Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Sample Size”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 433 records · Page 24Linked to original sources
PubMed1997

Motor unit number estimation: sample size considerations.

A computer model of the motor unit number estimation procedure was developed to evaluate the sampling error associated with estimates of the number of motor units in muscles. Two different distributions were used to model the motor unit amplitude distribution and were chosen in such a manner that they qualitatively matched the distributions observed under both normal and neurogenic conditions. As expected, the results indicated that estimation error decreases as a function of sample size. However, the relationship between these two variables was nonlinear in the sense that successive increases in sample size lead to progressively smaller decreases in estimation error. The results also indicated that the shape of the motor unit amplitude distribution plays an important role. Specifically, estimates obtained using the distribution modeling normal muscle were generally higher than the actual number of motor units in the muscle, which was not the case for the distribution modeling neurogenic muscle. In addition, the neurogenic distribution was associated with much smaller estimation error, suggesting that motor unit number estimation is well suited to the analysis of neurogenic disease processes.

Cell Count↗
PubMed2003

Power and sample size calculations for generalized regression models with covariate measurement error.

Covariate measurement error is often a feature of scientific data used for regression modelling. The consequences of such errors include a loss of power of tests of significance for the regression parameters corresponding to the true covariates. Power and sample size calculations that ignore covariate measurement error tend to overestimate power and underestimate the actual sample size required to achieve a desired power. In this paper we derive a novel measurement error corrected power function for generalized linear models using a generalized score test based on quasi-likelihood methods. Our power function is flexible in that it is adaptable to designs with a discrete or continuous scalar covariate (exposure) that can be measured with or without error, allows for additional confounding variables and applies to a broad class of generalized regression and measurement error models. A program is described that provides sample size or power for a continuous exposure with a normal measurement error model and a single normal confounder variable in logistic regression. We demonstrate the improved properties of our power calculations with simulations and numerical studies. An example is given from an ongoing study of cancer and exposure to arsenic as measured by toenail concentrations and tap water samples.

Arsenic↗
PubMed2005

The effect of intraspecific sample size on type I and type II error rates in comparative studies.

Comparative studies have increased greatly in number in recent years due to advances in statistical and phylogenetic methodologies. For these studies, a trade-off often exists between the number of species that can be included in any given study and the number of individuals examined per species. Here, we describe a simple simulation study examining the effect of intraspecific sample size on statistical error in comparative studies. We find that ignoring measurement error has no effect on type I error of nonphylogenetic analyses, but can lead to increased type I error under some circumstances when using independent contrasts. We suggest using ANOVA to evaluate the relative amounts of within- and between-species variation when considering a phylogenetic comparative study. If within-species variance is particularly large and intraspecific sample sizes small, then either larger sample sizes or comparative methods that account for measurement error are necessary.

Biological Evolution↗
PubMed1994

Tutorial: planning for data collection. Part III--Sample size.

There is no simple answer to the question, "how large a sample should I take?" Sample size depends on various data collection design details and on how we intend to use the data in future decision making. But with careful thought and some basic statistical knowledge, even nonstatisticians can determine the appropriate sample size for achieving useful results from data collection efforts.

Data Collection↗
PubMed2004

Musculoskeletal parameters of muscles crossing the shoulder and elbow and the effect of sarcomere length sample size on estimation of optimal muscle length.

BACKGROUND: Knowledge of musculoskeletal parameters is essential to understanding and modeling a muscle's force generating capability. A study of musculoskeletal parameters was conducted in two parts: (I) Empirical measurement of upper extremity musculoskeletal parameters. (II) Computational bootstrap simulation to examine statistical power of detecting optimal muscle length as a function of sarcomere length sample size and effect size. METHODS: Parameters were determined with a cadaver model. Sarcomere lengths were measured for 120 samples per muscle using laser diffraction and the mean sarcomere length used to estimate optimal muscle length. A bootstrap computational simulation was conducted to estimate variance in mean sarcomere length as a function of sample size. Statistical power for detecting optimal muscle length as a function of sample size and effect size was then determined. FINDINGS: Parameters are reported in tabular format. Power is 80% at approximately 85, 50, 40 and 25 samples for effect sizes of 0.5, 0.75, 1.0 and 1.5 mm respectively. INTERPRETATION: Musculoskeletal parameters for predicting muscle forces can be adequately measured in a cadaver model. Measurement of 40-60 sarcomere lengths per muscle is sufficient to calculate mean sarcomere length for estimating optimal muscle length with power of 80% for an effect size of 0.75-1.0 mm.

Adult↗
PubMed2000

A statistical model for assessing sample size for bacterial colony selection: a case study of Escherichia coli and avian cellulitis.

A general problem for microbiologists is determining the number of phenotypically similar colonies growing on an agar plate that must be analyzed in order to be confident of identifying all of the different strains present in the sample. If a specified number of colonies is picked from a plate on which the number of unique strains of bacteria is unknown, assigning a probability of correctly identifying all of the strains present on the plate is not a simple task. With Escherichia coli of avian cellulitis origin as a case study, a statistical model was designed that would delineate sample sizes for efficient and consistent identification of all the strains of phenotypically similar bacteria in a clinical sample. This model enables the microbiologist to calculate the probability that all of the strains contained within the sample are correctly identified and to generate probability-based sample sizes for colony identification. The probability of cellulitis lesions containing a single strain of E. coli was 95.4%. If one E. coli strain is observed out of three colonies randomly selected from a future agar plate, the probability is 98.8% that only one strain is on the plate. These results are specific for this cellulitis E. coli scenario. For systems in which the number of bacterial strains per sample is variable, this model provides a quantitative means by which sample sizes can be determined.

Animals↗
PubMed1983

A method for the rapid assessment of sample size in dietary studies.

Critical readers should be suspicious about the inability of a dietary study to discriminate between the energy intakes of two groups when small sample sizes have been used. The possibility of a false-negative (type II error) should be considered. This problem could be avoided if investigators used adequate sample sizes. A review of 26 dietary studies published in the American Journal of Clinical Nutrition between 1979 and 1981 revealed that the median "SD of energy intakes" was 525 kcal/day. This figure was used to illustrate a simple method for estimating appropriate sample sizes assuming type I and type II error probabilities of 0.05. Prospective use of this method should increase the reproducibility of conclusions drawn from dietary studies.

Calorimetry↗
PubMed1999

Sample size and the study of F waves.

Ulnar nerve F waves were studied in 23 healthy volunteers and 27 diabetic patients. Latencies and chronodispersion were analyzed in each group for different sample sizes. Significant differences were not detected with the different sample sizes for mean latencies, with samples above 16 stimuli or 10 waves for minimum and maximum latencies and above 20 stimuli or 16 waves for chronodispersion. These findings suggest that these limits may be adequate for group comparison. However, for the analysis of individual patients, the evidence suggests that larger samples are required for the determination of the minimum and maximum latencies and chronodispersion.

Adolescent↗
PubMed2006

Sample size calculations based on generalized estimating equations for population pharmacokinetic experiments.

We present a method for calculating the sample size of a pharmacokinetic study analyzed using a mixed effects model within a hypothesis testing framework. A sample size calculation method for repeated measurement data analyzed using generalized estimating equations has been modified for nonlinear models. The Wald test is used for hypothesis testing of pharmacokinetic parameters. A marginal model for the population pharmacokinetic is obtained by linearizing the structural model around the subject specific random effects. The proposed method is general in that it allows unequal allocation of subjects to the groups and accounts for situations where different blood sampling schedules are required in different groups of patients. The proposed method has been assessed using Monte Carlo simulations under a range of scenarios. NONMEM was used for simulations and data analysis and the results showed good agreement.

Computer Simulation↗
PubMed2005

Bilateral symmetry of the human metacarpal: implications for sample size calculations.

OBJECTIVE: The aim of this study was to assess the three-dimensional mechanical symmetry of the human second metacarpal and provide sample size estimates for future mechanical intervention studies of the metacarpal. DESIGN: Bone densitometry and digital image analysis were used to assess the morphometric, geometric and densitometric symmetry of the second human metacarpal. BACKGROUND: An assessment of the left-right mechanical symmetry of the human metacarpal is important in considering the suitability of using the contralateral metacarpal as a control and in providing sample size calculations for future studies involving a mechanical intervention to the metacarpal such as implantation of a metacarpophalangeal prosthesis. METHODS: Metaphyseal sectional areas, diaphyseal cortical sectional areas, second moments of area, average periosteal and medullary radii and bone densities were measured at nine transverse levels for each of seven pairs of index metacarpals using computed tomography and bone densitometry. Polar Fourier regression was used to assess the morphometry of sectional periosteal and endosteal boundaries. Differences between clinically important left-right parameters were assessed. RESULTS: Mean differences between clinically important left-right parameters were small (<3%) and similar to the degree of experimental precision. There were strong significant left-right correlations for the morphometric, geometric and densitometric parameters considered, indicating a high degree of bilateral mechanical symmetry. CONCLUSIONS: The contralateral bone is a suitable control for mechanical intervention studies of the human metacarpal, and the use of bilateral pairing results in an important reduction in sample size. RELEVANCE: Responses to mechanical interventions on the human metacarpal, such as implantation of a metacarpophalangeal prosthesis, are generally unknown. The degree of left-right mechanical symmetry in the human metacarpal provides a measure of the advantage of using paired design studies to address these questions.

Anatomy, Cross-Sectional↗
PubMed2003

Considerations on sample size and power calculations in randomized clinical trials.

Many studies in orthopaedics and sports medicine have not considered sample size or statistical power as important issues in study design. This article addresses the importance of a sample size calculation in randomized clinical trials and the components of the calculations that researchers must consider in their preliminary planning of an investigation. The types of data being collected, level of significance, types I and II errors, and power are also addressed.

Humans↗
PubMed2002

Sample size requirements for matched case-control studies of gene-environment interaction.

Consideration of gene-environment (GxE) interaction is becoming increasingly important in the design of new epidemiologic studies. We present a method for computing required sample size or power to detect GxE interaction in the context of three specific designs: the standard matched case-control; the case-sibling, and the case-parent designs. The method is based on computation of the expected value of the likelihood ratio test statistic, assuming that the data will be analysed using conditional logistic regression. Comparisons of required sample sizes indicate that the family-based designs (case-sibling and case-parent) generally require fewer matched sets than the case-control design to achieve the same power for detecting a GxE interaction. The case-sibling design is most efficient when studying a dominant gene, while the case-parent design is preferred for a recessive gene. Methods are also presented for computing sample size when matched sets are obtained from a stratified population, for example, when the population consists of multiple ethnic groups. A software program that implements the method is freely available, and may be downloaded from the website http://hydra.usc.edu/gxe.

Black or African American↗
PubMed1987

Sample size in the planning and interpretation of clinical trials.

An understanding of sample size determination is important in both planning and interpreting the results of clinical trials. A Type II error occurs when it is concluded that there is no difference between treatment groups, when in truth there is a difference. Such a false negative conclusion results from too few patients in a trial. In this review the principles of estimating sample size before a trial is commenced and evaluating the results of a negative completed trial are reviewed. Clinically relevant examples are used to illustrate these concepts.

Biometry↗
PubMed2003

Matched-pair noninferiority trials using rate ratio: a comparison of current methods and sample size refinement.

In this article, we consider the establishment of noninferiority between a reference test and a new test with respect to the ratio of sensitivity and/or specificity. We first review two (one-sided) noninferiority tests, namely the logarithmic transformation test and the Fieller-type test, and their associated sample size formulae proposed for matched-pair designs when the null hypothesis is of a specified nonunity rate ratio. Different methods for implementing these one-sided noninferiority tests are reviewed. They include (1) the sample-based method, (2) the constrained least-squares estimation method, and (3) the constrained maximum likelihood estimation method. We conduct a simple empirical study to evaluate the performance of various tests/methods. In summary, statistics based on constrained maximum likelihood estimation always control the actual type I error rate much better than other statistics. Moreover, the corresponding approximate sample size formulae are valid asymptotically in the sense that the exact powers associated with the approximate sample size formulae are generally close to the prespecified power level. Methods based on constrained maximum likelihood estimation are illustrated with a real example from a clinical laboratory study.

Clinical Trials as Topic↗
PubMed2006

Proof-of-principle phase II MRI studies in stroke: sample size estimates from dichotomous and continuous data.

BACKGROUND AND PURPOSE: Since the failure of a number of phase III trials of neuroprotection in ischemic stroke, the need for smaller phase II studies with MRI surrogates has emerged. There is, however, little information available about sample size requirements for such phase II trials and rarely enough patients in single studies to make robust estimates. We have formed an international collaborative group to assemble larger datasets and from these have generated sample size tables for MRI-based infarct expansion as the outcome measure. METHODS: Twelve centers from Australia, Europe, and North America contributed data from patients with hemispheric ischemic stroke. Infarct expansion was defined from initial diffusion-weighted images and later fluid-attenuated inversion recover or T2 images. Sample size estimates were calculated from data on infarct expansion ratios treated as dichotomous or continuous variables. A nonparametric approach was used because the distribution of infarct expansion was resistant to all forms of transformation. RESULTS: As an example, a 20% absolute reduction in infarct expansion ratio (< or = 1), 80% power, and alpha = 0.05 requires 99 patients in each arm. To achieve an equivalent effect size with a continuous approach requires 61 patients. CONCLUSIONS: These tables will be useful in planning phase II trials of therapy with the use of MRI outcome measures. For positive studies, biologically plausible surrogates such as these may provide a rationale for proceeding to phase III trials.

Australia↗
PubMed2000

Clinical trials in the genomic era: effects of protective genotypes on sample size and duration of trial.

It is well known that individuals can vary widely in their disease susceptibilities. One potential source of this variation is the genetic makeup of individuals, which can confer either protection or susceptibility to disease. Here we examine the effects of protective genotypes on the sample sizes and time required to detect differences between clinical trial arms. We show that including individuals with protective genotypes in a clinical trial can increase required sample sizes and trial duration. One can deal with this issue by pregenotyping subjects and selectively enrolling them based on their genotype. Thus we also calculate the number of individuals that must be recruited and pregenotyped to fulfill sample size requirements. The benefits of genotypically screening study subjects will depend on numerous factors, including ease of patient recruitment, cost of genotyping, long-term costs of study (or long-term cost per subject), and the strength of the protective effect. We present several examples that show the potential value of incorporating information about protective genotypes into a clinical trial.

Clinical Trials as Topic↗
PubMed2005

Sample size calculations for comparative clinical trials with over-dispersed Poisson process data.

This paper develops a new formula for sample size calculations for comparative clinical trials with Poisson or over-dispersed Poisson process data. The criteria for sample size calculations is developed on the basis of asymptotic approximations for a two-sample non-parametric test to compare the empirical event rate function between treatment groups. This formula can accommodate time heterogeneity, inter-patient heterogeneity in event rate, and also, time-varying treatment effects. An application of the formula to a trial for chronic granulomatous disease is provided.

Clinical Trials as Topic↗