Search PubMed⌕ Search
Home/Archive/PubMed

PubMed · 11084228

Proportion estimation with confidence limits.

M F Wilkins·L Boddy·C W Morris
View original source ↗Export metadata ↓

Abstract

A common task in microbiology involves determining the composition of a mixed population of individuals by drawing a sample from the population and using some procedure to identify the individuals in the sample. There may be a significant probability that the identification procedure misidentifies some members of the sample (for example, because the available data are insufficient unambiguously to identify an individual) which makes finding the proportions in the underlying population non-trivial. A further complication arises where individuals are present in the population that do not belong to any of the subpopulations recognised by use of the identification procedure. A simple algorithm is presented to address these problems and construct a maximum likelihood estimate of the proportions, together with confidence limits. The technique is illustrated using an example drawn from flow cytometry in which phytoplankton cells are identified from flow cytometry data by an RBF neural network, and the limitations of the approach are discussed.

Explore related subjects

Confidence IntervalsFlow CytometryNeural Networks, ComputerProbabilityJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

M F Wilkins, L Boddy, C W Morris. 2000-12-01. Proportion estimation with confidence limits.. https://doi.org/10.1016/s0167-7012(00)00204-9

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2001

Prophylaxis of oral mucositis in irradiated head-and-neck cancer patients: a proposed classification scheme of interventions and meta-analysis of randomized controlled trials.

PURPOSE: To identify, classify, and evaluate agents used in the prophylaxis of oral mucositis in irradiated head and neck cancer patients. METHODS: Data sources included multiple databases and manual citation review of relevant literature. Based on the eligibility criteria, 59 studies were independently reviewed by two reviewers. Forty-two studies were included in the classification scheme, of which 15 met the criteria for inclusion in the meta-analysis. Data were extracted by duplicate independent review, with disagreement resolved by consensus. RESULTS: Overall, the interventions reduced the odds of developing severe oral mucositis, when assessed by clinicians, by 36% (OR: 0.64; 95% CI: 0.46, 0.88). Subgroup analysis suggested that only the narrow-spectrum antibacterial lozenges were effective (OR: 0.45; 95% CI: 0.23, 0.86); however, the power of the aggregated data in the other classes may have been insufficient to detect differences. When the outcome was assessed by patients, no significant difference was seen in the outcome between the treatment and the control groups (OR: 0.79; 95% CI: 0.56-1.12). CONCLUSIONS: Overall, interventions chosen on a sound biologic basis to prevent severe oral mucositis are effective. In particular, when oral mucositis is assessed by clinicians, narrow-spectrum antibiotic lozenges appear to be beneficial. Methodologic limitations were evident in many of the studies. Further research using validated measurement tools in larger, methodologically sound trials is warranted.

Confidence Intervals↗
PubMed2001

[Roaming through methodology: XXIX. P].

The abundant use of p-values and statistical significance in medical literature often leads to invalid conclusions about the reported study results. A statistically significant result may be clinically irrelevant, while a clinically relevant effect may be ignored due to lack of statistical significance. These false conclusions can be attributed to the fact that p-values are often considered as a measure of relevance, validity and precision of a study outcome. A p-value, however, only conveys information about precision. In addition, a more informative means to describe the precision of a study exists, viz. confidence intervals. It is therefore important that both the editors of medical journals and the authors of scientific papers continue to use confidence intervals instead of p-values.

Confidence Intervals↗