Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Sample size estimation”

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 1,135 records · Page 63Linked to original sources
PubMed2003

Likelihood inference for exchangeable binary data with varying cluster sizes.

This article investigates maximum likelihood estimation with saturated and unsaturated models for correlated exchangeable binary data, when a sample of independent clusters of varying sizes is available. We discuss various parameterizations of these models, and propose using the EM algorithm to obtain maximum likelihood estimates. The methodology is illustrated by applications to a study of familial disease aggregation and to the design of a proposed group randomized cancer prevention trial.

Algorithms↗
PubMed2007

Closed-form confidence intervals on measures of precision for an interlaboratory study.

Within the pharmaceutical industry it is common practice to transfer analytical methods from one laboratory to other laboratories. An experiment or interlaboratory study is performed to estimate the repeatability, the intermediate precision, and the reproducibility of the analytical method. These measures of precision are quantified by appropriate sums of variance components from an analysis of variance model describing the structure of the data. In the literature, several methods have been described for calculating approximate (closed-form) confidence intervals on sums of variance components, i.e., Welch, Satterthwaite, and modified large-sample (MLS). Comparisons between these methods have been performed for one-way and two-way classification analysis of variance models only. Interlaboratory studies though often need higher order classifications. Therefore, these methods for constructing confidence intervals are compared on the measures of precision from a specfic three-way classification analysis of variance model that is frequently used for method transfer studies. Using a simulation study, the coverage probability for these methods is evaluated in situations where variance components may be estimated negatively with the standard moment estimates and where either the standard moment estimates are adjusted to zero or remain unadjusted. The MLS method is superior to the other two methods in case the standard moment estimates are used. If the adjusted moment estimates are used, then the method of Satterthwaite performs similar to the MLS method for many settings of the variance components and sample sizes but much better for some particular settings. The method of Satterthwaite performs better than the method of Welch for all the selected settings of variance components and sample sizes, irrespective of the standard or adjusted moment estimates.

Analysis of Variance↗
PubMed2006

Organochlorine contaminants in complete clutches of Morelet's crocodile (Crocodylus moreletii) eggs from Belize.

Seven complete clutches of Morelet's crocodile (Crocodylus moreletii) eggs were collected in northern Belize and examined for organochlorine (OC) pesticide residues. The primary OC detected, p,p-DDE, was found in every egg analyzed (n=175). Other OCs detected included p,p-DDT, p,p-DDD, methoxychlor, aldrin, and endosulfan I. Concentrations of individual OCs ranged from 4 ppb (ng chemical/g egg wet weight) to greater than 500 ppb. A statistical evaluation of p,p-DDE levels in three complete clutches was used to derive the minimum number of eggs needed from a clutch to precisely determine the mean p,p-DDE concentration representative of that clutch. Sample sizes of 8 (80% confidence level) and 11 (90% confidence level) were determined to yield an accurate estimate of contaminant levels in a full clutch of eggs. The statistically recommended sample size of 11 eggs (at 90% confidence level) was successfully tested on the four additional clutches.

Aldrin↗
PubMed2006

A retrospective cohort study of Southeast Asian patients with large congenital melanocytic nevi and the risk of melanoma development.

BACKGROUND: The lifetime risk of developing melanoma in Caucasian patients with large congenital melanocytic nevi (LCMN) is estimated to be between 4.5% and 10%. Cohort studies of LCMN and the risk of melanoma development in an Asian population are not available. OBJECTIVE: We sought to determine the risk of melanoma development in a retrospective cohort of patients presenting with LCMN to a dermatology tertiary referral center in Singapore from January 1989 to December 2004. METHODS: Patients with congenital melanocytic nevi (CMN) that covered at least 5% of the body surface area were included in the study. Data were obtained from electronic records and photographic documentation. A search for malignancy was done using the National Cancer Registry database. RESULTS: In all, 39 patients (23 male and 16 female) met the study criteria of LCMN; 15 of 39 patients also met the criteria of having a giant CMN (ie, a CMN that is predicted to be at least 20-cm diameter in adulthood). There were 29 Chinese, 6 Malay, 1 Indian, and 3 Caucasian patients. Their ages ranged from 23 months to 60 years (mean 18.8 years). They presented at a mean age of 26 months and were followed up for an average of 16.9 years. The size of the LCMN ranged from 5% to 40% of body surface area, with a mean of 12.2%. The most common sites were the back (54%), lower limb (28%), and abdomen (26%). Satellite lesions were present in 22 patients. Magnetic resonance imaging of the head or thoracolumbar spine was performed in 7 patients with LCMN on the scalp/face or back, respectively; all produced normal findings. Only one patient was treated: he had carbon-dioxide laser ablation and Q-switched neodymium:yttrium-aluminum-garnet laser treatment of a small part of his LCMN. Skin biopsies were done in 5 patients who had developed nodules; histology showed no evidence of malignancy. No patients had developed any form of malignancy. LIMITATIONS: The addition of 3 adult patients born before the start of the cancer registry may have led to survivor bias. The small sample size did not allow a precise estimate of the risk of melanoma development in our study population. CONCLUSION: The risk of melanoma development in LCMN within a predominantly Southeast Asian cohort appears to be very low. Prophylactic complete excision of LCMN is ideal, but seldom achievable. Hence, patient education, regular melanoma surveillance, and biopsy of suspicious lesions are very important.

Adolescent↗
PubMed2006

[Anesthesia practice in Catalonia, Spain: background, objectives, and design of the ANESCAT 2003 survey].

BACKGROUND AND OBJECTIVE: The increasing workload in anesthesiology together with the shortage of anesthetists has led to worldwide concern within the specialty. In 2003, the Catalan Society of Anesthesiology, Critical Care and Pain Therapy undertook the ANESCAT survey to determine the anesthesia practice workload in Catalonia, Spain. PATIENTS AND METHOD: A set of 3 questionnaires was used to quantify anesthesia practice and resources. A sample size of 12,228 events was estimated to be necessary to be representative of the number of anesthetic procedures carried out in Catalonia annually. A prospective, cross-sectional survey was carried out on 14 randomly chosen days in 2003. Each hospital designated a coordinator responsible for ensuring that a questionnaire was filled in for each anesthetic procedure, to provide information about patient characteristics, anesthetic technique, and the intervention for which anesthesia was needed. RESULTS: All 131 public and private hospitals in which anesthetic procedures were carried out participated. The geographic distribution was as follows: Barcelona city, 54 (41.2%); rest of the province of Barcelona, 39 (29.8%); Tarragona, 15 (11.5%); Girona, 14 (10.7%), and Lleida, 9 (6.9%). A total of 23,136 questionnaires about anesthesia procedures were received; the number of questionnaires returned on the selected workdays varied by 1.85% and the percentage of incomplete returns was less than 5%. The number of individual anesthetists returning questionnaires for processing was 765. CONCLUSIONS: This large-scale study was possible thanks to a simple design and the strong motivation of a community of anesthesiologists. The results have provided an accurate picture of anesthesia practice within a specific geographical area. Such studies are necessary for introducing organizational changes and applying for additional resources.

Age Distribution↗
PubMed2006

Interval estimates of weighted effect sizes in the one-way heteroscedastic ANOVA.

A framework for comparing normal population means in the presence of heteroscedasticity and outliers is provided. A single number called the weighted effect size summarizes the differences in population means after weighting each according to the difficulty of estimating their respective means, whether the difficulty is due to unknown population variances, unequal sample sizes or the presence of outliers. For an ANOVA weighted for unequal variances, we find interval estimates for the weighted effect size. In addition, the weighted effect size is shown to be a monotone function of a suitably defined weighted coefficient of determination, which means that interval estimates of the former are readily transformed into interval estimates of the latter. Extensive simulations demonstrate the accuracy of the nominal 95% coverage of these intervals for a wide range of parameters.

Analysis of Variance↗
PubMed2005

Underwater video as a monitoring tool to detect change in seagrass cover.

To date seagrass monitoring has involved the removal of seagrass from its environment. In fragile or highly disturbed systems, monitoring using destructive techniques may interfere with the environment or add to the burden of disturbance. Video photography is a form of non-destructive monitoring that does not require the removal of seagrass or interference with the environment and has the potential to be a valuable tool in monitoring seagrass systems. This study investigated the efficacy of video photography as a tool for detecting change in seagrass cover, using the temperate Australian species Amphibolis antarctica (Labill.) Sonder ex Aschers. Using visual and random point estimates of seagrass cover from video footage, it was possible to determine the minimum sample size (number of random video frames) needed to detect change in seagrass cover, the minimum detectable change in cover and the probability of the monitoring design committing a Type II error. Video footage was examined at three scales: transects (m apart), sites (km apart) and regions (tens of km apart). Using visual and random point estimation techniques, a minimum sample size of ten quadrats per transect was required to detect change in uniform and variable seagrass cover. With ten quadrats it was possible to identify a minimum detectable change in cover of 15% for uniform and 30% for variable seagrass cover. Power analysis was used to determine the probability of committing a Type II error from the data. Region level data had low power, corresponding to a high risk of committing a Type II error. Site and transect level data had high power corresponding to a low risk of committing a Type II error. Based on this study's data, managers using video to monitor for change in seagrass cover are advised to use data from the smaller scale, for example, site and transect level data. By using data from the smaller scale, managers will have a low risk of incorrectly concluding there has not been a disturbance when one has actually occurred.

Ecosystem↗
PubMed1986

Small sample properties of some parametric bioassay estimators of the LD90.

Bioassay experiments are frequently conducted with small sample sizes, but the literature offers little comparative information for small sample sizes among the analytical procedures. A computer simulation study was performed to compare several traditional analytical procedures for estimating the LD90. These estimation procedures include probit analysis with maximum likelihood estimation, logit analysis with maximum likelihood, and minimum chi 2 estimation methods. The stimulation results indicate the conditions under which each analytical method appears most useful. Recommendations are tentatively made for minimally adequate designs for bioassay studies where an LD90 is to be estimated.

Animals↗
PubMed1994

Interactions between stroke data banks and clinical trials.

The number of clinical trials to evaluate new therapies for stroke treatment and prevention is growing rapidly. Although stroke data banks cannot answer treatment efficacy questions, they can have powerful interactions with the design and conduct of clinical trials. Through data banks one can generate hypotheses regarding treatment, estimate the frequency of outcome events, calculate sample size, determine stratification factors that may or may not be needed in a clinical trial, establish inclusion and exclusion criteria and decide on the elements to include in the data collection forms. Using a data bank one can estimate the number of patients that may be screened, eligible, refused, and enrolled in a clinical trial with given inclusion and exclusion criteria. Data banks are helpful for surveillance of all eligible subjects and calculating the proportion of the total cases who were randomized. With the more widespread analyses of stroke data banks we can design focused clinical trials and reach some definitive conclusions regarding the future treatment of stroke.

Bias↗
PubMed2000

Laser Doppler scanning: how many measurements are required to assess regional cerebral blood flow?

This study was initiated to determine the optimal number of measuring sites necessary to estimate regional cerebral blood flow (CBF) under pathophysiological conditions. 25 rats were exposed to 15 minutes of global cerebral ischemia. Local CBF was sequentially measured by laser Doppler (LD) at 32 locations during baseline conditions, ischemia and reperfusion using a computer-controlled scanning technique. A simulation study was performed based on 800 local measurements at each time point: random samples (size 1-100) were repeatedly drawn to estimate the variability of median flow. Accuracy was defined as probability that the simulated median differed less than +/- 5 LD-units from the true median of the 800 data. Above a single location, CBF was measured with an accuracy of 21.6 +/- 0.4% (baseline conditions, n = 100 simulations, mean +/- SEM), 85.8 +/- 0.4% (ischemia) and 11.1 +/- 0.3% (30th min. reperfusion). Accuracy increases to 75.2 +/- 0.5% (baseline conditions), 100 +/- 0% (ischemia) and 41.8 +/- 0.6% (30th min. reperfusion) if 24 locations are scanned. Scanning, therefore, improves accuracy and reduces variability of CBF measurements. With enough local CBF measurements laser Doppler assessment of regional CBF is possible. Single location CBF assessment is sufficiently accurate only during ischemia. During reperfusion, when accuracy is half reduced compared to baseline conditions, larger sample sizes are required.

Animals↗
PubMed2000

Intraclass correlations from a community-based alcohol prevention study: the effect of repeat observations on the same communities.

OBJECTIVE: School- and community-based alcohol prevention programs are often evaluated using a group-randomized trial (GRT) design with a single pretest and a single posttest survey. To size such studies properly, investigators need accurate estimates of the variance and intraclass correlation that will be operative in their analyses. Until recently, the only available estimates were based on cross-sectional analyses. A recent report suggests that values from cross-sectional analyses may overestimate the intraclass correlation operative in pretest-posttest analyses. The purpose of this article is to review these issues, present estimates of intraclass correlation for a variety of alcohol-related endpoints based on cross-sectional analyses and to compare those estimates to estimates based on pretest-posttest analyses. We will also show how these estimates can be used to establish optimal sample sizes for GRTs to evaluate school- and community-based alcohol prevention programs. METHOD: Data were collected from 18 to 20 year olds and high-school seniors as part of an alcohol prevention effort employing a group-randomized trial design with a single pretest and a single posttest survey. Data were analyzed via mixed-model regression methods to estimate components of variance. Those components were then used to compute the intraclass correlations operative in both cross-sectional analyses and in pretest-posttest analyses. RESULTS: Results indicate that intraclass correlations operative in pretest-posttest analyses are much smaller than are those operative in cross-sectional analyses. CONCLUSIONS: Our findings indicate that future alcohol-prevention studies employing a group-randomized trial design with a single pretest and single posttest survey may not need to be as large as previously suggested by intraclass correlation estimates based on cross-sectional data. This holds true even if they are analyzed to reflect the extra variation typical of group-randomized trials.

Adolescent↗
PubMedDate not supplied

Designing population pharmacokinetic studies: performance of mixed designs.

The interplay of the following factors: population design (PDN), the cost function in terms of maximum cost (Max. C) (i.e., maximum number of samples/sample size), sample size, and intersubject variability [restricted (30%) to moderate (60%)] on the estimation of pharmacokinetic parameters from population pharmacokinetic data sets obtained using mixed designs was investigated in a simulation study. A two compartment model with multiple bolus intravenous inputs was assumed, and the residual variability was set at 15%. The sample size (N) investigated ranged from 30 to 200 with the associated cost function varying accordingly with the five individual and sixteen population designs studied. Accurate and precise estimates of structural model parameters were obtained for N > or = 50 (Max. C > or = 150) irrespective of the intersubject variability (ITV) and PDN investigated. When ITV was 30%, all structural model parameters were well estimated irrespective of the PDN. Robust estimates of clearance and its variability were obtained for all N at all levels of ITV with Max. C > or = 90 (PDN > or = 4). Imprecise estimates of ITV in V1, V2, and Q were obtained at 60% ITV irrespective of N, PDN, or Max. C. Positive bias was associated with the estimation of variability in V1, V2, and Q with PDN < or = 4 (Max. C < or = 150). This was due in part to a greater proportion of subjects sampled only once. Correspondingly, residual variability was underestimated. It is of utmost importance to avoid this artifact by ensuring that at least a moderate subset of subjects contributing data to a population pharmacokinetic study contribute data more than once. Given a sample size and ITV, the cost function must be considered in designing a population pharmacokinetic study using mixed designs.

Humans↗
PubMed2002

Statistical properties of Teng and Risch's sibship type tests for detecting an association between disease and a candidate allele.

Risch and Teng [Genome Res 1998;8:1273-1288] and Teng and Risch [Genome Res 1999;9:234-241] proposed a class of transmission/disequilibrium test-like statistical tests based on the difference between the estimated allele frequencies in the affected and control populations. They evaluated the power of a variety of family-based and nonfamily-based designs for detecting an association between a candidate allele and disease. Because they were concerned with diseases with low penetrances, their power calculations assumed that unaffected individuals can be treated as a random sample from the population. They predicted that this assumption rendered their sample size calculations slightly conservative. We generalize their partial ascertainment conditioning by including the status of the unaffected sibs in the calculations of the distribution and power of the statistic used to compare the allele frequency in affected offspring to the estimated frequency in the parents, based on sibships with genotyped affected and unaffected sibs. Sample size formulas for our full ascertainment methods are presented. The sample sizes for our procedure are compared to those of Teng and Risch. The numerical results and simulations indicate that the simplifying assumption used in Teng and Risch can produce both conservative and anticonservative results. The magnitude of the difference between the sample sizes needed by their partial ascertainment approximation and the full ascertainment is small in the circumstances they focused on but can be appreciable in others, especially when the baseline penetrances are moderate. Two other statistics, using different estimators for the variance of the basic statistic comparing the allele frequencies in the affected and unaffected sibs are introduced. One of them incorporates an estimate of the null variance obtained from an auxiliary sample and appears to noticeably decrease the sample sizes required to achieve a prespecified power.

Case-Control Studies↗
PubMed1982

Effects of field size when using Kerley's histological method for determination of age at death.

The field size at which a bone is read affects the results obtained when using Kerley's histological method for age estimation, even after applying the recommended correction factor. Whereas there is no tendency for any one of three field sizes tested to consistently underestimate or overestimate age, a field size closest to that used by Kerley in his original study had significantly lower variances for its age estimates, and thus provides greater reliability. This particular field size yields more precise estimates because it is sampling a pattern and number of structures more similar to that of Kerley. Correction factors cannot equalize the counts of osteons and osteon fragments because of spatial variations in the distributions of these histological structures. A field size similar to that used by Kerley in gathering the data from which he developed his regression equations must be used to assure that the same pattern and number of structures is being sampled. For this reason, we suggest a field size as close to 2.06 mm2 as possible be used when employing Kerley's method.

Adolescent↗
PubMed1996

The estimation of caries prevalence in small areas.

National surveys have been effective for the estimation of caries prevalence in broad regions of the US. However, it is unclear if data from such surveys can be used to estimate prevalences in small areas such as states or counties because of small sample sizes within individual areas. In this study, we applied specialized statistical methods to the estimation of small-area caries measures using data from an oral health survey conducted in the State of Washington. Dental exams to assess caries and the presence of sealants and fluorosis were performed on 2921 third-grade students in 84 public schools selected by a stratified random sample from all 39 counties in the state. Statistical methods for small-area estimation were used to estimate disease and sealant utilization measures for each of the counties. Adjustment was made for covariates measured at the school level, including ethnicity and the proportion of children in the Federally sponsored school lunch program. Substantial variability in disease and sealant utilization between counties was found. The estimated number of decayed and filled surfaces per child was 4.7 (inter-county range, 2.4 to 7.4). The estimated number of surfaces of untreated decay was 1.2 per child overall (range, 0.5 to 3.1). Thirty percent of the children had restorative treatment needs (range, 15 to 54%). The prevalence of sealants on one or more permanent molars was estimated to be 34% (range, 19 to 46%). Overall, only 8% of children showed evidence of fluorosis. The results demonstrate the usefulness of small-area estimation methods for oral health surveys.

Child↗
PubMed2003

Errors and linkage disequilibrium interact multiplicatively when computing sample sizes for genetic case-control association studies.

Single nucleotide polymorphisms (SNP) may be used in case-control designs to test for association between a SNP marker and a disease. Such designs may assume that the genotype data are reported without error. Our goal is quantifying the effects that errors have on sample size for case-control studies with haplotypes formed by a disease locus and a SNP marker locus in the presence of linkage disequilibrium (LD). We consider the effects of a recently published error model on 2x3 chi-square analysis. We study the joint relation of LD and errors with sample size for three specific genetic disease models and two settings each of marker allele frequencies (total of 6 studies). Minimal sample size necessary for fixed asymptotic power is estimated as a 4th degree polynomial in the variables S (error) and D' (LD measure) via a backward step-wise regression. We find that increased error rates lower power. In all studies, we observe that LD and errors interact in a non-linear fashion. In particular, regression analyses shows that several higher order interaction terms have coefficients significantly different from 0 in each study, with fraction of variance explained greater than 0.9999. Finally, the increase in sample size necessary to maintain constant asymptotic power and level of significance as a function of S is smallest when D' = 1 (perfect LD). The increase grows monotonically as D' decreases to 0.5 for all studies.

Case-Control Studies↗
PubMed1998

On the sampling variance of intraclass correlations and genetic correlations.

Widely used standard expressions for the sampling variance of intraclass correlations and genetic correlation coefficients were reviewed for small and large sample sizes. For the sampling variance of the intraclass correlation, it was shown by simulation that the commonly used expression, derived using a first-order Taylor series performs better than alternative expressions found in the literature, when the between-sire degrees of freedom were small. The expressions for the sampling variance of the genetic correlation are significantly biased for small sample sizes, in particular when the population values, or their estimates, are close to zero. It was shown, both analytically and by simulation, that this is because the estimate of the sampling variance becomes very large in these cases due to very small values of the denominator of the expressions. It was concluded, therefore, that for small samples, estimates of the heritabilities and genetic correlations should not be used in the expressions for the sampling variance of the genetic correlation. It was shown analytically that in cases where the population values of the heritabilities are known, using the estimated heritabilities rather than their true values to estimate the genetic correlation results in a lower sampling variance for the genetic correlation. Therefore, for large samples, estimates of heritabilities, and not their true values, should be used.

Analysis of Variance↗
PubMed1998

Age-specific familial risks in common cancers of the offspring.

Quantitative data on familial cancer risks are important for clinical, psychological and scientific reasons. The available estimates carry many uncertainties due to sample size and possible bias in data collection and often refer to first-degree relatives of unspecified age and sex. We calculated sex- and age-specific familial hazard ratios (FHRs) of cancer in offspring aged 15-53 years of cancer probands at 16 male and 17 female cancer sites, based on registered nation-wide data, free from bias. The familial risks in offspring were high, > 5 for thyroid (FHR 10.7 in all offspring, CI 95% 6.9-16.6), and testicular cancer (FHR 5.4, CI 95% 2.6-11.3), or intermediate, FHR 2-5, for colon, rectal, lung, breast, cervical, uterine, ovarian, skin (melanoma and squamous cell) and other endocrine gland cancers. FHRs < 2.0 were observed for stomach, renal and nervous system cancers, lymphomas and leukemias. Some sex differences were observed: FHRs for male breast (only 2 cases) and thyroid cancers were over 2 times higher than the respective female ones. When parents were diagnosed before age 50 years, offspring were at an increased risk of familial breast, renal, skin (melanoma), nervous system, thyroid and non-thyroid endocrine gland cancers, particularly affecting young (< 40 years) individuals. The parental diagnostic age also affected offspring's risk of colon, rectal, uterine and ovarian cancers, but young individuals were not at a particular risk. No effect of age was noted for cervical cancer and lymphoma.

Adult↗