Sample size and repeated measures required in studies of foods in the homes of African-American families.
Ontology highlight
ABSTRACT:
SUBMITTER: Stevens J
PROVIDER: S-EPMC3349983 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:In the design of a randomized clinical trial with one pre and multiple post randomized assessments of the outcome variable, one needs to account for the repeated measures in determining the appropriate sample size. Unfortunately, one seldom has a good estimate of the variance of the outcome measure, let alone the correlations among the measurements over time. We show how sample sizes can be calculated by making conservative assumptions regarding the correlations for a variety of covariance structures. The most conservative choice for the correlation depends on the covariance structure and the number of repeated measures. In the absence of good estimates of the correlations, the sample size is often based on a two-sample t-test, making the 'ultra' conservative and unrealistic assumption that there are zero correlations between the baseline and follow-up measures while at the same time assuming there are perfect correlations between the follow-up measures. Compared to the case of taking a single measurement, substantial savings in sample size can be realized by accounting for the repeated measures, even with very conservative assumptions regarding the parameters of the assumed correlation matrix. Assuming compound symmetry, the sample size from the two-sample t-test calculation can be reduced at least 44%, 56%, and 61% for repeated measures analysis of covariance by taking 2, 3, and 4 follow-up measures, respectively. The results offer a rational basis for determining a fairly conservative, yet efficient, sample size for clinical trials with repeated measures and a baseline value.
| S-EPMC4100335 | biostudies-literature
Project description:While many studies have sought a window into the genetics of schizophrenia, few have focused on African-American families. An exception is the Project among African-Americans to Explore Risks for Schizophrenia (PAARTNERS), which seeks to identify novel and known risk variation for schizophrenia by genetic analyses of African-American families. We report a linkage study of diagnostic status in 217 African-American families using the Illumina Linkage Panel. Due to assumed incomplete and time-dependent penetrance, we performed linkage analysis using two different treatments of diagnosis: (1) treating both affected and unaffected individuals as informative for linkage (using the program SIBPAL) and (2) treating only affected individuals as informative (using the program MERLIN). We also explore three definitions of affected status: narrowly defined schizophrenia; one broadened to include schizoaffective disorder; and another including all diagnoses indicating psychosis. Several regions show a decrease in the evidence for linkage as the definition broadens 8q22.1 (rs911, 99.26 cM; SIBPAL p-value [p] goes from 0.006 to 0.02), 16q24.3 (rs1006547, 130.48 cM; p from 0.00095 to 0.0085), and 20q13.2 (rs1022689, 81.73 cM; p from 0.00015 to 0.032). One region shows a substantial increase in evidence for linkage, 11p15.2 (rs722317, 24.27 cM; p from 0.0022 to 0.0000003); MERLIN results support the significance of the SIBPAL results (p=0.00001). Our linkage results overlap two broad, previously-reported linkage regions: 8p23.3-p12 found in studies sampling largely families of European ancestry; and 11p11.2-q22.3 reported by a study of African-American families. These results should prove quite useful for uncovering loci affecting risk for schizophrenia.
| S-EPMC2721327 | biostudies-literature
Project description:This study presents results from a randomized controlled trial of the Protecting Strong African American Families (ProSAAF) program, a family-centered intervention designed to promote strong couple, coparenting, and parent-child relationships in two-parent African American families. A total of 346 African American couples with an early adolescent child participated; all families lived in rural, low-income communities in the southern USA. Intent-to-treat growth curve analyses involving three waves and spanning 17 months indicated that ProSAAF participants, compared with control participants, reported greater improvements in relationship communication, confidence, satisfaction, partner support, coparenting, and parenting. More than 80% of the couples attended all six of the in-home, facilitator-led sessions; costs to implement the program averaged $1739 per family. The findings inform the ongoing debate surrounding prevention programs for low-income and ethnic minority couples.
| S-EPMC6177321 | biostudies-literature
Project description:BackgroundSupervised learning methods need annotated data in order to generate efficient models. Annotated data, however, is a relatively scarce resource and can be expensive to obtain. For both passive and active learning methods, there is a need to estimate the size of the annotated sample required to reach a performance target.MethodsWe designed and implemented a method that fits an inverse power law model to points of a given learning curve created using a small annotated training set. Fitting is carried out using nonlinear weighted least squares optimization. The fitted model is then used to predict the classifier's performance and confidence interval for larger sample sizes. For evaluation, the nonlinear weighted curve fitting method was applied to a set of learning curves generated using clinical text and waveform classification tasks with active and passive sampling methods, and predictions were validated using standard goodness of fit measures. As control we used an un-weighted fitting method.ResultsA total of 568 models were fitted and the model predictions were compared with the observed performances. Depending on the data set and sampling method, it took between 80 to 560 annotated samples to achieve mean average and root mean squared error below 0.01. Results also show that our weighted fitting method outperformed the baseline un-weighted method (p < 0.05).ConclusionsThis paper describes a simple and effective sample size prediction algorithm that conducts weighted fitting of learning curves. The algorithm outperformed an un-weighted algorithm described in previous literature. It can help researchers determine annotation sample size for supervised machine learning.
| S-EPMC3307431 | biostudies-literature
Project description:Sarcoidosis is a granulomatous inflammatory disorder of complex etiology with significant linkage to chromosome 5, and marginal linkage was observed to five other chromosomes in African Americans (AAs) in our previously published genome scan. Because genetic factors underlying complex disease are often population specific, genetic analysis of samples with diverse ancestry (i.e., ethnic confounding) can lead to loss of power. Ethnic confounding is often addressed by stratifying on self-reported race, a controversial and less-than-perfect construct. Here, we propose linkage analysis stratified by genetically determined ancestry as an alternative approach for reducing ethnic confounding. Using data from the 380 microsatellite markers genotyped in the aforementioned genome scan, we clustered AA families into subpopulations on the basis of ancestry similarity. Evidence of two genetically distinct groups was found: subpopulation one (S1) comprised 219 of the 229 families, subpopulation two (S2) consisted of six families (the remaining four families were a mixture). Stratified linkage results suggest that only the S1 families contributed to previously identified linkage signals at 1p22, 3p21-14, 11p15, and 17q21 and that only the S2 families contributed to those found at 5p15-13 and 20q13. Signals on 2p25, 5q11, 5q35, and 9q34 remained significant in both subpopulations, and evidence of a new susceptibility locus at 2q37 was found in S2. These results demonstrate the usefulness of stratifying on genetically determined ancestry, to create genetically homogeneous subsets--more reliable and less controversial than race-stratified subsets--in which to identify genetic factors. Our findings support the presence of sarcoidosis-susceptibility genes in regions identified elsewhere but indicate that these genes are likely to be ancestry specific.
| S-EPMC1592564 | biostudies-literature
Project description:This study focuses on sample size determination in repeated measures studies with multinomial outcomes from multiple factors. In settings where multiple factors have repeated measures, a single subject could have hundreds of observations. Sample size selection may then refer to the number of subjects, the number of levels within a factor, or the number of repetitions within the level. We simulate multinomial data through a generalized linear mixed model (GLMM) with and without overdispersion, compute the empirical power of detecting group difference for several analytical methods and contrast their performance in group comparison studies with repeated multinomial data. We use four spatial functions to model the spatial correlation structures among observations. We evaluate the factors affecting the power under various scenarios. We also present a dataset typical in hearing studies for sound localization, in which a spatially distributed array of audio loudspeakers plays multiple sounds in order to compare two programming schemes for a hearing aid device.
| S-EPMC3339260 | biostudies-literature
Project description:ObjectivesWe sought to understand why randomised controlled trials in septic shock have failed to demonstrate effectiveness in the face of improving overall outcomes for patients and seemingly promising results of early phase trials of interventions.DesignWe performed a retrospective analysis of large critical care trials of severe sepsis and septic shock. Data were collected from the primary trial manuscripts, prepublished statistical plans or by direct communication with corresponding authors.SettingCritical care randomised control trials in severe sepsis and septic shock.Participants14 619 patients randomised in 13 trials published between 2005 and 2015, enrolling greater than 500 patients and powered to a primary outcome of mortality.InterventionMultiple interventions including the evaluation of treatment strategies and novel therapeutics.Primary and secondary outcome measuresOur primary outcome measure was the difference between the anticipated and actual control arm mortality. Secondary analysis examined the actual effect size and the anticipated effect size employed in sample size calculation.ResultsIn this post hoc analysis of 13 trials with 14 619 patients randomised, we highlight a global tendency to overestimate control arm mortality in estimating sample size (absolute difference 9.8%, 95% CI -14.7% to -5.0%, p<0.001). When we compared anticipated and actual effect size of a treatment, there was also a substantial overestimation in proposed values (absolute difference 7.4%, 95% CI -9.0% to -5.8%, p<0.0001).ConclusionsAn interpretation of our results is that trials are consistently underpowered in the planning phase by employing erroneous variables to calculate a satisfactory sample size. Our analysis cannot establish if, given a larger sample size, a trial would have had a positive result. It is disappointing so many promising phase II results have not translated into durable phase III outcomes. It is possible that our current framework has biased us towards discounting potentially life-saving treatments.
| S-EPMC6119416 | biostudies-literature
Project description:African Americans (AAs) are disproportionately affected by metabolic diseases and adverse drug events, with limited publicly available genomic and transcriptomic data to advance the knowledge of the molecular underpinnings or genetic associations to these diseases or drug response phenotypes. To fill this gap, we obtained 60 primary hepatocyte cultures from AA liver donors for genome-wide mapping of expression quantitative trait loci (eQTL) using LAMatrix. We identified 277 eGenes and 19,770 eQTLs, of which 67 eGenes and 7,415 eQTLs are not observed in the Genotype-Tissue Expression Project (GTEx) liver eQTL analysis. Of the eGenes found in GTEx only 25 share the same lead eQTL. These AA-specific eQTLs are less correlated to GTEx eQTL in effect sizes and have larger Fst values compared to eQTLs found in both cohorts (overlapping eQTLs). We assessed the overlap between GWAS variants and their tagging variants with AA hepatocyte eQTLs and demonstrated that AA hepatocyte eQTLs can decrease the number of potential causal variants at GWAS loci. Additionally, we identified 75,002 exon QTLs of which 48.8% are not eQTLs in AA hepatocytes. Our analysis provides the first comprehensive characterization of AA hepatocyte eQTLs and highlights the unique discoveries that are made possible due to the increased genetic diversity within the African ancestry genome.
2020-03-27 | GSE147628 | GEO
Project description:BackgroundGenome-wide association studies have identified polymorphisms associated with breast cancer subtypes and across multiple population subgroups; however, few studies to date have applied linkage analysis to other population groups.MethodsWe performed the first genome-wide breast cancer linkage analysis in 106 African American families (comprising 179 affected and 79 unaffected members) not known to be segregating BRCA mutations to search for novel breast cancer loci. We performed regression-based model-free multipoint linkage analyses of the sibling pairs using SIBPAL, and two-level Haseman-Elston linkage analyses of affected relative pairs using RELPAL.ResultsWe identified -log10 P values that exceed 4 on chromosomes 3q and 12q, as well as a region near BRCA1 on chromosome 17 (-log10 P values in the range of 3.0-3.2) using both sibling-based and relative-based methods; the latter observation may suggest that undetected BRCA1 mutations or other mutations nearby such as HOXB13 may be segregating in our sample.ConclusionsIn summary, these results suggest novel putative regions harboring risk alleles in African Americans that deserve further study.ImpactWe hope that our study will spur further family-based investigation into specific mechanisms for breast cancer disparities.
| S-EPMC4323921 | biostudies-literature
Project description:BACKGROUND:The goal of adaptation is to maintain the effectiveness of the original intervention by preserving the core elements that account for its success while delivering an intervention that is tailored to the new community and/or cultural context. The current study describes the process of adapting an evidence-based smoke-free homes (SFH) intervention for use in American Indian/Alaska Native (AI/AN) households. METHODS:We followed a systematic adaptation process. We first assessed the community through focus groups coordinated in collaboration with tribal partners. Because our team included the original developers of the intervention, the steps of understanding the intervention, selecting the intervention and consulting with experts were simplified. Additional steps included consulting with stakeholders through a national work group and collaboratively deciding what needed adaptation. RESULTS:A number of key themes pertinent to the adaptation of the SFH intervention were identified in the focus groups. These included the gravity of messaging about commercial tobacco use; respect, familialism, and intergenerationalism; imagery, including significant symbolism, colors, and representative role models; whether and how to address traditional tobacco; and, barriers to a SFH not adequately addressed in the original materials. CONCLUSIONS:Adaptation of an intervention to create smoke-free homes in AI/AN families necessitated both surface structure changes such as appearance of role models and deep structure changes that addressed core values, and beliefs and traditions.
| S-EPMC6651935 | biostudies-literature