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 757 records · Page 42Linked to original sources
PubMed1993

Sample size and power determination for a binary outcome and an ordinal exposure when logistic regression analysis is planned.

General methods of sample size determination for logistic regression analyses are now available, but these will often require substantial information for their application. The author presents methods useful in the special case of a binary outcome and a three-level quantitative exposure, which includes application to a three-level ordinal exposure for a specified scaling. The computationally simple methods were developed in planning an investigation of the prognostic value of multidrug resistance gene (mdr1) expression in sarcoma. Because logistic regression was planned for the analysis, calculations were based on the ability to detect a linear trend in the log odds of tumor response to chemotherapy associated with increases in the level of mdr1 expression from negative to low positive to high positive. Closed form expressions were used to assess sensitivity to the ordinal scaling and the distribution of the mdr1 levels, and to the assumption of a linear trend in the log odds versus a linear trend in the proportions.

Case-Control Studies↗
PubMed2005

Two-stage case-control studies: precision of parameter estimates and considerations in selecting sample size.

A two-stage case-control design, in which exposure and outcome are determined for a large sample but covariates are measured on only a subsample, may be much less expensive than a one-stage design of comparable power. However, the methods available to plan the sizes of the stage 1 and stage 2 samples, or to project the precision/power provided by a given configuration, are limited to the case of a binary exposure and a single binary confounder. The authors propose a rearrangement of the components in the variance of the estimator of the log-odds ratio. This formulation makes it possible to plan sample sizes/precision by including variance inflation factors to deal with several confounding factors. A practical variance bound is derived for two-stage case-control studies, where confounding variables are binary, while an empirical investigation is used to anticipate the additional sample size requirements when these variables are quantitative. Two methods are suggested for sample size planning based on a quantitative, rather than binary, exposure.

Case-Control Studies↗
PubMed2003

Overestimation of genetic risks owing to small sample sizes in cardiovascular studies.

We sought evidence of publication bias to explain conflicting findings in studies of angiotensin-converting enzyme deletion polymorphism (ACE D) and glycoprotein IIIa PlA2 (PLA2) polymorphism and the risk of myocardial infarction. Factor 5 Leiden (F5L), a well-established thrombotic risk factor, served as an internal comparison. We conducted systematic reviews of published studies involving ACE D, PLA2, F5L and relevant outcomes, searching medline (January 1990 through February, 2001), bibliographies, and meta-analyses. Random effects pooled odds ratios (95% confidence interval) for cardiovascular outcomes were as follows: PLA2 (n = 13,167 subjects): 1.13 (1.02, 1.26); ACE D (n = 42,140 subjects): 1.22 (1.11, 1.35); and F5L (n = 27,277 subjects): 4.43 (3.65, 5.38). However, funnel plots of ACE D and PLA2, but not F5L, showed an inverse relationship between sample size and odds ratios for ACE D (p = 0.02) and PLA2 (p = 0.04) but not F5L (p = 0.65) by Egger's test for potential publication bias. Despite research-based genotyping of over 50,000 subjects, the overall risk for myocardial infarction as a result of PLA2 and ACE D remains doubtful. Our study provides a clear example of how publication of underpowered studies can spuriously implicate polymorphisms as genetic risk factors.

Cardiovascular Diseases↗
PubMed2005

Sample sizes for clinical trials with time-to-event endpoints and competing risks.

We consider clinical trials where the time to occurrence of events in the presence of competing risks is the primary endpoint for treatment evaluation. The number of events with regard to the defined primary endpoint required to ensure the specified power can be calculated according to Schoenfeld's formula like in classical survival studies. However, determination of the number of patients that have to be recruited to observe the calculated number of events requires specification of the length of the accrual period, the trial duration and assumptions about the event-specific hazard functions. Information from previous studies about expected failure rates for the reference treatment is useful and can be translated into assumptions about the appropriate model parameters. A formula for sample size computation is presented for two competing outcome states. Nomograms help to communicate different alternatives of duration and size of the trial to interdisciplinary committees whose members plan and monitor the clinical trial. The 4D trial (Die Deutsche Diabetes Dialyse Studie) designed to compare lipid lowering treatment with HMG-CoA reductase inhibitor atorvastatin with placebo in type 2 diabetic patients on hemodialysis with respect to time to the composite event "cardiovascular death or non-fatal myocardial infarction" is used as an example to outline the statistical methods.

Clinical Trials Data Monitoring Committees↗
PubMed1994

The effect of sample size on the estimation of the frequency of DNA-profiles in RFLP-analysis.

Restriction fragment length polymorphism analysis (RFLP-analysis) was carried out on blood samples from 616 unrelated Danish Caucasians. DNA was restricted with Hinf I and analyzed with the single locus variable number tandem repeats (VNTR) probes MS1, MS31, MS43a and YNH24. The effect of the sample size on the estimates of the frequencies of DNA-profiles was investigated using reference samples of 50-1200 bands for each probe. The effects of using the upper confidence limit and a minimum default allele frequency in the calculation of the frequency of the DNA-profile were investigated. It is concluded that very small samples, e.g. 50 individuals, may be used as reference samples in the estimation of the frequency of a DNA-profile. The use of an upper confidence limit was without significant effect, whereas the use of a minimum default allele frequency prevented large underestimates.

Alleles↗
PubMed1995

Sample sizes for comparative inhaled corticosteroid trials with emphasis on showing therapeutic equivalence.

In the near future it is to be expected that many new inhaled corticosteroids or formulations of these drugs will be compared with older ones, to discover whether they are therapeutically equivalent or not. The statistical evaluation of these trials differs from the classic methods. When two averages are similar or differ only slightly, power is very low. The regulatory bodies demand a power of at least 80%. This problem was initially solved by using the so-called power approach. Researchers included enough volunteers to enable them to detect a predefined difference, considered to be without any clinical significance, with a power of 80%. This approach, however, has been shown to be incorrect and has been replaced by the two one-sided tests procedure, where a new sample size equation is derived. Important elements of this new equation are the coefficient of variation of the parameter measured, the difference between the averages of the two groups and the equivalence limit (the difference between the means still tolerable). This equation was used in the present study to estimate the number of volunteers needed in a parallel inhaled corticosteroids equivalence trial. The end points chosen were the changes in FEV1 and PC20 due to the corticosteroid effect. Calculations were performed by extracting data from published placebo-controlled trials, and defining a range of equivalence limits and differences between the group averages. It was shown that a huge number of volunteers (500-1000) will be needed, as a result of the small corticosteroid effect and the high variance.(ABSTRACT TRUNCATED AT 250 WORDS)

Administration, Inhalation↗
PubMed1997

Sample size estimation in studies monitoring exercise-induced bronchoconstriction in asthmatic children.

BACKGROUND: The repeatability of the response to standardised treadmill exercise testing using dry air and monitoring of heart rate in asthmatic children suffering from exercise-induced bronchoconstriction (EIB) has not been well established. METHODS: Twenty seven asthmatic children with known EIB performed standardised exercise testing twice within a period of three weeks. The tests were performed on a treadmill while breathing dry air. During both tests heart rate had to reach 90% of the predicted maximum. Response to exercise was expressed as % fall in forced expiratory volume in one second (FEV1) from baseline and as area under the curve (AUC) of the time-response curve. RESULTS: The intra-class correlation coefficients for % fall and AUC (log-transformed) were 0.57 and 0.67, respectively. From these data, power curves were constructed that allowed estimations to be made of sample sizes required for studies of EIB in children. These indicated that, if a drug is expected to reduce EIB by 50%, as few as 12 patients would be sufficient to demonstrate this effect (90% power) using a parallel design study. CONCLUSIONS: Standardised exercise testing for EIB using dry air and monitoring of heart rate is adequately repeatable for use in research and clinical practice in children with asthma.

Adolescent↗
PubMed2005

Penalized Cox regression analysis in the high-dimensional and low-sample size settings, with applications to microarray gene expression data.

MOTIVATION: An important application of microarray technology is to relate gene expression profiles to various clinical phenotypes of patients. Success has been demonstrated in molecular classification of cancer in which the gene expression data serve as predictors and different types of cancer serve as a categorical outcome variable. However, there has been less research in linking gene expression profiles to the censored survival data such as patients' overall survival time or time to cancer relapse. It would be desirable to have models with good prediction accuracy and parsimony property. RESULTS: We propose to use the L(1) penalized estimation for the Cox model to select genes that are relevant to patients' survival and to build a predictive model for future prediction. The computational difficulty associated with the estimation in the high-dimensional and low-sample size settings can be efficiently solved by using the recently developed least-angle regression (LARS) method. Our simulation studies and application to real datasets on predicting survival after chemotherapy for patients with diffuse large B-cell lymphoma demonstrate that the proposed procedure, which we call the LARS-Cox procedure, can be used for identifying important genes that are related to time to death due to cancer and for building a parsimonious model for predicting the survival of future patients. The LARS-Cox regression gives better predictive performance than the L(2) penalized regression and a few other dimension-reduction based methods. CONCLUSIONS: We conclude that the proposed LARS-Cox procedure can be very useful in identifying genes relevant to survival phenotypes and in building a parsimonious predictive model that can be used for classifying future patients into clinically relevant high- and low-risk groups based on the gene expression profile and survival times of previous patients.

Biomarkers, Tumor↗
PubMed1999

Determination of power and sample size in the design of clinical trials with failure-time endpoints and interim analyses.

An important but difficult task in the design of a clinical trial to compare time to failure between two treatment groups is determination of the number of patients required to achieve a specified power of the test. Because patients typically enter the trial serially and are followed until they fail or withdraw from the study or until the study is terminated, the power of the test depends on the accrual pattern, the noncompliance rate, and the withdrawal rate in addition to the actual survival distributions of the two groups. Incorporating interim analyses and the possibility of early stopping into the trial increases its complexity, and although normal approximations have been developed for computing the significance level of the test when the log-rank or other rank statistics are used, there are no reliable analytic approximations for evaluating the power of the test. This article presents methods, based on Monte Carlo simulations and recent advances in group sequential testing with time-to-event responses, to choose appropriate test statistics, compute power and sample size at specified alternatives, check the adequacy of commonly used normal approximations of the type I error probability, and assess the performance of different interim analysis strategies. It also presents two computer programs implementing these methods.

Adrenergic beta-Antagonists↗
PubMed1996

A computer program for sample size and power calculations in the design of multi-arm and factorial clinical trials with survival time endpoints.

This paper presents a computer program for use in the design of long-term clinical trials with multiple treatment arms in which the primary outcome variables are censored survival times. The treatment arms may be structured as a one-way or multi-way factorial design. It is assumed that patients are entered and randomized to a treatment arm during an accrual period. The patients are then followed for a fixed period during which there may be dropouts. Various distributional assumptions can be used to model the survival times. These include an option in which there is an effect of treatment duly after a lag or delay time. The program then computes the power of various statistical tests of hypotheses concerning treatment differences, interactions and trends. The power computations are "exact" in that they use the Monte Carlo method to obtain Type I and II error probabilities. However the program also outputs the normal approximations for comparison, although they are typically not accurate in these situations. Fisher's LSD method is used to adjust for the multiple comparisons. By comparing the power for various sets of design parameters, such as sample size, numbers of factor levels, patient accrual rate, and length of follow-up, an appropriate design can be constructed. Two examples are provided. The first is a simple one-way layout with multiple treatment arms; the second a two-way factorial design for a proposed large scale cancer chemoprevention trial.

Clinical Trials as Topic↗
PubMed1998

Non-invasive measurements of arterial structure and function: repeatability, interrelationships and trial sample size.

1. Repeatability of measurements of arterial compliance and flow-mediated dilation of the brachial artery has been infrequently reported, despite increasing use in interventional and risk-factor modification studies. Furthermore, little is known about the interrelationships of the various indices. The purposes of this study were to determine the repeatability and interrelationships of a range of arterial indices.2. Fifty healthy volunteers, 20 men and 30 women, aged 20-70 (mean 46.5) years, were studied on two occasions, using an identical protocol, at a mean interval of 2.5 weeks. Tonometry, ultrasound and Doppler technique were used to measure the following: carotid wall intima-media thickness (IMT), total systemic artery compliance (SAC), arterial pulse wave velocity [PWV aorto-femoral (A-F), and femoral-dorsalis pedis (F-D)], carotid distensibility coefficient (DC) and carotid augmentation index (AI). Brachial flow-mediated dilation was measured in 30 subjects with analysis of diameter change for 4 min post ischaemia.3. There were no systematic differences over the observed range of measurements for any of the reported parameters. Coefficients of variation were as follows: IMT 2.8%, SAC 9.2%, PWV(A-F) 3.2%, PWV(F-D) 5.0%, DC 10.0%, AI 1.3%. Brachial flow-mediated dilation curves were not different between visits; changes were maximum 60-s post ischaemia. All indices of arterial compliance were significantly correlated with age. The three different indices of central arterial compliance [SAC, PWV(A-F) and AI] were significantly correlated with carotid intima-media thickness.4. Under controlled experimental conditions there was good repeatability of measurements of indices between sessions of both intrinsic and functional arterial mechanical properties (central and carotid arterial compliance, intima-media thickness and brachial flow-mediated dilation). Sample size tables for clinical trials using these indices are presented.

Adult↗
PubMed1989

A program to calculate sample size, power, and least detectable relative risk using a programmable calculator.

A program for the Hewlett Packard 41 series programmable calculator that determines sample size, power, and least detectable relative risk for comparative studies with independent groups is described. The user may specify any ratio of cases to controls (or exposed to unexposed subjects) and, if calculating least detectable relative risks, may specify whether the study is a case-control or cohort study.

Cohort Studies↗
PubMed2002

Characterization of soil organic matter content of two sample size populations along a climatic transect.

Soil organic matter (SOM) content was determined in two populations of soil samples that were taken from 0-2 soil depth. One population represented soil samples that were taken from a square of 25 cm2 in size (small-S population) and the other population represented soil samples that were taken from a square of 2500 cm2 in size (large-L population). The samples were collected on hillslopes in different climatic regions: Mediterranean (GIV), semi-arid (MAL), mildly-arid (MIS) and arid (KAL). The results of both S and L populations showed decreasing SOM mean and variance from the Mediterranean site to the arid site. Statistical and spatial characteristics of each population were compared between the climatic regions. In addition, comparison between the two populations was made for each site. The difference in sample size did not significantly affect the mean values of SOM of the two populations in sites GIV, MAL and KAL, but did affect the mean at site MIS. At all study sites, except for site MAL, the variance increased with decreasing sample size. At sites GIV and KAL the coefficient of variation of S population was higher (more than 1.5 times) than that of L population, whereas at sites MAL and MIS, the differences were negligible. The relationships between the values of S and L samples at the individual sampling points defined the background of the study sites, which reflects the effect of vegetation (type), grazing, biological crust and soil properties. It was found that at the extreme sites GIV and KAL the background was characterized by relatively low SOM content with small areas of high organic matter content. At site MIS the background was characterized by relatively high SOM with small areas of low organic matter content. At site MAL the background was not dominated by high values of SOM nor by low ones. The spatial pattern of L population became more simple with increasing aridity. At the relatively wet sites the spatial pattern did not depend on the sample size while in the more arid sites it was sample size dependent. It was indicated that the spatial structure of SOM at the semi-arid and mildly arid sites is anisotropic whereas at the Mediterranean and arid sites it is isotropic.

Climate↗
PubMed2003

Data adaptive interim modification of sample sizes for candidate-gene association studies.

OBJECTIVES: The use of conventional Transmission/Disequilibrium tests in the analysis of candidate-gene association studies requires the precise and complete pre-specification of the total number of trios to be sampled to obtain sufficient power at a certain significance level (type I error risk). In most of these studies, very little information about the genetic effect size will be available beforehand and thus it will be difficult to calculate a reasonable sample size. One would therefore wish to reassess the sample size during the course of a study. METHOD: We propose an adaptive group sequential procedure which allows for both early stopping of the study with rejection of the null hypothesis (H0) and for recalculation of the sample size based on interim effect size estimates when H0 cannot be rejected. The applicability of the method which was developed by Müller and Schäfer [Biometrics 2001;57:886-891] in a clinical context is demonstrated by a numerical example. Monte Carlo simulations are performed comparing the adaptive procedure with a fixed sample and a conventional group sequential design. RESULTS: The main advantage of the adaptive procedure is its flexibility to allow for design changes in order to achieve a stabilized power characteristic while controlling the overall type I error and using the information already collected. CONCLUSIONS: Given these advantages, the procedure is a promising alternative to traditional designs.

Data Interpretation, Statistical↗
PubMedDate not supplied

Reducing sample sizes when comparing experimental and control groups.

In comparing rates for two groups (one control and the other experimental), one may use an historical control to reduce the sample size needed for a test of significance to one-fourth that required if the control is not historical. If there is some doubt as to whether one's control is comparable to the historical control, a test showing the equality of the historical and experimental controls can lead to a halving of the sample required for significance testing. This same argument also applies to the comparison of two means.

Research Design↗
PubMed1984

Analysis of picogram quantities of protein in subnanoliter-size samples.

The ability to measure protein concentration in subnanoliter volumes would be helpful in many biological studies. A microassay for measuring nanogram protein quantities in nanoliter-size samples and an ultramicroassay for measuring picogram quantities in picoliter samples were developed to measure lymphatic protein concentration. Aliquots of a sample solution were mixed with an o-phthalaldehyde mercaptoethanol reagent using micropipetting techniques. Reaction product fluorescence was measured using a modified Leitz MPV-1 microscope as a microfluorometer. Fluorescence varied linearly with albumin concentrations between 1 and 8 g/100 ml. A typical microassay measuring albumin standards at 0.0, 1.0, 2.0, and 4.0 g/100 ml yielded a linear regression of y = 207x + 60 (r = 0.99). Minimum detectable protein concentration was 0.125 g/100 ml. The SE for the albumin standards varied from 0.02 to 0.17 g/100 ml. An ultramicroassay measuring similar standards yielded a linear regression of y = 1180x + 109 (r = 0.96). Minimum detectable protein concentration was 0.028 g/100 ml. The SE for the standards varied from 0.01 to 0.32 g/100 ml.

Albumins↗
PubMed1976

Reduction of sample size on the Technicon SMA 6/60 continuous-flow analyzer.

The manifold of the Sequential Multiple Analyzer SMA 6/60 (4 + 2) has been modified to decrease serum sample size to 90 mul, by using a common diluent for all six channels and recycling the discard of each dialyzer into the next one. The modification can be made in less than 4 h without the need for any additional parts; the modified manifold requires one-third fewer pump lines and fewer reagents, thus reducing operating costs and simplifying instrument maintenance, while retaining the same precision, speed, low carryover, and linearity of the production model.

Autoanalysis↗