Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “sampling design”

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 145 records · Page 8Linked to original sources
PubMed1991

Cognitive abilities and achievement status of children with myelomeningocele: a contemporary sample.

Designed study as a conceptual replication of Shaffer, Friedrich, Shurtleff, and Wolf (1985). Intelligence, school achievement, and perceptual motor skill data from 73 children with uncomplicated myelomeningocele were examined to determine their deviation from test norms. The respective impact of shunting and functional motor level was also assessed. The sample as a whole functioned below WISC-R and VMI norms. On the WRAT, deviation from the norms was evident only for the Arithmetic subtest. Partial replication of the Shunt X Motor level interaction reported by Shaffer et al. (1985) was obtained. Limitations of small-sample studies are discussed.

Adolescent↗
PubMed2003

Experimental design and sample size determination for testing synergism in drug combination studies based on uniform measures.

In anticancer drug development, the combined use of two drugs is an important strategy to achieve greater therapeutic success. Often combination studies are performed in animal (mostly mice) models before clinical trials are conducted. These experiments on mice are costly, especially with combination studies. However, experimental designs and sample size derivations for the joint action of drugs are not currently available except for a few cases where strong model assumptions are made. For example, Abdelbasit and Plackett proposed an optimal design assuming that the dose-response relationship follows some specified linear models. Tallarida et al. derived a design by fixing the mixture ratio and used a t-test to detect the simple similar action. The issue is that in reality we usually do not have enough information on the joint action of the two compounds before experiment and to understand their joint action is exactly our study goal. In this paper, we first propose a novel non-parametric model that does not impose such strong assumptions on the joint action. We then propose an experimental design for the joint action using uniform measure in this non-parametric model. This design is optimal in the sense that it reduces the variability in modelling synergy while allocating the doses to minimize the number of experimental units and to extract maximum information on the joint action of the compounds. Based on this design, we propose a robust F-test to detect departures from the simple similar action of two compounds and a method to determine sample sizes that are economically feasible. We illustrate the method with a study of the joint action of two new anticancer agents: temozolomide and irinotecan.

Animals↗
PubMed1999

Characteristics of low-angle x-ray scattering from some biological samples.

Design of medical imaging devices based on the detection of low-angle coherent scattering is a subject of increasing interest. The technique is based on the differences in the distribution of photons coherently scattered from different body tissues. Coherent scattering is also useful in monitoring changes that may occur in a healthy tissue (e.g. carcinoma). In this work, low angle scattering properties of some tissues and tissue-equivalent materials are studied. Special care is given to the possibility of distinguishing between tissues of similar water content (e.g. muscle and blood). For this purpose, a Monte Carlo simulation is updated, introducing molecular form factor data, which include molecular interference effects. This program is used to simulate the angular distribution of scattered photons from two tissue-equivalent materials (lucite and water) and three biological samples (muscle, fat and blood). Simulation results agree well with previously measured angular distributions of scattered photons at 59.54 keV. Scattering from water and lucite is also measured at 8.047 keV. The effects of scattering geometry, sample thickness, incident photon energy and tissue type on the angular distribution of scattered photons are investigated. Results reveal the potential of measuring the full width at half maximum (FWHM) of the scattered photon distribution for tissue characterization. Energies up to 13 keV and sample thickness of 0.3 cm reported maximum differences between investigated samples. These conditions are expected to maximize the potential of using coherent scattering set-ups to monitor changes in biological samples even if their water contents are similar. Present results may act as a guide for the optimization of coherent scattering imaging systems.

Adipose Tissue↗
PubMed1999

National Health Interview Survey: research for the 1995-2004 redesign.

OBJECTIVES: This report presents a major portion of the research carried out for the 1995-2004 redesign of the National Health Interview Survey. The primary focus of the 1995-2004 NHIS redesign research was to explore sample design options to improve the reliability of NHIS statistics for racial, ethnic, economic, and geographic domains. Another objective was to assess the integration of the sample designs of the NCHS surveys of health care providers and NHIS. METHODS: A number of research tasks were carried out by Westat, Inc., to explore the feasibility and cost of various sample design options for the 1995-2004 National Health Interview Survey redesign. This report provides a detailed description of the research that was carried out. RESULTS: The research results presented in this report were the primary basis for assessing the technical soundness and costs for a number of design alternatives. The first option, called the alpha option, was developed under the assumption of a 50-percent data collection budget increase. The second option, called the beta option, was developed under the assumption of no change in the data collection budget. The beta option was the design implemented in 1995. Other important research items described in this report include oversampling methods for minority populations and dual-frame sampling methods. The research results in this report also led to additional research, primarily in the area of survey integration. A more detailed description of the 1995-2004 NHIS design will appear in a forthcoming NCHS Series 2 report titled Design and Estimation for the 1995-2004 National Health Interview Survey.

Adolescent↗
PubMedDate not supplied

Survey sampling issues in primary care research.

Survey research methods are often used to answer questions in primary care medicine. Consequently, investigators must understand and address sampling issues. Probability sampling designs have particular utility for questions that seem most appropriate for survey research. These designs provide each member of the population with a known probability of selection, and if performed properly with an appropriate sample size, they provide a sample with essentially no selection bias. Examples of random and stratified sampling designs are presented. These two probability designs, along with nonprobability sampling techniques (convenience, purposive, quota), are discussed in terms of bias, error, and possible limitations.

Humans↗
PubMed1996

A comparison of methods for limited-sampling strategy design using data from a phase I trial of the anthrapyrazole DuP-941.

The pharmacokinetics of a drug in individual patients can be estimated using plasma samples collected at a limited number of time points. However, different methods for a limited-sampling strategy (LSS) design exist and the optimal method has not yet been defined. Plasma concentration data were available from 27 of 74 courses in a phase I study (dose range, 5-55 mg m-2) of the novel anthrapyrazole DuP-941. Three approaches to LSS development were compared. Firstly, forward stepwise regression (FSR) was used to derive equations to predict the DuP-941 area under the concentration-time curve (AUC) based on plasma concentrations measured at specified times. LSSs were developed using 14 randomly chosen data sets and were validated using the remaining 13 data sets. Secondly, "all subsets" regression (ASR) was used to develop LSSs. A jack-knife technique was also used to allow model development utilising 26 data sets and validation on the 27th data set. Thirdly, an LSS was developed using optimal sampling theory (OST), and the LSS was used in conjunction with a Bavesian algorithm. Selected sampling times for four-point LSSs were 10, 65, 185 and 485 min (FSR) and 10, 45, 200 and 480 min (OST). Ten candidate LSSs were developed using the ASR approach. ASR- and OST/Bayesian-derived four-point LSSs gave more precise (P < 0.05) estimates of AUC [mean absolute percentage of difference (MAD%) +/- SD: ASR, 6.4 +/- 3.7%; OST/Bayesian, 6.8 +/- 4.6%] than did FSR (MAD% = 15.1 +/- 9.9%). The OST/Bayesian approach is recommended because it allows estimation of all model parameters and is more flexible with regard to sample collection time and design variables.

Adult↗
PubMed1998

Reliability of single sample experimental designs: comfortable effort level.

This study was designed to ascertain the intrasubject variability across multiple recording sessions-most often disregarded in reporting group mean data or unavailable because of single sample experimental designs. Intrasubject variability was assessed within and across several experimental sessions from measures of speaking fundamental frequency, vocal intensity, and reading rate. Three age groups of men and women--young, middle-aged, and elderly--repeated the vowel /a/, read a standard passage, and spoke extemporaneously during each experimental session. Statistical analyses were performed to assess each speaker's variability from his or her own mean, and that which consistently varied for any one speaking sample type, both within or across days. Results indicated that intrasubject variability was minimal, with approximately 4% of the data exhibiting significant variation across experimental sessions.

Adult↗
PubMed1996

Biosafety implications in sample introduction: module design characteristics for discrete-sample systems used in critical whole blood analyte testing environments.

Systems designed for the measurement of pH/blood gases and expanded versions of these systems that include the ability to measure electrolytes or other related quantities, all incorporate one or more sampling modules that are limited in their ability to allow for the safe handling of potentially biohazardous blood samples. Systems that provide for injection of sample from a syringe use more than the required volume for sample testing and have the potential for causing splash-back of the sample if the introduction port is blocked. The probes of aspiration-based systems require manual dexterity by the operator and present the possibility of operator injury with a contaminated probe tip or the possibility of system damage as the probe extends and the operator moves the collection device into place. Some systems have the potential for both types of biohazards. This report describes the implications for system design of the sample collection devices commonly in use, and it offers a design solution that combines the ergonomics of an injection system and the operational advantages of an aspiration system, in combination, addressing the biosafety aspects in a unique fashion.

Blood Gas Analysis↗
PubMed1997

[Estimation methods in a sampling survey].

The objective of this paper is to present a guide for statistical analysis of a sampling survey. Advantages and disadvantages of classical sampling designs are first discussed. A sampling survey was designed to give more precise estimates of parameters which characterize a targeted well-defined population. Simple sampling design often is impossible in large population and rarely is the optimal solution. According to practical and economic constraints, and to available sampling frames, other strategies (stratification, unequal probabilities, several selection steps) may be necessary or more efficient. Fundamental tools to compute estimators and their confidence intervals are presented. The choice of the sampling method determine for each population unit the probability to include it in the final sample. These inclusion probabilities must be known to formulate estimators, ideally unbiased and with low variance. Difficulties arise from calculating the variance, especially for estimators which are not linear functions of the characteristics of interest. In that case, estimation procedures include Taylor linearization. It is always possible to find at least one linear estimator for a total. The total is the key-parameter in sampling theory, most parameters (such as ratios, means, percentages...), being function of unknown totals. Numerical examples are given.

Confidence Intervals↗
PubMed1987

Evaluation of efficient designs for observational epidemiologic studies.

Recent research in the design of observational epidemiologic studies has been focused on determining which design is most efficient for controlling a potential confounding factor in the analysis of the disease-exposure relationship. Typically, only two candidate designs have been considered, the matched design and the random sample design. These are merely two of an infinite variety of potential designs in which the distributions of the confounder in the comparison groups and the ratio of group sample sizes are arbitrarily chosen. Only in special cases will either of the standard designs be the most efficient or "optimal" design. We construct optimal designs by minimizing the variance of the desired estimate of effect with respect to the controllable design parameters. Construction of an optimal design depends on unknown parameters, so that in practice only an approximately optimal design, perhaps constructed sequentially, is possible. We evaluate the potential usefulness of optimal designs by identifying circumstances in which an optimal design results in large efficiency gains relative to both the matched and random sample designs. We find that there can be substantial efficiency gains in follow-up studies when both the exposure and confounder are strong risk factors. Practical issues in the implementation of these designs are discussed.

Epidemiologic Methods↗
PubMed1997

Duration of general practice consultations: association with patient occupational and educational status.

Past studies have demonstrated that the majority of health care visits are made to general practitioners, and that socio-economically disadvantaged individuals are significantly more likely to use such services. Relatively little is known, however, about the quality of general practice care provided to patients of different socio-economic status. The specific aims of the study were to determine whether an association existed between consultation duration and patient educational and occupational status, and if an association was evident, to determine the extent of association after taking into account a range of identified confounding variables and the effect of a clustered sample design. Consecutive consultations from a randomly selected sample of general practitioners were audiotaped and their durations measured electronically. Patient education and occupational status were obtained by questionnaire. Information concerning a range of additional patient, practitioner and consultation variables was also assessed in order to identify possible confounders of the association between consultation duration and patient occupational and educational status. No association was evident between consultation duration and level of patient educational qualification. Independent of identified confounding variables and the effect of a clustered sample design, general practitioners spent less time with those patients employed in unskilled occupations. Unskilled patients received 2.1 min or 21% less time per consultation than patients in professional occupations. The odds of patients in unskilled occupations receiving a long consultation (> 10 min) were 26% less than the odds of patients in professional occupations. The finding of an occupational status differential in the duration of general practice consultations suggests that socio-economically disadvantaged patients may not be receiving the health care they require. Further research is required to confirm these findings and to identify whether similar differentials are evident in more specific elements of general practice care.

Adult↗
PubMed2003

Design and sample size estimation in clinical trials with clustered survival times as the primary endpoint.

Many clinical trials involve the collection of data on the time to occurrence of the same type of multiple events within sample units, in which ordering of events is arbitrary and times are usually correlated. To design a clinical trial with this type of clustered survival times as the primary endpoint, estimating the number of subjects (sampling units) required for a given power to detect a specified treatment difference is an important issue. In this paper we derive a sample size formula for clustered survival data via Lee, Wei and Amato's marginal model. It can be easily used to plan a clinical trial in which clustered survival times are of primary interest. Simulation studies demonstrate that the formula works very well. We also discuss and compare cluster survival time design and single survival time design (for example, time to the first event) in different scenarios.

Cluster Analysis↗
PubMed1989

Optimal design of sampling schedules for studying glucose kinetics with tracers.

Minimum size sampling schedules for estimating glucose kinetic parameters from an impulsive (bolus) tracer injection in normal humans and rats are presented. Glucose kinetics are described by a two-compartment linear model, and reference values of the parameters are estimated from a data base with many samples. The optimal sampling schedule (OSS) is determined in each individual by using a D-optimal criterion and consists of four samples. A population optimal sampling schedule (POSS) applicable to all the individuals of a given population is then determined, and its reliability and efficiency in recovering kinetic parameters (e.g., rate constants, plasma clearance rate, and mean residence time) is assessed. The influence of model and measurement error on OSS is discussed. Moreover, the adoption of an enhanced POSS (EPOSS, 8 samples) is shown to improve accuracy and precision of parameter estimates in a predictable manner. Finally some suggestions are given for obtaining more information from turnover studies using a constant infusion of tracer, with or without a priming pulse of tracer.

Animals↗
PubMed2001

Statistical analysis of spatial pattern: a comparison of grid and hierarchical sampling approaches.

Previous studies have combined random-site hierarchical sampling designs with analysis of variance techniques, and grid sampling with spatial autocorrelation analysis. We illustrate that analysis techniques and sampling designs are interchangeable using densities of an infaunal bivalve from a study in Poverty Bay, New Zealand. Hierarchical designs allow the estimation of variances associated with each level, but high-level factors are imprecisely estimated, and they are inefficient for describing spatial pattern. Grid designs are efficient for describing spatial pattern, and are amenable to conventional analysis. Our example deals with a continuous spatial habitat, but our conclusions also apply in disjunct or patchy habitats. The influence of errors in positioning is also assessed. The advantages of systematic sampling are reviewed, and more efficient hierarchical approaches are identified. The distinction between biological and statistical significance in all analyses is emphasised.

Animals↗
PubMed1995

Infection risk and potential contamination of urine specimens associated with sample port design of catheter leg bags.

The ease of disinfection of the sample ports of three types of urine drainage leg bags with different sampling port systems was assessed using a bladder bag model. The ports were contaminated with Escherichia coli, 'disinfected' using a standard method, then sampled at time intervals up to one week after contamination. It was discovered that leg bags which employ a needle-based sampling system (the 'sample safe port system') were easier to disinfect than those which did not, and that organisms are retained in large enough numbers to lead to misdiagnosis of a urinary tract infection or to pose a retrograde infection risk.

Catheters, Indwelling↗
PubMed2000

Design and estimation for the National Health Interview Survey, 1995-2004.

OBJECTIVES: This report presents an overview, a detailed description of the sample design features, and estimation structures for the 1995-2004 National Health Interview Survey (NHIS). It is intended to serve the same role for the current (1995-2004) National Health Interview Survey design as the NCHS publication, Series 2, No. 110, Design and Estimation for the National Health Interview Survey, 1985-94, did for the previous design. METHODS: The 1995-2004 NHIS sample design uses cost-effective complex-sampling techniques including stratification, clustering, and differential sampling rates to achieve several objectives. These objectives include improved reliability of racial, ethnic, and geographical domains. This report provides a description of those methods. RESULTS: This report presents the operating characteristics of the 1995-2004 NHIS. The general sampling structure is presented along with a discussion of the weighting and variance estimation techniques. This report is intended for the general users of NHIS data systems. A companion report, Series 2, No. 126, National Health Interview Survey: Research for the 1995-2004 Redesign, provides a finer level of detail on the redesign process.

Data Interpretation, Statistical↗
PubMed2003

Implementation and applications of bootstrap methods for the National Immunization Survey.

In complex probability sample surveys, numerous adjustments are customarily made to the survey weights to reduce potential bias in survey estimates. These adjustments include sampling design (SD) weight adjustments, which account for features of the sampling plan, and non-sampling design (NSD) weight adjustments, which account for non-sampling errors and other effects. Variance estimates prepared from complex survey data customarily account for SD weight adjustments, but rarely account for all NSD weight adjustments. As a result, variance estimates may be biased and standard confidence intervals may not achieve their nominal coverage levels. We describe the implementation of the bootstrap method to account for the SD and NSD weight adjustments for complex survey data. Using data from the National Immunization Survey (NIS), we illustrate the use of the bootstrap (i). for evaluating the use of standard confidence intervals that use Taylor series approximations to variance estimators that do not account for NSD weight adjustments, (ii). for obtaining confidence intervals for ranks estimated from weighted survey data, and (iii). for evaluating the predictive power of logistic regressions using receiver operating characteristic curve analyses that account for the SD and NSD adjustments made to the survey weights.

Analysis of Variance↗
PubMed1995

Design of sampling plans for mycotoxins in foods and feeds.

The control of the occurrence of mycotoxins in foods and feeds requires effective surveillance and quality control procedures which facilitate the identification and control of the mycotoxin problem respectively. Surveillance and quality control procedures involve a sequence of sampling, sample preparation, and analysis steps; and the integrity of the data produced by these procedures will be determined by the effectiveness of these steps. It is imperative that the sampling step is performed as accurately as possible so that the sample collected is representative of the batch of food or feed under investigation. Needless to say, the collection of a biased sample will completely invalidate the resultant analytical data. Most attempts to develop effective sampling protocols have focused upon the aflatoxins, since the majority of current regulations are concerned specifically with this group of mycotoxins. However, the design of effective sampling protocols has been severely hindered by the highly skewed distribution of the aflatoxins in foods and feeds. Studies already performed indicate that representative samples of commodities, composed of large particles (e.g., corn and oilseed kernels) should be 10 kg in weight, at least, and composed of approximately one hundred incremental samples. Similar studies have indicated that samples of oilseed cakes and meal, however, should be composed of fifty incremental samples which afford a composite sample of approximately 5 kg in weight.

Food Analysis↗