.13 to 1.33; I2 = 69%), assuring confidentiality (OR 1.33; 95% CI 1.24 to 1.42); using first-class outward mailing (OR 1.11; 95% CI 1.02 to 1.21); and when questionnaires originated from a university (OR 1.32; 95% CI 1.13 to 1.54). The odds of response were reduced when the questionnaire included questions of a sensitive nature (OR 0.94; 95% CI 0.88 to 1.00). Electronic We found 88 eligible trials that evaluated over 30 different ways of increasing response to electronic questionnaires. We found substantial heterogeneity amongst trial results in half of the strategies. The odds of response tripled when: using a brief letter rather than a detailed letter (OR 3.26; 95% CI 1.79 to 5.94); and when a picture was included in an email (OR 3.05; 95% CI 1.84 to 5.06; I2 = 19%). The odds of response almost doubled when: using monetary incentives (OR 1.88; 95% CI 1.31 to 2.71; I2 = 79%); and using a more interesting topic (OR 1.85; 95% CI 1.52 to 2.26). The odds of response increased by half when: using non-monetary incentives (OR 1.60; 95% CI 1.25 to 2.05); using shorter e-questionnaires (OR 1.51; 95% CI 1.06 to 2.16; I2 = 94%); and using a more interesting e-questionnaire (OR 1.85; 95% CI 1.52 to 2.26). The odds of response increased by a third when: offering survey results as an incentive (OR 1.36; 95% CI 1.16 to 1.59); using a white background (OR 1.31; 95% CI 1.10 to 1.56); and when stressing the benefits to society of response (OR 1.38; 95% CI 1.07 to 1.78; I2 = 41%). The odds of response also increased with: personalised e-questionnaires (OR 1.24; 95% CI 1.17 to 1.32; I2 = 41%); using a simple header (OR 1.23; 95% CI 1.03 to 1.48); giving a deadline (OR 1.18; 95% CI 1.03 to 1.34); and by giving a longer time estimate for completion (OR 1.25; 95% CI 0.96 to 1.64). The odds of response were reduced when: "Survey" was mentioned in the e-mail subject (OR 0.81; 95% CI 0.67 to 0.97); when the email or the e-questionnaire was from a male investigator, or it included a male signature (OR 0.55; 95% CI 0.38 to 0.80); and by using university sponsorship (OR 0.84; 95%CI 0.69 to 1.01). The odds of response using a postal questionnaire were over twice those using an e-questionnaire (OR 2.33; 95% CI 2.25 to 2.42; I2 = 98%). Response also increased when: providing a choice of response mode (electronic or postal) rather than electronic only (OR 1.76 95% CI 1.67 to 1.85; I2 = 97%); and when administering the e-questionnaire by computer rather than by smartphone (OR 1.62 95% CI 1.36 to 1.94). AUTHORS' CONCLUSIONS: Researchers using postal and electronic questionnaires can increase response using the strategies shown to be effective in this Cochrane review.

Implications for cisgender female underrepresentation, small sample sizes, and misgendering in sport and exercise science research.

A sex-data gap, from testing primarily males, results in a lack of scientific knowledge for other groups (females, transgender individuals). It is unknown whether typical recruitment and participant characterization causes incorrect statistical decisions, and three factors were evaluated: 1) underrepresenting cisgender females, 2) recruiting small sample sizes, 3) misgendering. Data from the National Health and Nutrition Examination Survey (2003-2004) were evaluated for sex differences after removing missing values (N = 3,645; F = 1,763). Disparities were determined by utilizing sample sizes common in sport and exercise science research; mean sample size N = 187, median sample size N = 20. Participants were randomly allocated into datasets in an imbalanced manner (33.5% females, 66.5% males). Potential effects of misgendering were determined at rates of 2% and 5%. Differences between the complete data set and expected decisions were conducted through Chi-squared (χ2) goodness of fit with significance at p < .05. When the entire dataset was evaluated as if a sex testing disparity was present, decisions were not altered (χ2 = .52, p = .47). Differences were observed for mean sample size (χ2 = 4.89, p = .027), median sample size (χ2 = 13.52, p < .001), and misgendering at 2% (χ2 = 13.52, p = < .001) and 5% (χ2 = 13.52, p = < .001). Recruitment practices in sport and exercise science research should be revisited, as testing primarily cisgender males has consequences, particularly in small sample sizes. Misgendering participants also has consequences on ultimate decisions and interpretations of data, regardless of sample size. Inclusiveness is needed in helping all individuals feel valued and respected when participating in sport and exercise science research.

A multi-dimensional incomplete stepped-wedge trial design to estimate the impact of standards-based audit.

A clinical audit is a low-cost process used for quality improvement in healthcare. Such audits are however infrequently used in resource poor countries, where the need for and potential impact of quality improvement is higher. Sets of standards for use in maternal and newborn care have been established based on internal guidelines and evidence. The before-after design of a clinical audit is prone to bias in the estimation of the impact of conducting a clinical audit. A trial design that would provide an unbiased estimate of the impact of implementing a clinical audit process on the attainment of standards selected (a standards-based audit) was needed. The aim of this paper is to introduce and describe the design of trials we developed to meet this need. A novel randomised stepped-wedge trial design to estimate the impact of conducting standards-based audits is presented. A multi-dimensional incomplete stepped-wedge cluster randomised trial design suitable for estimation of the impact of Standards-based audits on compliance with standard is proposed; two variants are described in detail. A method for sample size estimation is described. Analyses can be performed for the binary outcome using a generalised linear mixed model framework to estimate the impact of the approach on compliance with standards subjected to a standards-based audit; additional terms to consider including in sensitivity analyses are considered. The design presented has the potential to estimate the impact of introducing the standards-based audit process on compliance with standard, while providing participating healthcare providers opportunity to gain experience of implementing the standards-based audit process. The design may be applicable in other areas in which multiple processes are to be studied.

The unit ratio-extended Weibull family and the dropout rate in Brazilian undergraduate courses.

We propose a new family of distributions, so-called the unit ratio-extended Weibull family ([Formula: see text]). It is derived from ratio transformation in an extended Weibull random variable. The use of this transformation is a novelty of the work since it has been less explored than the exponential and has not yet been studied within the extended Weibull class. Moreover, we offer a valuable alternative to model double-bounded variables on the unit interval. Five [Formula: see text] special models are studied in detail, namely the: i) unit ratio-Gompertz; ii) unit ratio-Burr XII; iii) unit ratio-Lomax; v) unit ratio-Rayleigh, and vi) unit ratio-Weibull distributions. We propose a quantile-parameterization for the new family. The maximum likelihood estimators (MLEs) are presented. A Monte Carlo study is performed to evaluate the behavior of the MLEs of unit ratio-Gompertz and unit ratio-Rayleigh distributions. This last model has closed-form and approximately unbiased MLE for small sample sizes. Further, the [Formula: see text] submodels are adjusted to the dropout rate in Brazilian undergraduate courses. We focus on the areas of civil engineering, economics, computer sciences, and control engineering. The applications show that the new family is suitable for modeling educational data and may provide effective alternatives compared to other usual unit models, such as the Beta, Kumaraswamy, and unit gamma distributions. They can also outperform some recent contributions in the unit distribution literature. Thus, the [Formula: see text] family can provide competitive alternatives when those models are unsuitable.

Sample size requirements for testing treatment effect heterogeneity in cluster randomized trials with binary outcomes.

Cluster randomized trials (CRTs) refer to a popular class of experiments in which randomization is carried out at the group level. While methods have been developed for planning CRTs to study the average treatment effect, and more recently, to study the heterogeneous treatment effect, the development for the latter objective has currently been limited to a continuous outcome. Despite the prevalence of binary outcomes in CRTs, determining the necessary sample size and statistical power for detecting differential treatment effects in CRTs with a binary outcome remain unclear. To address this methodological gap, we develop sample size procedures for testing treatment effect heterogeneity in two-level CRTs under a generalized linear mixed model. Closed-form sample size expressions are derived for a binary effect modifier, and in addition, a computationally efficient Monte Carlo approach is developed for a continuous effect modifier. Extensions to multiple effect modifiers are also discussed. We conduct simulations to examine the accuracy of the proposed sample size methods. We present several numerical illustrations to elucidate features of the proposed formulas and to compare our method to the approximate sample size calculation under a linear mixed model. Finally, we use data from the Strategies and Opportunities to Stop Colon Cancer in Priority Populations (STOP CRC) CRT to illustrate the proposed sample size procedure for testing treatment effect heterogeneity.

Inclusion of binary proxy variables in logistic regression improves treatment effect estimation in observational studies in the presence of binary unmeasured confounding variables.

We present a simulation study and application that shows inclusion of binary proxy variables related to binary unmeasured confounders improves the estimate of a related treatment effect in binary logistic regression. The simulation study included 60,000 randomly generated parameter scenarios of sample size 10,000 across six different simulation structures. We assessed bias by comparing the probability of finding the expected treatment effect relative to the modeled treatment effect with and without the proxy variable. Inclusion of a proxy variable in the logistic regression model significantly reduced the bias of the treatment or exposure effect when compared to logistic regression without the proxy variable. Including proxy variables in the logistic regression model improves the estimation of the treatment effect at weak, moderate, and strong association with unmeasured confounders and the outcome, treatment, or proxy variables. Comparative advantages held for weakly and strongly collapsible situations, as the number of unmeasured confounders increased, and as the number of proxy variables adjusted for increased.

How important is the linearity assumption in a sample size calculation for a randomised controlled trial where treatment is anticipated to affect a rate of change?

BACKGROUND: For certain conditions, treatments aim to lessen deterioration over time. A trial outcome could be change in a continuous measure, analysed using a random slopes model with a different slope in each treatment group. A sample size for a trial with a particular schedule of visits (e.g. annually for three years) can be obtained using a two-stage process. First, relevant (co-) variances are estimated from a pre-existing dataset e.g. an observational study conducted in a similar setting. Second, standard formulae are used to calculate sample size. However, the random slopes model assumes linear trajectories with any difference in group means increasing proportionally to follow-up time. The impact of these assumptions failing is unclear. METHODS: We used simulation to assess the impact of a non-linear trajectory and/or non-proportional treatment effect on the proposed trial's power. We used four trajectories, both linear and non-linear, and simulated observational studies to calculate sample sizes. Trials of this size were then simulated, with treatment effects proportional or non-proportional to time. RESULTS: For a proportional treatment effect and a trial visit schedule matching the observational study, powers are close to nominal even for non-linear trajectories. However, if the schedule does not match the observational study, powers can be above or below nominal levels, with the extent of this depending on parameters such as the residual error variance. For a non-proportional treatment effect, using a random slopes model can lead to powers far from nominal levels. CONCLUSIONS: If trajectories are suspected to be non-linear, observational data used to inform power calculations should have the same visit schedule as the proposed trial where possible. Additionally, if the treatment effect is expected to be non-proportional, the random slopes model should not be used. A model allowing trajectories to vary freely over time could be used instead, either as a second line analysis method (bearing in mind that power will be lost) or when powering the trial.

Evaluation of pragmatic oxygenation measurement as a proxy for Covid-19 severity.

Choosing optimal outcome measures maximizes statistical power, accelerates discovery and improves reliability in early-phase trials. We devised and evaluated a modification to a pragmatic measure of oxygenation function, the [Formula: see text] ratio. Because of the ceiling effect in oxyhaemoglobin saturation, [Formula: see text] ratio ceases to reflect pulmonary oxygenation function at high [Formula: see text] values. We found that the correlation of [Formula: see text] with the reference standard ([Formula: see text]/[Formula: see text] ratio) improves substantially when excluding [Formula: see text] and refer to this measure as [Formula: see text]. Using observational data from 39,765 hospitalised COVID-19 patients, we demonstrate that [Formula: see text] is predictive of mortality, and compare the sample sizes required for trials using four different outcome measures. We show that a significant difference in outcome could be detected with the smallest sample size using [Formula: see text]. We demonstrate that [Formula: see text] is an effective intermediate outcome measure in COVID-19. It is a non-invasive measurement, representative of disease severity and provides greater statistical power.

Phosphodiesterase 5 inhibitors (PDE5i) for the treatment of Raynaud's phenomenon.

BACKGROUND: Raynaud's phenomenon is a vasodilatory phenomenon characterised by digital pallor, cyanosis, and pain of the extremities. Primary Raynaud's phenomenon has no underlying disease associated with it, while secondary Raynaud's phenomenon is associated with connective tissue disorders such as systemic sclerosis. Systemic sclerosis causes fibrosis and commonly affects the skin and internal organs such as the gastrointestinal tract, lungs, kidney, and heart. Phosphodiesterase 5 inhibitors (PDE5i) are a class of drugs that increases blood flow to the extremities and may be beneficial in the treatment of Raynaud's phenomenon. OBJECTIVES: To assess the benefits and harms of PDE5i compared to placebo for the treatment of Raynaud's phenomenon. SEARCH METHODS: We searched the Cochrane Central Register of Controlled Trials, MEDLINE, Embase, and clinical trial registries up to June 2022. We did not apply any language restrictions. We searched the bibliographies of retrieved articles and contacted key experts in the field for additional and unpublished data. SELECTION CRITERIA: Randomised controlled trials (RCTs) comparing PDE5i to placebo in people with primary and secondary Raynaud's phenomenon. DATA COLLECTION AND ANALYSIS: We used standard methodological procedures expected by Cochrane. MAIN RESULTS: This review included nine RCTs which ranged in duration from four to eight weeks and included a total of 411 participants. The majority had Raynaud's phenomenon secondary to systemic sclerosis. Tadalafil was assessed in four studies, sildenafil in three studies, vardenafil in one study, and a new PDE5 inhibitor known as "PF-00489791" in one study. Three studies were parallel design and six studies were cross-over. The frequency of attacks per week was 24 with placebo and PDE5i reduced the frequency of attacks by an average of three attacks per week (mean difference (MD) -3.07, 95% confidence interval (CI) -5.15 to -1.00; 8 studies; low-certainty evidence). The duration of attacks per day was 55 minutes with placebo and PDE5i reduced the duration of attacks by an average of five minutes (MD -5.31, 95% CI -8.90 to -1.71; 8 studies; low-certainty evidence). Very low-certainty evidence from one study with eight participants showed severity of Raynaud's attacks (assessed on a 10 cm visual analogue scale with lower scores indicating less severity) was 20% lower with a PDE5i (3.7 with placebo compared to 1.6 with treatment; MD -2.1, 95% CI -2.7 to 1.4; very low-certainty evidence). Pain and patient global assessment were assessed on a 10 cm visual analogue scale with lower scores indicating improvement. Low-certainty evidence showed that the use of PDE5i may result in little to no difference compared to placebo in reducing the average pain of Raynaud's attacks (3 to 2.9; MD -0.10, 95% CI -0.78 to 0.57; 4 studies). Global scores were 36% lower with the use of a PDE5i compared to placebo (9.2 to 5.6; MD -3.59, 95% CI -4.45 to -2.73; 1 study, 24 participants; low-certainty evidence). The rate of withdrawals during treatment with PDE5i ranged from 4% to 20% compared with 2% in the placebo group in five studies. Four studies reported no withdrawals due to adverse events. Seven studies reported no serious adverse events. The rate of serious adverse events reported in two studies ranged from 2% during treatment to 4% with placebo. The majority of the studies were judged as low or unclear risk of bias for selection, performance, and detection bias. Almost half were judged at high risk of attrition bias and unclear risk for selective reporting bias. We downgraded frequency of attacks, duration of attacks, pain intensity, and patient global assessment for small sample sizes and concerns about inconsistency and graded each as low certainty of evidence. We downgraded severity of attacks to very low certainty due to serious concerns about imprecision and publication bias. We downgraded withdrawals due to adverse events and serious adverse events to moderate certainty of evidence due to a low number of reported events. AUTHORS' CONCLUSIONS: Based on low-certainty evidence, PDE5i may reduce the frequency of attacks of Raynaud's phenomenon by a small amount per week, result in a small reduction in the duration of attack, improve patients' global assessment of their disease, and result in little to no difference in pain. PDE5i probably result in little or no difference in serious adverse events but slightly increase the likelihood of withdrawing from treatment due to an adverse event.

Indexing and partitioning the spatial linear model for large data sets.

We consider four main goals when fitting spatial linear models: 1) estimating covariance parameters, 2) estimating fixed effects, 3) kriging (making point predictions), and 4) block-kriging (predicting the average value over a region). Each of these goals can present different challenges when analyzing large spatial data sets. Current research uses a variety of methods, including spatial basis functions (reduced rank), covariance tapering, etc, to achieve these goals. However, spatial indexing, which is very similar to composite likelihood, offers some advantages. We develop a simple framework for all four goals listed above by using indexing to create a block covariance structure and nearest-neighbor predictions while maintaining a coherent linear model. We show exact inference for fixed effects under this block covariance construction. Spatial indexing is very fast, and simulations are used to validate methods and compare to another popular method. We study various sample designs for indexing and our simulations showed that indexing leading to spatially compact partitions are best over a range of sample sizes, autocorrelation values, and generating processes. Partitions can be kept small, on the order of 50 samples per partition. We use nearest-neighbors for kriging and block kriging, finding that 50 nearest-neighbors is sufficient. In all cases, confidence intervals for fixed effects, and prediction intervals for (block) kriging, have appropriate coverage. Some advantages of spatial indexing are that it is available for any valid covariance matrix, can take advantage of parallel computing, and easily extends to non-Euclidean topologies, such as stream networks. We use stream networks to show how spatial indexing can achieve all four goals, listed above, for very large data sets, in a matter of minutes, rather than days, for an example data set.

Protocol update and baseline characteristics for the TRIal to slow the Progression of Diabetes (TRIPOD) randomized controlled trial.

BACKGROUND: Type 2 diabetes (T2D), a major risk factor for cardiovascular disease and other adverse health conditions, is on the rise in Singapore. TRIPOD is a randomized controlled trial aimed to determine whether complementing usual care with an evidence-based diabetes management package (DMP) -comprising access to an evidence-based app, health coaching, pedometer, glucometer and weighing scale, with or without a financial rewards scheme (M-POWER rewards), can improve mean HbA1c levels at months 6 and 12. METHODS: The protocol was published in Trials, accessible via https://trialsjournal.biomedcentral.com/articles/10.1186/s13063-019-3749-x 1. This manuscript updates the protocol with changes to the study design due to challenges with recruitment and presents baseline characteristics. Key updates include changing the arm allocation ratio from 1:1:1 (Arm 1-Usual Care: Arm 2-DMP: Arm 3-DMP+M-POWER rewards) to 10:1:10, the sample size from 339 to 269, the intervention period from two to one year, and the primary hypothesis to focus solely on differences between Usual Care and DMP+M-POWER rewards. Recruitment for the study began on 19 October 2019 and ended on 4 June 2022. RESULTS: The average age of participants was 55.0 (SD9.7) years old and 64.2% were male. The majority of participants (76.8%) were Chinese, 4.9% Malay and 18.3% Indian and of other ethnicities. 67.0% had a monthly household income of SGD$4000 or more. The mean baseline HbA1c was 8.10% (SD 0.95) and the mean body mass index was 26.8 kg/m2 (SD 5.3). DISCUSSION: The final participant completed month 12 follow-up data collection on 8 June 2023. All pre-planned analyses will be conducted and final results reported. TRIAL REGISTRATION: ClinicalTrials.gov NCT03800680 . Registered on 11 January 2019.

How do pilot and feasibility studies inform randomised placebo-controlled trials in surgery? A systematic review.

INTRODUCTION: Randomised controlled trials (RCTs) with a placebo comparator are considered the gold standard study design when evaluating healthcare interventions. These are challenging to design and deliver in surgery. Guidance recommends pilot and feasibility work to optimise main trial design and conduct; however, the extent to which this occurs in surgery is unknown. METHOD: A systematic review identified randomised placebo-controlled surgical trials. Articles published from database inception to 31 December 2020 were retrieved from Ovid-MEDLINE, Ovid-EMBASE and CENTRAL electronic databases, hand-searching and expert knowledge. Pilot/feasibility work conducted prior to the RCTs was then identified from examining citations and reference lists. Where studies explicitly stated their intent to inform the design and/or conduct of the future main placebo-controlled surgical trial, they were included. Publication type, clinical area, treatment intervention, number of centres, sample size, comparators, aims and text about the invasive placebo intervention were extracted. RESULTS: From 131 placebo surgical RCTs included in the systematic review, 47 potentially eligible pilot/feasibility studies were identified. Of these, four were included as true pilot/feasibility work. Three were original articles, one a conference abstract; three were conducted in orthopaedic surgery and one in oral and maxillofacial surgery. All four included pilot RCTs, with an invasive surgical placebo intervention, randomising 9-49 participants in 1 or 2 centres. They explored the acceptability of recruitment and the invasive placebo intervention to patients and trial personnel, and whether blinding was possible. One study examined the characteristics of the proposed invasive placebo intervention using in-depth interviews. CONCLUSION: Published studies reporting feasibility/pilot work undertaken to inform main placebo surgical trials are scarce. In view of the difficulties of undertaking placebo surgical trials, it is recommended that pilot/feasibility studies are conducted, and more are reported to share key findings and optimise the design of main RCTs. PROSPERO REGISTRATION NUMBER: CRD42021287371.

Optimal trial design selection: a comparative analysis between two-arm and three-arm trials incorporating network meta-analysis for evaluating a new treatment.

BACKGROUND: Planning the design of a new trial comparing two treatments already in a network of trials with an a-priori plan to estimate the effect size using a network meta-analysis increases power or reduces the sample size requirements. However, when the comparison of interest is between a treatment already in the existing network (old treatment) and a treatment that hasn't been studied previously (new treatment), the impact of leveraging information from the existing network to inform trial design has not been extensively investigated. We aim to identify the most powerful trial design for a comparison of interest between an old treatment A and a new treatment Z, given a fixed total sample size. We consider three possible designs: a two-arm trial between A and Z ('direct two-arm'), a two-arm trial between another old treatment B and Z ('indirect two-arm'), and a three-arm trial among A, B, and Z. METHODS: We compare the standard error of the estimated effect size between treatments A and Z for each of the three trial designs using formulas. For continuous outcomes, the direct two-arm trial always has the largest power, while for a binary outcome, the minimum variances among the three trial designs are conclusive only when [Formula: see text]. Simulation studies are conducted to demonstrate the potential for the indirect two-arm and three-arm trials to outperform the direct two-arm trial in terms of power under the condition of [Formula: see text]. RESULTS: Based on the simulation results, we observe that the indirect two-arm and three-arm trials have the potential to be more powerful than a direct two-arm trial only when [Formula: see text]. This power advantage is influenced by various factors, including the risk of the three treatments, the total sample size, and the standard error of the estimated effect size from the existing network meta-analysis. CONCLUSIONS: The standard two-arm trial design between two treatments in the comparison of interest may not always be the most powerful design. Utilizing information from the existing network meta-analysis, incorporating an additional old treatment into the trial design through an indirect two-arm trial or a three-arm trial can increase power.

Efficacy and Safety of Probiotics in Geriatric Patients with Constipation: Systematic Review and Meta-Analysis.

BACKGROUND: Probiotics may be an effective alternative to traditional drug therapy for constipation in the elderly. OBJECTIVE: To assess the efficacy and safety of probiotics in managing constipation among the elderly. METHODS: Eight databases were queried for randomized controlled trials (RCTs) investigating probiotics' efficacy in addressing constipation among the elderly until January 2023. The meta-analysis was conducted employing R software version 4.2.2. The Cochrane risk of bias tool was utilized to evaluate the risk of bias, and the GRADE approach was employed to assess the credibility of the evidence concerning the efficacy of probiotics in treating constipation in older individuals. RESULTS: A total of six RCTs involving 444 patients were included. Two studies were rated as low risk of bias. The meta-analysis findings revealed that probiotics, when compared to a placebo, led to an increase in stool frequency (MD = 1.02,95% CI [0.21, 2.07], p<0.05, very low quality), the probiotic group exhibited a notable impact on ameliorating symptoms associated with constipation (OR = 11.28, 95%CI [7.21, 17.64], p < 0.05, very low quality), no significant disparities were observed in terms of efforts to evacuate, manual maneuvers, and the incidence of adverse events (p>0.05). CONCLUSION: The available evidence indicates a degree of uncertainty, ranging from low-to-very low, suggesting the efficacy of probiotics in augmenting bowel frequency and ameliorating constipation-related symptoms among elderly patients with constipation. Nevertheless, given the quality of the studies included, it is advisable to conduct further well-designed investigations with substantial sample sizes to substantiate the findings of this study.

Sample Size Planning in Quantitative Nursing Research.

Editor's note: This is the 18th article in a series on clinical research by nurses. The series is designed to be used as a resource for nurses to understand the concepts and principles essential to research. Each column will present the concepts that underpin evidence-based practice-from research design to data interpretation. To see all the articles in the series, go to https://links.lww.com/AJN/A204.

Multiply robust estimator for the difference in survival functions using pseudo-observations.

BACKGROUND: When estimating the causal effect on survival outcomes in observational studies, it is necessary to adjust confounding factors due to unbalanced covariates between treatment and control groups. There is no study on multiple robust method for estimating the difference in survival functions. In this study, we propose a multiply robust (MR) estimator, allowing multiple propensity score models and outcome regression models, to provide multiple protection. METHOD: Based on the previous MR estimator (Han 2014) and pseudo-observation approach, we proposed a new MR estimator for estimating the difference in survival functions. The proposed MR estimator based on the pseudo-observation approach has several advantages. First, the proposed estimator has a small bias when any PS and OR models were correctly specified. Second, the proposed estimator considers the advantage pf the pseudo-observation approach, which avoids proportional hazards assumption. A Monte Carlo simulation study was performed to evaluate the performance of the proposed estimator. And the proposed estimator was used to estimate the effect of chemotherapy on triple-negative breast cancer (TNBC) in real data. RESULTS: The simulation studies showed that the bias of the proposed estimator was small, and the coverage rate was close to 95% when any model for propensity score or outcome regression is correctly specified regardless of whether the proportional hazard assumption holds, finite sample size and censoring rate. And the simulation results also showed that even though the propensity score models are misspecified, the bias of the proposed estimator was still small when there is a correct model in candidate outcome regression models. And we applied the proposed estimator in real data, finding that chemotherapy could improve the prognosis of TNBC. CONCLUSIONS: The proposed estimator, allowing multiple propensity score and outcome regression models, provides multiple protection for estimating the difference in survival functions. The proposed estimator provided a new choice when researchers have a "difficult time" choosing only one model for their studies.