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 1,009 records · Page 56Linked to original sources
PubMed2003

Gene and haplotype frequencies for the loci hLA-A, hLA-B, and hLA-DR based on over 13,000 german blood donors.

Numerous applications in clinical medicine and forensic sciences depend on reliable data concerning the frequencies of human leukocyte antigen (HLA) genes and haplotypes. Assuming a Hardy-Weinberg equilibrium of the underlying population, these frequencies can be estimated from phenotype data using an expectation-maximization-algorithm also known under the name "gene counting." We have refined this algorithm in order to cope with the heterogeneous resolution of HLA phenotypes frequently occurring in large datasets due to the structure of the HLA nomenclature. This was a prerequisite to analyze a set of 13,386 blood donors contributed by over 40 blood banks who were tested for HLA-DR when they volunteered to become marrow donors. This data set is still unique in the German national donor registry because their HLA-DR-typing was not biased by patient oriented searches or other strategies for selective typing. As a consequence of the size of the sample, the frequency estimates for the genes and the two- and three-locus haplotypes of HLA-A, HLA-B, and HLA-DR are of unprecedented precision and allow interesting projections concerning the efficiency and economic aspects of the development of a large donor registry in Germany.

Algorithms↗
PubMed2006

The weighted generalized estimating equations approach for the evaluation of medical diagnostic test at subunit level.

Sensitivity and specificity are common measures used to evaluate the performance of a diagnostic test. A diagnostic test is often administrated at a subunit level, e.g. at the level of vessel, ear or eye of a patient so that the treatment can be targeted at the specific subunit. Therefore, it is essential to evaluate the diagnostic test at the subunit level. Often patients with more negative subunit test results are less likely to receive the gold standard tests than patients with more positive subunit test results. To account for this type of missing data and correlation between subunit test results, we proposed a weighted generalized estimating equations (WGEE) approach to evaluate subunit sensitivities and specificities. A simulation study was conducted to evaluate the performance of the WGEE estimators and the weighted least squares (WLS) estimators (Barnhart and Kosinski, 2003) under a missing at random assumption. The results suggested that WGEE estimator is consistent under various scenarios of percentage of missing data and sample size, while the WLS approach could yield biased estimators due to a misspecified missing data mechanism. We illustrate the methodology with a cardiology example.

Biometry↗
PubMed2005

Using local data to monitor obesity rates in Wisconsin counties, 1994-2003.

INTRODUCTION: Although county-level obesity estimates are necessary for planning and evaluating community-based interventions, the quality of these data has never been examined. OBJECTIVES: To evaluate the reliability of the county-level obesity prevalence estimates from Wisconsin's 72 counties and to highlight the variation of obesity among Wisconsin counties. METHODS: Obesity prevalence data for each county in Wisconsin were obtained from the Wisconsin Behavioral Risk Factor Surveys (BRFS) from 1994 to 2003. During this 10-year period, 26,635 residents were interviewed by telephone, with sample sizes ranging from 6586 in Milwaukee County to 15 in Menominee County. The number of counties with reportable and reliable estimates, using criteria of sample sizes > or = 50 and > or = 300, respectively, was determined. RESULTS: The 10-year obesity prevalence was reportable for 68 of Wisconsin's 72 counties, ranging from 9.7% in Bayfield County to 29% in Langlade County. By pooling data from the BRFS for 5-, 3-, and 1-year periods, estimates are reportable for 43, 24, and 4 counties, respectively. A sample size of at least 300 provides a more reliable estimate, but is available for only 5 counties for a 5-year period. CONCLUSIONS: By pooling 10 years of survey data, obesity rates can be estimated for most of Wisconsin's 72 counties, demonstrating marked variation in rates across the state. This surveillance system provides valuable data for larger counties for planning and program evaluation. Supplemental surveys can be conducted to provide more reliable and timely estimates.

Humans↗
PubMed2000

Evaluation and extensions of a structural equation modeling approach to the analysis of survival data.

Recently a new method for the analysis of survival data using a structural equation modeling approach has been suggested by Pickles and colleagues using twin data they demonstrated the application of this model to study the correlation in age of onset. The purpose of the current research is twofold: 1) to evaluate the statistical performance of the model as presented by Pickles and colleagues, and 2) to expand and evaluate the model in more applications, including both genetically informative data and other multivariate examples. Results evaluated from this study involve three areas of method performance: Type-I error rates, power, and parameter estimates under four different distributions (normal, Gamma-2, Gamma-6 and g-and-h) and four different sample sizes (n = 125, 250, 500 and 750). Results based on the original Pickles model indicated that in all sample size and distribution conditions the Type-I error rate was adequate, in fact below the nominal level of .05. Additionally, power was greater than .80 for sample sizes of 500 or more for all distribution conditions. Parameter estimates were upwardly biased when the population value was rho = .20. This bias varied across distributions; the g-and-h distribution showed the largest bias. Results from the expanded model indicated that Type-I error rates were adequate. Power results were not affected by distribution type; sample sizes of 500 were above the .80 level. Parameter estimates continued to be upwardly biased in this more general model, although the degree of bias was smaller.

Bias↗
PubMed1997

Guidelines for the design and conduct of clinical trials on dentine hypersensitivity.

Clinical trials on dentine hypersensitivity have been numerous and protocols varied. To date there is little consensus as to the conduct of studies on this poorly-understood yet common and painful dental condition. A committee of interested persons from academia and industry was convened to discuss the subject of clinical trials on dentine hypersensitivity and a consensus report is presented. A double-blind randomized parallel groups design is recommended, although cross-over designs may be used for the preliminary screening of agents. Subjects may have multiple sites scored. Sample size will be determined by estimating the variability in the study population, the effect to be detected and the power of the statistical test to be used. Subject selection is based on a clinical diagnosis of dentine hypersensitivity, excluding those with conflicting characteristics such as currently-active medical or dental therapy. The vestibular surfaces of incisors, cuspids and bicuspids are preferred as sites to be tested. A range of sensitivity levels should be included. Tactile, cold and evaporative air stimuli should be applied. Negative and benchmark controls should be incorporated. Most trials should last 8 weeks. Sensitivity may be assessed either in terms of the stimulus intensity required to evoke pain or the subjective evaluation of pain produced by a stimulus using a visual analog or other appropriate scale. The subject's overall assessment may be determined by questionnaire. Outcomes should be expressed in terms of clinically significant changes in symptoms. Follow-up evaluation is required to determine the persistence of changes. At least 2 independent trials should be conducted before a product receives approval.

Air↗
PubMed2003

Can transcriptome size be estimated from SAGE catalogs?

MOTIVATION: SAGE (Serial Analysis of Gene Expression) can be used to estimate the number of unique transcripts in a transcriptome. A simple estimator that corrects for sequencing and sampling errors was applied to a SAGE library (137 832 tags) obtained from mouse embryonic stem cells, and also to Monte Carlo simulated libraries generated using assumed distributions of 'true' expression levels consistent with the data. RESULTS: When the corrected data themselves were taken as the underlying model of 'ground truth', the estimator converged to the 'true' value (53 535) only after counting 300 000 simulated tags, more than twice the number in the experiment. The SAGE data could also be well fit by a Monte Carlo model based on a truncated inverse-square distribution of expression levels, with 130 000 'true' transcripts and 10(6) samples needed for convergence. We conclude that the size of a transcriptome is ill-determined from SAGE libraries of even moderately large size. In order to obtain a valid estimate, one must sample a number of tags inversely proportional to the lowest abundance level, which is not known a priori. This constrains the design of SAGE experiments intended to determine biological complexity. AVAILABILITY: The 'homemade' software used for this analysis was not designed for general or 'production' use, but the authors will be happy to share Fortran sourcecode with interested parties. CONTACT: sternm@grc.nia.nih.gov

Algorithms↗
PubMed2002

Intake estimation of polychlorinated dibenzo-p-dioxins, dibenzofurans (PCDD/Fs) and polychlorinated biphenyls (PCBs) in salmon: the inclusion of uncertainty.

Dioxins and dioxin-like PCBs are given toxic equivalency factors (TEFs) in order to calculate the combined toxic equivalence (TEQ) of these contaminants in a sample of food. This study calculates the probability of an average consumer exceeding the recommended tolerable daily intake of 1-4 pg WHO-TEQ kg(-1) bw day(-1) as the amount of salmon in the diet is increased. Probabilistic risk analysis is used to account for the known uncertainties in this calculation. When the TEF uncertainty was excluded with no salmon consumption, the background dietary intake ranged from 1.36 to 1.78 pg TEQ kg(-1) bw day(-1). A weekly consumption of three standard salmon portions resulted in a 36% chance of exceeding the upper limit of the TDI. Inclusion of the TEF uncertainty increased the background dietary intake range from 2.1 to 4.4 pg TEQ kg(-1) bw day(-1), and the weekly consumption of one salmon portion resulted in a 79% chance of the average consumer exceeding the upper TDI. The most important factors contributing to the uncertainty in these results were, in order of magnitude, the TEF for PCB 126 and the sampling uncertainty (sample size) followed by the measurement uncertainty of PCB 126. We recommend that it is more important to increase sample size and produce more precise estimates in the TEF than to improve analytical accuracy.

Animals↗
PubMed2000

Residential randon exposure and lung cancer risk in Misasa, Japan: a case-control study.

In order to investigate an association between residential radon exposure and risk of lung cancer, a case-control study was conducted in Misasa Town, Tottori Prefecture, Japan. The case series consisted of 28 people who had died of lung cancer in the years 1976-96 and 36 controls chosen randomly from the residents in 1976, matched by sex and year of birth. Individual residential radon concentrations were measured for 1 year with alpha track detectors. The average radon concentration was 46 Bq/m3 for cases and 51 Bq/m3 for controls. Compared to the level of 24 or less Bq/m3, the adjusted odds ratios of lung cancer associated with radon levels of 25-49, 50-99 and 100 or more Bq/m3, were 1.13 (95% confidence interval; 0.29-4.40), 1.23 (0.16-9.39) and 0.25 (0.03-2.33), respectively. None of the estimates showed statistical significance, due to small sample size. When the subjects were limited to only include residents of more than 30 years, the estimates did not change substantially. This study did not find that the risk pattern of lung cancer, possibly associated with residential radon exposure, in Misasa Town differed from patterns observed in other countries.

Adult↗
PubMedDate not supplied

Life expectancy biases in clinical decision modeling.

Clinical decision models often rely upon survival models predicated on disease-specific hazard functions combined with baseline hazard functions obtained from standard life tables. Two biases may arise in such a modeling process. First, life expectancy estimates may be biased even if estimates of survival probabilities are unbiased (misestimation bias). In simulation studies, the authors discovered that the magnitude of misestimation bias is larger as life expectancy increases, sample size decreases, and censoring percentage increases. In the context of a simple decision analysis, they found that imbalances in the sample sizes for the data used to estimate the parameters among different strategies resulted in non-optimal decisions in the long run. The second bias stems from misspecification of the survival model itself (misspecification bias). Using a simple cost-effectiveness model, the authors found that life expectancies and incremental cost-effectiveness ratios differed depending on whether an excess-mortality or a proportional-hazards model was specified. In addition, a predictable pattern was observed for these two survival models when extrapolated to other age and gender groups.

Bias↗
PubMed2005

Multisystemic Therapy for social, emotional, and behavioral problems in youth aged 10-17.

BACKGROUND: Multisystemic Therapy (MST) is an intensive, home-based intervention for families of youth with social, emotional, and behavioral problems. Masters-level therapists engage family members in identifying and changing individual, family, and environmental factors thought to contribute to problem behavior. Intervention may include efforts to improve communication, parenting skills, peer relations, school performance, and social networks. Most MST trials were conducted by program developers in the USA; results of one independent trial are available and others are in progress. OBJECTIVES: To provide unbiased estimates of the impacts of MST on restrictive out-of-home living placements, crime and delinquency, and other behavioral and psychosocial outcomes for youth and families. SEARCH STRATEGY: Electronic searches were made of bibliographic databases including the Cochrane Library, C2-SPECTR, PsycINFO, Science Direct and Sociological Abstracts) as well as government and professional websites, from 1985 to January 2003. Reference lists of articles were examined, and experts were contacted. SELECTION CRITERIA: Studies where youth (age 10-17) with social, emotional, and/or behavioral problems were randomised to licensed MST programs or other conditions (usual services or alternative treatments). DATA COLLECTION AND ANALYSIS: Two reviewers independently reviewed 266 titles and abstracts; 95 full-text reports were retrieved, and 35 unique studies were identified. Two reviewers independently read all study reports for inclusion. Eight studies were eligible for inclusion. Two reviewers independently assessed study quality and extracted data from these studies.Significant heterogeneity among studies was identified (assessed using Chi-square and I(2)), hence random effects models were used to pool data across studies. Odds ratios were used in analyses of dichotomous outcomes; standardised mean differences were used with continuous outcomes. Adjustments were made for small sample sizes (using Hedges g). Pooled estimates were weighted with inverse variance methods, and 95% confidence intervals were used. MAIN RESULTS: Pooled results show no significant effects of MST on the likelihood or duration of restrictive out-of-home placements, proportion of youth who were arrested or convicted, or numbers of arrests/convictions within one-year post-intervention. There were no significant differences on drug tests or self-reported drug use at a 6-month follow-up. In analyses of post-treatment data for program completers, there were no significant between-group differences on self-reported delinquency, peer relations, youth behavior problems, youth psychiatric symptoms, parent psychiatric symptoms, or family functioning. AUTHORS' CONCLUSIONS: There is little evidence of the superiority of MST over other interventions with youth. There is also no evidence that MST has harmful effects.

Adolescent↗
PubMed1999

The design, errors and costs of a local adult oral health survey.

OBJECTIVE: To evaluate the errors and costs of a sampling and survey design for producing reliable estimates of oral health in a demographically diverse local population with a potentially high non-response rate. BASIC RESEARCH DESIGN: A two-stage cluster sample of 45-54 year old adults was drawn from a sampling frame of patients registered with local GPs and cross checked against the electoral register. The modes of data collection were interview/examination and questionnaire. Statistical properties of the estimates were evaluated and costs of the survey described. MAIN OUTCOME MEASURES: The frequency of categories of non-response were described. Sample characteristics were compared with (1) the local population's (1991) census distribution with respect to gender, ethnic composition and socio-economic group (SEG); (2) local utilisation data. The bias effects on oral health values of gender, SEG and non-response, were estimated. The design effect was described for mean number of teeth and proportion with 21 teeth or more. Optimal primary and secondary sample sizes, and non-response follow-up fractions, were estimated. CONCLUSION: This paper describes and costs a sampling and survey design which efficiently produced statistically acceptable estimates of oral health, using small samples from a selected age group in a district, posing demographic and non-response problems in ensuring reliable epidemiological results. The findings indicate that national surveys may give reasonable projected estimates for even richly diverse local populations.

Adult↗
PubMed2005

Bias of estimates of the number needed to treat.

There are several commonly used measures of association between treatment and control event rates in the population (piT and piC, respectively). One such measure, the number needed to treat (NNT) indicates the number of patients, on average, who must be treated in order to prevent one additional adverse event, and is equal to 1/(piC - piT). Because the population values piC and piT are unknown, the sample proportions (rates) pC and pT are used as estimates. The precision of a sample-based estimator is usually exhibited in terms of confidence intervals. However, the accuracy of the estimator (i.e., its bias) is often ignored. The purpose of the present study is to examine the degree of bias. Using exact calculations based on the binomial theorem, we determined the bias of an estimate of NNT conditional on pC not equal pT, and the bias of an adjusted estimator of the NNT for various sample sizes (n= 10, 20, 30, 40, 50, 100) and population parameters (0.01 < or = piC < or = 0.9; 0.01 < or = piC - piT < or = 0.8). The magnitude and non-monotonic nature of the bias are due to the NNT scale. The bias of the adjusted estimator can be approximated for some studies using the tabular results in this analysis.

Bias↗
PubMed2000

Estimation following extension of a study on the basis of conditional power.

Proschan and Hunsberger (1) propose a method based on conditional power for designed extension of a study beyond its originally intended sample size. Their data-dependent sampling method can be viewed as a two-stage procedure in which the target total sample size is dependent upon the data observed at the first stage. We demonstrate that the maximum likelihood estimate of the parameter of interest upon completion may be biased, and that this bias is similar in direction and magnitude to that commonly associated with estimation following a group sequential test with predetermined target total sample size. Furthermore, we show how a bias adjusted estimate may be formed.

Algorithms↗
PubMed1987

Kappa as an index of reproducibility: distribution under the null-hypothesis.

The authors report a Monte-Carlo study of the properties of the weighted Kappa (Kw) statistic under the null-hypothesis and the assumption of equal marginal distributions, two hypotheses required in order to use Kw as an index of reproducibility. Different factors that may affect the Kw distribution are investigated: sample size, choice of the set of weights, number of levels of the rating scale and shape of the marginal distribution. Convergence towards the asymptotic distribution is studied and confidence limits are derived. For these latter, except in the uniform marginal distribution case, the use of values obtained by simulation instead of asymptotic estimates appears to be necessary for sample sizes of 30 or less.

Epidemiologic Methods↗
PubMed2006

An ecometric analysis of neighbourhood cohesion.

BACKGROUND: It is widely believed that the social environment has an important influence on health, but there is less certainty about how to measure specific factors within the social environment that could link the neighbourhood of residence to a health outcome. The objectives of the study were to examine the underlying constructs captured by an adapted version of Buckner's neighbourhood cohesion scale, and to assess the reliability of the scale at the small-area-level by combining ecometric methodology with ordinal modelling of a five-point scale. METHODS: Data were analysed from 11,078 participants in the Caerphilly Health and Social Needs Study, who were sampled from within 325 UK census enumeration districts in Caerphilly county borough, Wales, UK. The responses of interest came from 15 question items designed to capture different facets of neighbourhood cohesion. Factor analysis was used to identify constructs underlying the neighbourhood cohesion item responses. Using a multilevel ecometric model, the variability present in these ordinal responses was decomposed into contextual, compositional, item-level and residual components. RESULTS: Two constructs labelled neighbourhood belonging and social cohesion were identified, and variability in both constructs was modelled at each level of the multilevel structure. The intra-neighbourhood correlations were 6.4% and 1.0% for the neighbourhood belonging and social cohesion subscales, respectively. Given the large sample size, contextual neighbourhood cohesion scores can be estimated reliably. The wide variation in the observed frequency of occurence of the scale item activities suggests that the two subscales have desirable ecometric properties. Further, the majority of between-neighbourhood variation is not explained by the socio-demographic characteristics of the individual respondents. CONCLUSION: Assessment of the properties of the adapted neighbourhood cohesion scale using factor analysis and ecometric analysis extended to an ordinal scale has shown that the items allow fine discrimination between individuals. However, large sample sizes are needed in order to accurately estimate contextual neighbourhood cohesion. The scale is therefore appropriate for use in the measurement of neighbourhood cohesion at small-area-level in future studies of neighbourhoods and health.

Journal Article↗
PubMed2001

Risk of hepatitis C virus infection in multiply transfused premature neonates.

BACKGROUND: Reports from around the world indicate that multiply transfused patients are at increased risk of hepatitis C virus (HCV) infection, with reported rates of between 4% and 44%. Such reports are mostly of haematological and renal patients. As recipients of blood products in the newborn period, premature infants share this risk, but there is little information regarding their risk. AIM: To assess the risk of HCV infection in children who, as premature neonates, received multiple blood products prior to the introduction of screening of donated blood for HCV. METHODS: Premature infants born between January 1985 and January 1990 who had attended our high-risk follow-up clinic were selected on the basis of the number of transfusions of blood, platelets or fresh frozen plasma they received in the newborn period. Ethical approval to offer HCV testing to parents was obtained from the Central Sydney Area Health Service Ethics Review Committee. Parents of infants who received three or more transfusions were then contacted by mail with the approved letter explaining the study, and offered HCV testing. Detection of anti-HCV antibodies was undertaken using second, and later third generation enzyme immunoassay kits. Samples which were found to be 'indeterminate' were tested using a Wellcozyme HCV western blot assay (Murex Diagnostics Ltd, Datford, UK). Hepatitis C virus-ribonucleic acid (RNA) was detected using an 'in-house' polymerase chain reaction (PCR) assay. Alanine transaminase (ALT) was also measured, with values above 55 U/L considered abnormal. RESULTS: Consent was obtained for 45 children (25 males, 20 females). The mean (+/- SEM) gestational age and weight of the children at birth was 26.7 +/- 0.2 weeks and 938 +/- 27 g, respectively. The children received 198 transfusions of blood products, an average of 4.4 U per child. All of the infants except for one were negative for anti-HCV antibodies. One infant was 'indeterminate' (low positive on third generation test but negative on second generation test), but proved negative subsequently on both western blot and PCR testing. HCV-RNA was not detected in any of the infants on PCR testing. All of the samples had normal ALT values, the mean being 16 U/L (range 8-52). CONCLUSION: None of the children consenting to this study had evidence of current HCV infection. Because of the sample size, we were not able to estimate the true risk of infection from this study, except that the upper limit for the risk is about 1/200 per transfused blood sample.

Blood Transfusion↗
PubMed2000

Genetic and environmental influences on functional abilities in Danish twins aged 75 years and older.

BACKGROUND: Functional abilities vary widely among elderly persons. The determinants of this variation are probably multiple and include normal aging processes as well as disease expression. This study estimates the relative importance of genetic and environmental factors to variation in functional abilities in elderly persons. METHODS: We conducted a survey among all Danish twins aged 75 years and older who were identified in the population-based Danish Twin Registry. Interviews were conducted with 77% (7% by proxy responders) of the 3099 individuals in the study population. Functional abilities were assessed by validated Danish survey instruments and were scored on three scales. Heritability (proportion of the population variance attributable to genetic variation) was estimated using structural equation analyses. RESULTS: Structural equation analyses revealed a substantial heritability (34%-47%) for the three functional ability scores among the women aged 80 years and older compared with a more modest heritability (15%-34%) among the women aged 75-79 years. The remaining variation could be attributed to individuals' nonfamilial environments. Comparisons of the functional abilities of twins with living versus deceased co-twins also suggested a difference in the genetic influence for the two age groups. Although heritability estimates were uniformly low in the male participant sample, the size of the sample was not sufficiently large to allow for precise estimates of heritability. CONCLUSION: For women we found that the effect of genetic factors on functional abilities increases with age and accounts for one third to one half of the variation among individuals aged 80 years and older. An understanding of the genetic mechanisms underlying functional abilities in the oldest individuals may enhance the possibilities for improving health in the elderly population by modifying environmental factors.

Activities of Daily Living↗
PubMed1990

Estimation issues in clinical trials and overviews.

There is a general move towards greater emphasis on point and interval estimates of treatment effect in reporting of clinical trials, so that significance testing plays a lesser role. In this article we examine a number of issues which affect the use and interpretation of conventional estimation methods. Should we accept or avoid the stereotypes of 95 per cent confidence? Should the abstract of a trial report include confidence intervals for major endpoints? Are frequentist confidence intervals being interpreted correctly, and should Bayesian probability intervals be more widely used in trial reports? Does the timing of publication, such as early stopping because of a large observed treatment difference, lead to exaggerated point and interval estimates? How can we produce realistic estimates from subgroup analyses? Is publication bias seriously affecting our ability to obtain unbiased estimates? Is the emphasis on estimation methods a powerful tool for encouraging larger sample sizes? Can we resolve the controversy concerning fixed or random effects models for estimation in overviews of related trials? Our arguments are illustrated by results from recent trials in cardiovascular disease.

Bayes Theorem↗