Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Sampling Errors”

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
PubMed2004

Significance of subclassifying high-grade squamous intraepithelial lesions into moderate dysplasia/CIN II versus severe dysplasia/CIN III/CIS in the Bethesda System terminology.

Recent revisions of the Bethesda System (TBS III) did not modify the original two-tiered low-grade and high-grade squamous intraepithelial lesion (LSIL/HSIL) terminology and continued to offer the option of subclassifying HSIL into moderate dysplasia/cervical intraepithelial neoplasia (CIN II) and severe dysplasia/CIN III. The purpose of this study is to evaluate the significance of the HSIL moderate dysplasia/CIN II subclassification and the causes of Pap test-biopsy discordance for this subclassification. HSIL/moderate dysplasia/CIN II Pap tests were identified from the University of California Davis Medical Center laboratory file for a 5-yr period (1997-2001) and correlated with follow-up cervical biopsies. Cervical biopsies with CIN II diagnoses were identified from the laboratory file for the same time period, and correlated with their preceding Pap test. Discordant Pap test-biopsy pairs from either group were reviewed by two pathologists for the following causes for discordance: cytologic overcall or undercall, biopsy overcall or undercall, and sampling error or possible lesion regression. During the review period, 161 of 378 total HSIL Pap tests had a HSIL/CIN II result (42%), and 81/161 (50%) had a follow-up cervical biopsy. 38/81 (47%) were concordant, and 43 (53%) were discordant; 39/43 discordant cases had both Pap test and biopsy slides available for review. CIN I was the most common discordant biopsy diagnosis. Sampling error was the most common cause of discordance and was three times more common than the other causes; 536 CIN cervical biopsies with CIN were identified in the laboratory files during this review period, and 108/536 (20%) received a diagnosis of CIN II. Sixty-seven of 108 (62%) had a preceding Pap test result available; 32 of the 67 (48%) had a concordant preceding Pap test with a HSIL/CIN II result, and 35 (52%) were discordant; 32/35 discordant cases had both Pap test and biopsy slides available for review. LSIL was the most common discordant Pap test diagnosis. Sampling error was also the most common cause of discordance, and was also three time more frequent than any other cause for discordance. HSIL/CIN II is a meaningful subclassification in our laboratory. We support the TBS III recommendation for optional subclassification of HSIL and suggest that individual laboratories may wish to monitor use of this subclassification through internal correlation studies.

Female↗
PubMed1993

Short algorithm to compensate for sampling-volume errors in diffusion-cell studies.

This communication describes a short algorithm enabling arbitrarily large but equal samples to be taken from the two chambers of a diaphragm diffusion cell without introducing any systematic error. It creates a transformed time-scale, dependent on sampling volume, which linearizes the output, fits this to a straight line by simple linear regression, and computes the diffusion coefficient from the slope. The advantages of sampling equal fractions from both chambers are discussed in terms of the greater precision this allows. The procedure may have uses in other fields.

Algorithms↗
PubMed2004

Moment estimation of population diversity and genetic distance from data on recessive markers.

A moment-based method for estimating a measure of population diversity, theta or Wright's FST, is given for dominant markers such as amplified fragment length polymorphisms (AFLPs) or RAPDs in noninbred populations. Basic assumptions are that there is random mating, Hardy-Weinberg equilibrium, linkage equilibrium, no mutation from common ancestor and equally distant populations. It is based on the variances between and within populations of genotype frequencies, whereas previously moment methods for dominant markers have been indirect in that they have been based on first estimating allele frequencies and then using the variances of those frequencies. The use of genotype frequencies directly appears to be more robust. Approximate sampling errors of the estimates are given. Methods are extended to estimate genetic distances and their sampling errors. The AFLP data from samples of breeds of pig are used for illustration.

Analysis of Variance↗
PubMedDate not supplied

Analysis of false-negative and underreported smears in the Florence district screening program for cervical carcinoma.

AIMS AND BACKGROUND: To review false-negative or underreported (reactive changes, squamous or glandular atypia) smears performed in women developing histologically proven CIN2 or more severe lesions within 24 months and evaluate error causes. The study setting was the Florence District cervical cancer population-based screening: about 60,000 women age 25-60 years screened per year. METHODS: 118 false-negative or underreported cases were identified at screening files-cancer Registry matching, and the original smears were reviewed by six independent readers to judge smear adequacy and error type. RESULTS: Sampling errors (reported as inadequate, negative or less severe than CIN1 at review) accounted for 74% and screening/interpretation errors (reported as CIN1 or more severe at review) accounted for 26% of studied cases. Screening/interpretation errors were more likely ascribed to misinterpretation and underreporting than to misperception of cellular abnormalities. CONCLUSIONS: Quality control should above all address the problem of sampling adequacy. Due to the rarity of misperceived abnormalities (true screening errors), manual or automated rescreening of negative smears would not be an effective procedure for quality control.

Adult↗
PubMed1990

Flow cytometric DNA ploidy analysis of soft tissue sarcomas. A comparative study of preoperative fine needle aspirates and postoperative fresh tissues and archival material.

Flow cytometric (FCM) DNA ploidy measurements on frozen fresh samples of soft tissue sarcomas were compared with the corresponding analyses on preoperative fine needle aspirates and postoperative formalin-fixed archival tissues from the same tumors. A concordance in ploidy status (diploid versus non-diploid) was obtained for 63% of the fresh tissue-fine needle aspiration (FNA) sample comparisons and for 85% of the fresh tissue-archival material comparisons. The majority of discordances in the fresh tissue-FNA sample comparisons could be explained by FNA sampling errors. In the remaining discordant cases (3 of 27 FNA sample comparisons and 6 of 40 archival material comparisons), sampling errors could not explain the differences in ploidy status. The discordant cases were evenly distributed among the different sampling methods. Method reproducibility was not responsible for the differences in ploidy determinations; tumor heterogeneity may be an explanation for the discrepancies. This study showed that archival soft tissue sarcoma samples are as well suited for DNA ploidy analysis as are fresh frozen tissues.

Archives↗
PubMed2007

Linked surveys of health services utilization.

The linked population/establishment survey (LS) of health services utilization is a two-phase sample survey that links the sample designs of the population sample survey (PS) and the health-care provider establishment sample survey (ES) of health services utilization. In Phase I, household respondents in the PS identify their health-care providers during a specified calendar period. In Phase II, health-care providers identified in Phase I report the variables of interest for all or a sample of their transactions with all households during the same calendar period. The LS has been proposed as a potential design alternative to the PS whenever the health-care transactions of interest are hard to find or enumerate in household surveys and as a potential design alternative to the ES whenever it is infeasible or expensive to construct or maintain complete sampling provider frames that list all health-care providers with good measures of provider size. Suppose that the non-sampling errors are ignorable, how do the LS, PS and ES sampling errors compare? This paper addresses that question by summarizing and extending recent research findings that compare expressions of the sampling variance of (1) the LS and PS of equivalent household sample size and (2) the LS and the ES of equivalent expected health-care provider and transaction sample sizes. The paper identifies the parameters contributing to the precision differences and assesses the conditions that favour the LS or one or the other surveys. Published in 2007 by John Wiley & Sons, Ltd.

Data Interpretation, Statistical↗
PubMed1980

Research design: sampling techniques.

Conditions affecting the decision of whether to take a census or a sample; the major types of sampling procedures, both probability and nonprobability;; and the statistical approaches to sample size determination for simple random samples are discussed. An overview of selected terms and symbols used in sampling literature and a checklist of basic questions to guide a researcher interested in using sampling for a study are provided. While the researcher can control sampling error by increasing the sample size, the concern should be the magnitude of the total error for the study (both sampling and nonsampling errors).

Pharmacy Service, Hospital↗
PubMed2000

Penny-wise and pound-foolish: the impact of measurement error on sample size requirements in clinical trials.

BACKGROUND: Clinical research studies must compensate for measurement error by increasing the number of subjects that are studied, thereby increasing the financial costs of research and exposing greater numbers of subjects to study risks. In this article, we model the relationship between reliability and sample-size requirements and consider the potential tangible cost savings resulting from the decreased number of subjects needed when reliability of raters is improved or multiple ratings are used. METHODS: Standard methods are used to model reliability based on the intraclass correlation coefficient (R) and to perform power calculations. The impact of multiple raters on reliability for a given baseline level of reliability is modeled according to the Spearman Brown formula. RESULTS: Our models demonstrate that meaningful reductions in sample size requirements are gained from improvements in reliability. For example, improving reliability from R = .7 to R = .9 will decreases sample size requirements by 22%. Reliability is improved by training and by the use of the mean of multiple ratings. For example, if the reliability of a single rating is 0.7, the reliability of the mean of two ratings will be 0.8. CONCLUSIONS: The costs to improve reliability either through rater training efforts or use of the mean of multiple ratings is cost effective because of the consequent reduction in number of subjects needed. Efforts to improve reliability and thus reduce subject requirements in a study also may lead to fewer patients bearing the burden of research participation and to a shortening of the duration of studies.

Clinical Trials as Topic↗
PubMed2004

Fine needle aspiration of the thyroid: a cytohistologic correlation and study of discrepant cases.

OBJECTIVE: Fine needle aspiration (FNA) is a reliable method in the initial assessment of thyroid nodules. The purpose of this study was to evaluate the causes for discordance between the interpretation on FNA and the pathologic findings in the resected thyroid. METHODS: A computer search of all thyroidectomy specimens with previous FNA from January 1998 to December 2001 was obtained from the files of the Lauren V. Ackerman laboratory of surgical pathology, Barnes-Jewish Hospital. Excluded from the study were those FNAs performed for suspected and confirmed metastatic disease to the thyroid as well as those cases unavailable for review. A total of 45 FNA cases were identified with cytologic and histologic discrepancies. RESULTS: Of the 1253 individual thyroid FNA performed during the study period, 255 patients (20%) subsequently had an open surgical procedure on the thyroid. Of those who underwent surgery, 196 cases (77%) were concordant, whereas 45 patients (18%) were discordant, and 14 cases were excluded due to unavailability of slides for review (for example, returned consult slides). The causes of the 45 discordant cases were: 20 cases (44%) were unsatisfactory for diagnosis, 14 cases (31%) were due to interpretation error (false positive), and 11 cases (24%) were due to sampling error (false negative). CONCLUSIONS: The most common causes of our discrepant cases are those whose FNA diagnosis was interpreted as "unsatisfactory for diagnosis," in 20 (7.8%) of 255 surgical cases. The false negative rate due to sampling error in 11 (4%) of 255 cases was mainly due to the presence of microscopic papillary thyroid carcinoma (PTC); the false positive rate was due to interpretation error in 14 (6%) of 255 cases, and those were explained by the occurrence of overlapping cytologic features among adenomatous nodules, follicular neoplasms, the follicular variant of PTC, and Hashimoto's thyroiditis.

Biopsy, Fine-Needle↗
PubMed1998

Sample design, sampling weights, imputation, and variance estimation in the 1995 National Survey of Family Growth.

OBJECTIVES: Cycle 5 of the National Survey of Family Growth (NSFG) was conducted by the National Center for Health Statistics (NCHS) in 1995. The NSFG collects data on pregnancy, childbearing, and women's health from a national sample of women 15-44 years of age. This report describes how the sample was designed, shows response rates for various subgroups of women, describes how the sampling weights were computed to make national estimates possible, shows how missing data were imputed for a limited set of key variables, and describes the proper ways to estimate sampling errors from the NSFG. The report includes both nontechnical summaries for readers who need only general information and more technical detail for readers who need an in-depth understanding of these topics. METHODS: The 1995 NSFG was based on a national probability sample of women 15-44 years of age in the United States and was drawn from 14,000 households interviewed in the 1993 National Health Interview Survey (NHIS). Of the 13,795 women eligible for the NSFG, 10,847 (79 percent) gave complete interviews. RESULTS: This report recommends using weighted data for analysis and a software package that will estimate sampling errors from complex samples (for example, SUDAAN or comparable software). The rate of missing data in the 1995 NSFG was very low. However, missing data were imputed for 315 key variables, called "recodes." Of the 315 recodes defined for Cycle 5, 271 variables had missing data on less than 1 percent of the cases; only 44 had 1 percent or more with missing data. These missing values were imputed for all of these 315 variables. The imputation procedures are described in this report.

Adolescent↗
PubMed2001

Type I error in sample size re-estimations based on observed treatment difference.

Sample size re-estimation based on an observed difference can ensure an adequate power and potentially save a large amount of time and resources in clinical trials. One of the concerns for such an approach is that it may inflate the type I error. However, such a possible inflation has not been mathematically quantified. In this paper the mathematical mechanism of this inflation is explored for two-sample normal tests. A (conditional) type I error function based on normal data is derived. This function not only provides the quantification but also gives mathematical mechanisms of possible inflation in the type I error due to the sample size re-estimation. Theoretically, based on their decision rules (certain upper and lower bounds), people can calculate this function and exactly visualize the changes in type I error. Computer simulations are performed to ensure the results. If there are no bounds for the adjustment, the inflation is evident. If proper adjusting rules are used, the inflation can be well controlled. In some cases the type I error can even be reduced. The trade-off is to give up some 'unrealistic power'. We investigated several scenarios in which the mechanisms to change the type I error are different. Our simulations show that similar results may apply to other distributions.

Clinical Trials as Topic↗
PubMed2005

Quantitative analysis of variability and uncertainty with known measurement error: methodology and case study.

The appearance of measurement error in exposure and risk factor data potentially affects any inferences regarding variability and uncertainty because the distribution representing the observed data set deviates from the distribution that represents an error-free data set. A methodology for improving the characterization of variability and uncertainty with known measurement errors in data is demonstrated in this article based on an observed data set, known measurement error, and a measurement-error model. A practical method for constructing an error-free data set is presented and a numerical method based upon bootstrap pairs, incorporating two-dimensional Monte Carlo simulation, is introduced to address uncertainty arising from measurement error in selected statistics. When measurement error is a large source of uncertainty, substantial differences between the distribution representing variability of the observed data set and the distribution representing variability of the error-free data set will occur. Furthermore, the shape and range of the probability bands for uncertainty differ between the observed and error-free data set. Failure to separately characterize contributions from random sampling error and measurement error will lead to bias in the variability and uncertainty estimates. However, a key finding is that total uncertainty in mean can be properly quantified even if measurement and random sampling errors cannot be separated. An empirical case study is used to illustrate the application of the methodology.

Journal Article↗
PubMed2003

Quantifying errors without random sampling.

BACKGROUND: All quantifications of mortality, morbidity, and other health measures involve numerous sources of error. The routine quantification of random sampling error makes it easy to forget that other sources of error can and should be quantified. When a quantification does not involve sampling, error is almost never quantified and results are often reported in ways that dramatically overstate their precision. DISCUSSION: We argue that the precision implicit in typical reporting is problematic and sketch methods for quantifying the various sources of error, building up from simple examples that can be solved analytically to more complex cases. There are straightforward ways to partially quantify the uncertainty surrounding a parameter that is not characterized by random sampling, such as limiting reported significant figures. We present simple methods for doing such quantifications, and for incorporating them into calculations. More complicated methods become necessary when multiple sources of uncertainty must be combined. We demonstrate that Monte Carlo simulation, using available software, can estimate the uncertainty resulting from complicated calculations with many sources of uncertainty. We apply the method to the current estimate of the annual incidence of foodborne illness in the United States. SUMMARY: Quantifying uncertainty from systematic errors is practical. Reporting this uncertainty would more honestly represent study results, help show the probability that estimated values fall within some critical range, and facilitate better targeting of further research.

Bias↗
PubMed2004

Impact of taxon sampling on the estimation of rates of evolution at sites.

The function of individual sites within a protein influences their rate of accepted point mutation. During the computation of phylogenetic likelihoods, rate heterogeneity can be modeled on a site-per-site basis with relative rates drawn from a discretized Gamma-distribution. Site-rate estimates (e.g., the rate of highest posterior probability given the data at a site) can then be used as a measure of evolutionary constraints imposed by function. However, if the sequence availability is limited, the estimation of rates is subject to sampling error. This article presents a simulation study that evaluates the robustness of evolutionary site-rate estimates for both small and phylogenetically unbalanced samples. The sampling error on rate estimates was first evaluated for alignments that included 5-45 sequences, sampled by jackknifing, from a master alignment containing 968 sequences. We observed that the potentially enhanced resolution among site rates due to the inclusion of a larger number of rate categories is negated by the difficulty in correctly estimating intermediate rates. This effect is marked for data sets with less than 30 sequences. Although the computation of likelihood theoretically accounts for phylogenetic distances through branch lengths, the introduction of a single long-branch outlier sequence had a significant negative effect on site-rate estimates. Finally, the presence of a shift in rates of evolution between related lineages can be diagnostic of a gain/loss of function within a protein family. Our analyses indicate that detecting these rate shifts is a harder problem than estimating rates. This is so, partially, because the difference in rates depends on two rate estimates, each with an intrinsic uncertainty. The performances of four methods to detect these site-rate shifts are evaluated and compared. Guidelines are suggested for preparing data sets minimally influenced by error introduced by sequence sampling.

Animals↗
PubMed2005

On the use of beta coefficients in meta-analysis.

This research reports an investigation of the use of standardized regression (beta) coefficients in meta-analyses that use correlation coefficients as the effect-size metric. The investigation consisted of analyzing more than 1,700 corresponding beta coefficients and correlation coefficients harvested from published studies. Results indicate that, under certain conditions, using knowledge of corresponding beta coefficients to input missing correlations (effect sizes) generally produces relatively accurate and precise population effect-size estimates. Potential benefits from applying this knowledge include smaller sampling errors because of increased numbers of effect sizes and smaller non-sampling errors because of the inclusion of a broader array of research designs.

Humans↗
PubMed2000

Chorionic villus sampling before multifetal pregnancy reduction.

OBJECTIVE: This study was undertaken to determine the technical feasibility and accuracy of chorionic villus sampling before multifetal pregnancy reduction and to determine whether sampling increases the pregnancy loss rate after the reduction procedure. STUDY DESIGN: Between January 22, 1986, and January 20, 2000, a total of 1183 patients underwent first-trimester multifetal pregnancy reduction at Mount Sinai Medical Center. Chorionic villus sampling was attempted in 86 patients before the reduction procedure. Information on the technical success and accuracy of chorionic villus sampling, as well as pregnancy outcome, was collected on all patients. Pregnancy loss rates before 24 weeks' gestation in patients undergoing chorionic villus sampling before multifetal pregnancy reduction were compared with rates in patients not undergoing sampling. RESULTS: Chorionic villus sampling was successfully completed in 85 (98.8%) of 86 patients in whom sampling was attempted. Of 166 fetuses, 165 (99.4%) were successfully sampled. Of 165 fetuses, 3 (1.8%) had karyotypic abnormalities. Sampling errors were probably made in 2 (1.2%) of 165 fetuses. Of the 73 patients who have been delivered or are beyond 24 weeks' gestation, only 1 patient (1.4%) had a pregnancy loss after the multifetal pregnancy reduction. CONCLUSIONS: Chorionic villus sampling before multifetal pregnancy reduction is technically feasible and accurate, with an acceptably low sampling error rate. Chorionic villus sampling before multifetal pregnancy reduction appears to be safe and does not increase the risk of loss after the reduction procedure.

Adult↗
PubMedDate not supplied

Cell preparation methods and criteria for sample adequacy. International Academy of Cytology Task Force summary. Diagnostic Cytology Towards the 21st Century: An International Expert Conference and Tutorial.

ISSUES: Cell Preparation Methods Standardized fixation and optimal staining Sampling of cervix, sampling error, homogenization of sample, subsampling Assessment of liquid-based preparations: efficacy and economic impact Training and transitional procedures before full implementation of new technologies Criteria for Sample Adequacy Clinician responsibility for collecting and providing representative sample to laboratory Collection instruments, number of slides Cellular content of samples: evidence of transformation zone (TZ) sampling, number of squamous cells present, obscuring factors Screening issues CONSENSUS POSITION The conventional cervical smear remains the standard method of cervical cancer screening but has limitations in individual test sensitivity and specificity. Sample takers should: (1) receive appropriate training in sample collection, (2) be held responsible for providing the laboratory with appropriate samples, and (3) have their performance monitored. The instruments used for sampling should collect cells from both the ectocervix and endocervix; optimally, TZ sampling, represented by the presence of endocervical or squamous metaplastic cells, should be identifiable in samples other than atrophic specimens. The adequacy of a specimen (as judged microscopically) does not guarantee that it is representative of the cervix. Each cytology report should include a comment on cellular content/adequacy of the specimen. Liquid-based preparations may overcome many of the inherent problems with the conventional cervical smear. ONGOING ISSUES: We need further data on the cost-effectiveness of making two slides from cervical specimens and/or using two samplers rather than a single one. Do we have enough information to make recommendations as to the appropriate type of sampler to be used in particular situations, such as routine screening? What is the best method of screening for/detecting endocervical glandular neoplasia? How are such terms as unsatisfactory and inadequate defined in cervical cytology classifications other than the Bethesda System? What number and types of epithelial cells should be present (visualized) in a cervical smear or liquid-based preparation for it to be considered adequate? Do we need to have evidence of TZ sampling in specimens taken during the follow-up period after treatment of squamous intraepithelial lesion or after detection of endocervical glandular neoplasia? What criteria for obscuring factors, such as blood and inflammation, should be used in assessing adequacy? Cost-benefit analyses of utilizing liquid-based preparations are needed. Should we inform women about the technical details of the test methods available or chosen by the laboratory? Are women in a position to decide which method is the most appropriate to assess their cervical scrape sample? We need to obtain more information about the properties of proprietary liquid fixative/transport media with respect to inactivation of viral pathogens, tuberculosis and other bacterial pathogens and suitability for immunobiologic and molecular tests, etc. We need to obtain more information on the use of stoichiometric stains and the limitations of Papanicolaou stain for image analysis systems. The use of liquid-based preparations for nongynecologic cytopathology and ancillary tests must be considered, including criteria for adequacy. We need to obtain more information on the time required for and best methods of training experienced cytotechnologists to become competent at assessing liquid-based cervical preparations.

Cell Biology↗
PubMed2005

Consumer food safety knowledge, practices, and demographic differences: findings from a meta-analysis.

Risk communication and consumer education to promote safer handling of food can be the best way of managing the risk of foodborne illness at the consumer end of the food chain. Thus, an understanding of the overall status of food handling knowledge and practices is needed. Although traditional qualitative reviews can be used for combining information from several studies on specific food handling behaviors, a structured approach of meta-analysis can be more advantageous in a holistic assessment. We combined findings from 20 studies using meta-analysis methods to estimate percentages of consumers engaging in risky behaviors, such as consumption of raw food, poor hygiene, and cross-contamination, separated by various demographic categories. We estimated standard errors to reflect sampling error and between-study random variation. Then we evaluated the statistical significance of differences in behaviors across demographic categories and across behavioral measures. There were considerable differences in behaviors across demographic categories, possibly because of socioeconomic and cultural differences. For example, compared with women, men reported greater consumption of raw or undercooked foods, poorer hygiene, poorer practices to prevent cross-contamination, and less safe defrosting practices. Mid-age adults consumed more raw food (except milk) than did young adults and seniors. High-income individuals reported greater consumption of raw foods, less knowledge of hygiene, and poorer cross-contamination practices. The highest raw ground beef and egg consumption and the poorest hygiene and cross-contamination practices were found in the U.S. Mountain region. Meta-analysis was useful for identifying important data gaps and demographic groups with risky behaviors, and this information can be used to prioritize further research.

Adolescent↗