Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Poisson Distribution”

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 343 records · Page 19Linked to original sources
PubMed2006

A cross-national study of transitions in deficit counts in two birth cohorts: implications for modeling ageing.

Generally, health does not improve with age, and many physical and physiological functions are known to decline. These changes do not occur uniformly, however; for many reasons, some people experience significant improvement in their health over non-trivial time intervals. Earlier, we showed that 5-year transitions in health status in elderly people (age 65+ years) can be modeled as a stochastic process, using a modified Poisson distribution with four readily interpretable parameters. The original description was based on follow-up of a single cross-sectional study, thus mixing age and cohort effects. Here, we again used a multistate Markov chain to model 5-year deficit accumulation in relation to frailty in both a Swedish birth cohort (aged 70 years at inception) and, from the original cross-sectional study, a Canadian birth cohort, aged 69-71. In both datasets, we found again that a modified Poisson describes the transition in health status with high precision. The parameters of the model though different, are close to each other, even though the cohorts are from different countries, were assembled 20 years apart, and counted different deficits. The model suggests that all health transitions, including health improvement, worsening, and death, can be summarized in a unified stochastic model with a few interpretable parameters.

Aged↗
PubMedDate not supplied

Prevalence of tetraploid metaphases in semidirect and cultured chorionic villi.

OBJECTIVE: Investigation of the normal frequency of tetraploid metaphases in semidirect (STC) and cultured (LTC) chorionic villi. METHODS: Fifty metaphases in STC- and in LTC-villi slides of 100 women of advanced maternal age were screened for tetraploidy. RESULTS: Up to three tetraploid metaphases were encountered in 27% of the STC-villi preparations; the scores fitted a Poisson distribution. In all LTC-villi preparations tetraploid cells were seen; the scores fitted a log-Gaussian distribution. CONCLUSIONS: On the basis of these distributions, we propose a protocol for the management of tetraploid metaphases in chorionic villi, strongly reducing the number of prenatal follow-up investigations.

Cells, Cultured↗
PubMed1994

Sample size requirements for evaluating heart valves with constant risk events.

A method is described for computing sample size requirements for a clinical study of a new heart valve, according to the guidance document recently revised by the FDA. The FDA requirements specify a one-sample hypothesis test in which the complication rates for the study valve are compared to fixed values determined from previous experience with approved devices. These values, which can differ for different complications and for mechanical or tissue valve types, are called OPC's (Objective Performance Criteria). The method described, using the Poisson distribution, provides a simple formula for computing the valve-years required corresponding to any OPC. At the OPC level required by the FDA guidelines (1.2%/year), the minimum follow-up necessary is about 800 valve-years.

Guidelines as Topic↗
PubMed2005

Duality of fatigue failures of materials caused by Poisson defect statistics of competing failure modes.

The statistical nature of failures of components subjected to fatigue loading is a major challenge in engineering applications. Here, we report an interesting fatigue phenomenon in which there is a 'duality' of the S-N fatigue data (S is stress and N is cycles to failure)--the grouping of data into two distinct S-N curves as a result of two competing failure modes. The proportions of failure by either mode are about the same and one cannot predict which failure mode will eventually dominate. This means that fatigue lives may be unpredictable in materials under certain application conditions and the consequences can be disastrous. Based on Poisson defect statistics and Monte Carlo simulations, we show that this phenomenon can arise from the Poisson distribution of low populations of microscale defects. An unexpected finding is that there should be a combination of average defect density and specimen area at which this phenomenon is observable in materials having sparsely populated defects.

Algorithms↗
PubMed1995

The mathematical relationship between the number of events in which people are injured and the number of people injured.

In this paper the mathematical relationship between the number of times people sustained injuries and the number of people injured is discussed. The number of injury-causing events in a population will be larger than the number of people injured as people can be injured on more than one occasion. The Poisson distribution is used as a way to study the relationship between the two different sets of numbers. A practical example is given of injuries sustained while running. From this it seems that injury proneness needs to be considered in studying those who were injured on more than one occasion while running during the past year.

Accidents↗
PubMed1998

[Analysis of variance of bacterial counts in milk. 1. Characterization of total variance and the components of variance random sampling error, methodologic error and variation between parallel errors during storage].

In contrast to the prevailing automatized chemical analytical methods, classical microbiological techniques are linked with considerable material- and human-dependent sources of errors. These effects must be objectively considered for assessing the reliability and representativeness of a test result. As an example for error analysis, the deviation of bacterial counts and the influence of the time of testing, bacterial species involved (total bacterial count, coliform count) and the detection method used (pour-/spread-plate) were determined in a repeated testing of parallel samples of pasteurized (stored for 8 days at 10 degrees C) and raw (stored for 3 days at 6 degrees C) milk. Separate characterization of deviation components, namely, unavoidable random sampling error as well as methodical error and variation between parallel samples, was made possible by means of a test design where variance analysis was applied. Based on the results of the study, the following conclusions can be drawn: 1. Immediately after filling, the total count deviation in milk mainly followed the POISSON-distribution model and allowed a reliable hygiene evaluation of lots even with few samples. Subsequently, regardless of the examination procedure used, the setting up of parallel dilution series can be disregarded. 2. With increasing storage period, bacterial multiplication especially of psychrotrophs leads to unpredictable changes in the bacterial profile and density. With the increase in errors between samples, it is common to find packages which have acceptable microbiological quality but are already spoiled by the time of the expiry date labeled. As a consequence, a uniform acceptance or rejection of the batch is seldom possible. 3. Because the contamination level of coliforms in certified raw milk mostly lies near the detection limit, coliform counts with high relative deviation are expected to be found in milk directly after filling. Since no bacterial multiplication takes place during storage, then error between samples always predominates the total variation. 4. The present results cannot be simply applied to other selective enumerations of microorganisms. Yet, a non-homogenous distribution should always be expected at microbial counts close to the detection limit. Technical errors arising from clustering as well as eugonic growth can additionally hamper the counting of colonies of such microorganisms. Effects of these observations in the decision-making process will be dealt with in the second communication.

Analysis of Variance↗
PubMed1992

Repeatability and reproducibility of egg counts of Schistosoma haematobium in urine.

Egg output in urinary schistosomiasis can be influenced by several factors, such as time of collection of urine, day to day variations, seasonal variations and environmental conditions. Additionally there are unavoidable random errors inherent in every test procedure. To assess the precision of Schistosoma haematobium egg counts, carried out after paper filtration, two measures are determined, namely repeatability (r) and reproducibility (R). 10 aliquots of 10 urine samples are examined by 5 microscopists and values for r and R are calculated following the methods of the British Standards Institution (BSI, 1987). Results show unexpectedly high values for the 2 measures in relation to the overall means in all 10 urine samples, and analyses of variance confirm that there are large variations between aliquots of equal volume drawn from the same urine specimen, highly significant in all 10 urine specimens; variations between microscopists are considerably lower and only highly significant in one urine specimen. The Poisson heterogeneity test for all urine samples refutes in 9 out of 10 cases the hypothesis that aliquots of equal volume taken from a well mixed urine sample could reasonably be drawn from a Poisson distribution. It is therefore concluded that egg counts are very valuable for community studies and should always be performed, but results must be interpreted with more caution than before and great care taken in analyzing counts (especially in longitudinal studies), in classifying them and in relating them to morbidity.(ABSTRACT TRUNCATED AT 250 WORDS)

Animals↗
PubMed1999

On the theory of partially inbreeding finite populations. VI. The survival probability of a two-locus allele combination when there is partial selfing.

Consider a large population with two loci that may be linked, with one having alleles A and a and the second alleles B and b. Let there be initially one individual with genotype AB/ab in a population otherwise consisting of ab/ab individuals. We assume that AB/ab, Ab/aB, AB/aB, AB/Ab and AB/AB individuals have higher probabilities of survival to adulthood than individuals with genotype ab/ab. The probability that AB ultimately survives, if there is a positive probability of selfing, is calculated. To simplify calculations, it is assumed that the number of offspring produced by any individual follows a Poisson distribution and that genotypes of separate offspring are independent. If recombination is possible, we conclude that a population with a high probability of selfing is more likely to accumulate epistatically favorable genes than one reproducing largely by random mating. This advantage of selfing becomes more pronounced as the strength of selection in favor of AB increases.

Alleles↗
PubMed1999

Point source sulphur dioxide peaks and hospital presentations for asthma.

OBJECTIVE: To examine the effect on hospital presentations for asthma of brief exposures to sulphur dioxide (SO2) (within the range 0-8700 micrograms/m3) emanating from two point sources in a remote rural city of 25,000 people. METHODS: A time series analysis of SO2 concentrations and hospital presentations for asthma was undertaken at Mount Isa where SO2 is released into the atmosphere by a copper smelter and a lead smelter. The study examined 5 minute block mean SO2 concentrations and daily hospital presentations for asthma, wheeze, or shortness of breath. Generalised linear models and generalised additive models based on a Poisson distribution were applied. RESULTS: There was no evidence of any positive relation between peak SO2 concentrations and hospital presentations or admissions for asthma, wheeze, or shortness of breath. CONCLUSION: Brief exposures to high concentrations of SO2 emanating from point sources at Mount Isa do not cause sufficiently serious symptoms in asthmatic people to require presentation to hospital.

Air Pollutants↗
PubMed2003

A longitudinal study of a natural lice infestation in growing cattle over two winter periods.

A group of 61 cattle which were naturally infested with lice was followed over two winter periods. Data were collected on the number of lice found at various body sites over this period. Summary statistics were produced and due to the repeated measured and hierarchical structure of the data, multi-level analysis was used to model the population dynamics of Bovicola bovis and assess the influence of the various hierarchical levels. A four level Poisson model was produced--level one, the individual number of lice at each parting; level two, the body site examined (shoulder, midline or rump); level three, the time of the inspection and level four, the animal. Seasonal fluctuation in lice numbers was modelled using a cosine function transformation of time. A seasonal pattern was seen in both year's with lice counts higher in the first than the second year. The midline area was the most sensitive to detection of B. bovis. Variance contributed by the individual animal was less than that contributed by the body site examined and the time of the inspection. The model suggested that lice numbers within the shoulder and rump sites were near random following a Poisson distribution, but aggregation of lice occurred at the midline site with the distribution between animals following a Negative Binomial Pattern. The midline site was the most sensitive site for detecting B. bovis. Infestation numbers were higher in the first winter when cattle were younger. In the second winter, there was no difference in lice numbers between cattle exposed to infection for the first or second time.

Animals↗
PubMed1996

Distinct developmental patterns of short-term and long-term functioning lymphoid and myeloid precursors defined by competitive limiting dilution analysis in vivo.

Functional abilities of individual marrow precursor cells were defined by competitive limiting dilution without enrichment, tissue culture, or induced marking, manipulations that might affect cell functions. We directly measured long-term repopulating abilities in limiting doses (0.25-1.0 x 10(5)) of genetically marked congenic marrow cells. These were mixed with a standard dose of 4 or 5 x 10(5) competitor marrow cells, which contained a predictable distribution of precursor cells and allowed quantitative assays. Percentages of donor type T and B lymphocytes, granulocytes, platelets, and erythrocytes were measured in recipient blood. Applying the maximum likelihood statistic, concentrations (per 10(5)) of precursors repopulating at least one lineage were: 4.7 and 6.0 after 6 wk, 1.6 and 2.7 after 14 to 15 wk, and 1.2 and 1.9 after 30 to 32 wk; concentrations repopulating at least three lineages were 2.3 and 3.4 after 6 wk, 0.9 and 1.7 after 14 to 15 wk, and 0.9 and 1.3 after 32 wk. Almost all precursors functioning after 14 wk repopulated all lineages. At 6 wk, similar levels of donor cells were produced in recipients of both short- and long-term precursors. However, after 14 to 32 wk, contributions by short-term precursors (about two-thirds of the precursors) dropped to zero, while contributions by long-term precursors (about one-quarter of the precursors) expanded severalfold. The latter permanently repopulated all lineages after 30 to 32 wk, functioning as the most primitive stem cells (PSC) in the immune and myeloid systems. Nearly all the variance in long-term repopulated recipients was explained using the Poisson distribution to calculate donor percentages in a model where each donor and competitor PSC contributed equally.

Animals↗
PubMed1990

Murphy's law of limiting dilution cloning.

Conventional practice and literature on limiting dilution cloning address the irrelevant problem of selection of a single progenitor from a uniform population, and provide optimistic estimates of monoclonality for interesting cultures and subcultures. Any cell line established via these estimates is suspect and may be polyclonally metastable. Cultures derived by limiting dilution of the progenitors of independently Poisson distributed populations obey a counterintuitive relation with the characteristics of a Murphy's law: the probability that an interesting culture is monotypic or monoclonal is less than that of a random non-sterile culture, decreases for increasingly rare interesting cultures, and is bounded below by the probability of sterility. A priori and empiric a posteriori estimates of the probability that interesting subcultures are monotypic or monoclonal are derived consistent with this principle.

Cells, Cultured↗
PubMed1998

[Study on the power of O/E method].

This paper addresses the methodology of calculating the power of O/E method and introduces the relevant algorithm for estimating the sample size. Based on the principles of hyporthesis testing and Poisson distribution, the power can be worked out for given sample size, baseline rate(pi 0) and the factor of increasing (gamma). The power increases with the increase in sample size, pi 0 and gamma. In shape the power is not a continuous smooth line but a zigzag line. The method illustrated in this paper can be also used for estimaging the sample size of studies on the intervention of diseases.

Congenital Abnormalities↗
PubMed2006

Solving the chemical master equation for monomolecular reaction systems analytically.

The stochastic dynamics of a well-stirred mixture of molecular species interacting through different biochemical reactions can be accurately modelled by the chemical master equation (CME). Research in the biology and scientific computing community has concentrated mostly on the development of numerical techniques to approximate the solution of the CME via many realizations of the associated Markov jump process. The domain of exact and/or efficient methods for directly solving the CME is still widely open, which is due to its large dimension that grows exponentially with the number of molecular species involved. In this article, we present an exact solution formula of the CME for arbitrary initial conditions in the case where the underlying system is governed by monomolecular reactions. The solution can be expressed in terms of the convolution of multinomial and product Poisson distributions with time-dependent parameters evolving according to the traditional reaction-rate equations. This very structured representation allows to deduce easily many properties of the solution. The model class includes many interesting examples. For more complex reaction systems, our results can be seen as a first step towards the construction of new numerical integrators, because solutions to the monomolecular case provide promising ansatz functions for Galerkin-type methods.

Kinetics↗
PubMed1996

Can you count on the mitotic index?

The mitotic index (MI) is the most commonly use quantitative measure in anatomic pathology but has been widely criticized for supposed "irreproducibility." In this article, the authors show that mitotic figure (MF) counts may be described by a Poisson distribution, give confidence intervals for the MI, and show that the supposed irreproducibility is largely a consequence of the counting techniques. They also show how to obtain the MI to a predetermined level of precision and present an analysis of why mitotic figure counting works, when properly used, despite the inherently low precision of the estimates that are usually obtained.

Breast Neoplasms↗
PubMed2006

A modeling approach to the analysis of nerve regenerative experiments.

Many experiments aiming at the investigation of nerve repair involve elaborate testing over a certain time period. Data arising from such experiments are often analyzed by time-point. Such a cross-sectional approach is often very inefficient. In this paper, we consider a case study in which repeated measurements of two response variables assumed to be Poisson distributed are obtained. We show how a repeated measures modeling approach, based on generalized linear models, can handle both responses in one model and improve the inference in the nerve repair experiments. The benefits of the model as well as problems that can occur are illustrated and discussed.

Algorithms↗
PubMed1999

The oncogenic transforming potential of the passage of single alpha particles through mammalian cell nuclei.

Domestic, low-level exposure to radon gas is considered a major environmental lung-cancer hazard involving DNA damage to bronchial cells by alpha particles from radon progeny. At domestic exposure levels, the relevant bronchial cells are very rarely traversed by more than one alpha particle, whereas at higher radon levels-at which epidemiological studies in uranium miners allow lung-cancer risks to be quantified with reasonable precision-these bronchial cells are frequently exposed to multiple alpha-particle traversals. Measuring the oncogenic transforming effects of exactly one alpha particle without the confounding effects of multiple traversals has hitherto been unfeasible, resulting in uncertainty in extrapolations of risk from high to domestic radon levels. A technique to assess the effects of single alpha particles uses a charged-particle microbeam, which irradiates individual cells or cell nuclei with predefined exact numbers of particles. Although previously too slow to assess the relevant small oncogenic risks, recent improvements in throughput now permit microbeam irradiation of large cell numbers, allowing the first oncogenic risk measurements for the traversal of exactly one alpha particle through a cell nucleus. Given positive controls to ensure that the dosimetry and biological controls were comparable, the measured oncogenicity from exactly one alpha particle was significantly lower than for a Poisson-distributed mean of one alpha particle, implying that cells traversed by multiple alpha particles contribute most of the risk. If this result applies generally, extrapolation from high-level radon risks (involving cellular traversal by multiple alpha particles) may overestimate low-level (involving only single alpha particles) radon risks.

Alpha Particles↗
PubMed2004

Bias estimation in method comparison studies.

A test and a reference analytical method are usually compared for agreement based on paired data obtained from several independent subjects. Bias between two methods can be classified as constant and proportional. In this article, we provide an approach for maximum likelihood estimation of total bias between two methods and partitioning it into constant and proportional bias for each subject. Normal, binomial, or Poisson distribution are the conditional distributions of the response variable that we have considered here, whereas subjects are considered to be random sample from a normally distributed population. Real data on blood cell counts and hemoglobin are used for demonstration. The estimate of biases can be used to test different statistical hypotheses and/or for graphical interpretation of the agreement. The partitioning of total biases in terms of constant and proportional gives an insight on the sources of disagreement between two methods and helps designers and manufacturer's define a remedial strategy.

Algorithms↗