Microbial Sampling: Is It Better to Sample Many Times or Use Large Samples?

1993 ◽  
Vol 27 (3-4) ◽  
pp. 19-25 ◽  
Author(s):  
Charles N. Haas
Keyword(s):  
Small Volume ◽  
Negative Binomial ◽  
Dispersion Parameter ◽  
Microbial Quality ◽  
Large Samples ◽  
Repeated Sampling ◽  
Repeated Samples ◽  
Microbial Sampling

Repeated sampling of a water (raw, Ssished, recreational) is often used to assess microbial quality. Microbial distributions have often been found to be negative binomial distributed in such repeated samples. Under these conditions, it is shown that it is better to use a large number of small volume samples than vice versa, providing that the negative binomial dispersion parameter remains unaffected by volume. Further research is needed to determine if the latter assumption, which influences the conclusion proposed, is valid for various classes of microorganisms in various types of waters.

scholarly journals Acarological risk of exposure to agents of tick-borne zoonoses in the first recognized Italian focus of Lyme borreliosis

2003 ◽  
Vol 131 (3) ◽  
pp. 1139-1147 ◽  
Author(s):  
A. MANNELLI ◽  
G. BOGGIATTO ◽  
E. GREGO ◽  
M. CINCO ◽  
R. MURGIA ◽  
...  
Keyword(s):  
Negative Binomial ◽  
Seasonal Pattern ◽  
Borrelia Burgdorferi Sensu Lato ◽  
Borrelia Garinii ◽  
Granulocytic Ehrlichiosis ◽  
Host Seeking ◽  
Repeated Sampling ◽  
Risk Of Exposure ◽  
Tick Counts

Acarological risk was calculated as the probability of encountering at least one host-seeking Ixodes ricinus tick infected by the pathogen Borrelia burgdorferi sensu lato, in 100 m transects in the province of Genoa, Italy. The seasonal pattern of I. ricinus was studied using generalized estimating equations (GEE) with negative binomial error, to consider overdispersion of tick counts and repeated sampling of the same dragging sites from April 1998 to March 1999. Prevalence of infection by B. burgdorferi s.l. was evaluated by PCR and hybridization with genospecies-specific probes. Acarological risk (R) peaked in April (R=0·2, 95% CI 0·13–0·26) and November (R=0·29, 95% CI 0·10–0·46). Borrelia garinii and B. valaisiana were the most common genospecies at our study site suggesting a major role of birds as reservoirs. DNA from Anaplasma phagocytophilum, the agent of granulocytic ehrlichiosis in humans and animals, was amplified from an adult I. ricinus.

Onychomycosis Infections

2017 ◽  
Vol 107 (4) ◽  
pp. 280-286 ◽  
Author(s):  
Aditya K. Gupta ◽  
Kerry-Ann Nakrieko
Keyword(s):  
False Negative ◽  
Kappa Statistic ◽  
False Negatives ◽  
Negative Results ◽  
False Negative Results ◽  
Repeated Sampling ◽  
Polymerase Chain ◽  
Serial Samples ◽  
Repeated Samples ◽  
Infecting Organisms

Background: Mycological culture is the traditional method for identifying infecting agents of onychomycosis despite high false-negative results, slower processing, and complications surrounding nondermatophyte mold (NDM) infections. Molecular polymerase chain reaction (PCR) methods are faster and suited for ascertaining NDM infections. Methods: To measure agreement between culture and PCR methods for identification of infecting species of suspected onychomycosis, single toenail samples from 167 patients and repeated serial samples from 43 patients with suspected onychomycosis were processed by culture and PCR for identification of 16 dermatophytes and five NDMs. Agreement between methods was quantified using the kappa statistic (κ). Results: The methods exhibited fair agreement for the identification of all infecting organisms (single samples: κ = 0.32; repeated samples: κ = 0.38). For dermatophytes, agreement was moderate (single samples: κ = 0.44; repeated samples: κ = 0.42). For NDMs, agreement was poor with single samples (κ = 0.16) but fair with repeated samples (κ = 0.25). Excluding false-negative reports from analyses improved agreement between methods in all cases except the identification of NDMs from single samples. Conclusions: Culture was three or four times more likely to report a false-negative result compared with PCR. The increased agreement between methods observed by excluding false-negative reports statistically clarifies and highlights the major discord caused by false-negative cultures. The increased agreement of NDM identification from poor to fair with repeated sampling along with their poor agreement in the single samples, with and without false-negatives, affirms the complications of NDM identification and supports the recommendation that serial samples help confirm the diagnosis of NDM infections.

scholarly journals Investigation of model calibration issues in the safety performance assessment of Ontario highways

2021 ◽  
Author(s):  
S.M. Morjina Ara Begum
Keyword(s):  
Negative Binomial ◽  
Prediction Models ◽  
Temporal Correlation ◽  
Negative Binomial Regression ◽  
Estimating Equation ◽  
Repeated Measurements ◽  
Safety Performance ◽  
Dispersion Parameter ◽  
Segment Length ◽  
Linear Modeling

A set of Safety Performance Function (SPFs) commonly known as accident prediction models, were developed for evaluating the safety of Highway segments under the jurisdiction of Ministry of Transportation, Ontario (MTO). A generalized linear modeling approach was used in which negative binomial regression models were delevoped separately for total accidents and for three severity types (Property Damage Only accidents, Fatal and Injury accidents) as a function of traffic volume AADT. The SPFs were calibrated from 100m homogenous segments as well as for variable length continuous segments that are homogeneous with respect to measured traffic and geometric characteristics. For the models calibrated for Rural 2-Lane Kings Highways, the variables that had significant effects on accident occurrence were the terrain, shoulder width and segment lenght. It was observed that the disperson parameter of the negative binomial districution is large for 100m segments and smaller for longer segments. Further investigation of the dispersion parameter for Rural 2-Lane Kings Highways showed that the models calibrated with a separate dispersion parameter for each site depending on the segment length performed better that the model calibrated considering fixed dispersion parameter for all sites. For Rural 2-Lane Kings Highways, a model was calibrated with trend considering each year as a separate observation. The GEE (Generalized Estimating Equation) procedure was use to develop these models since it incorporated the temporal correlation that exists in repeated measurements. Results showed that integration of time trend and temporal correlation in the model improves the model fit.

On Difference Equations, Probability Models and the “Generalized Event Count” Distribution

1996 ◽  
Vol 6 ◽  
pp. 175-212 ◽  
Author(s):  
Timothy W. Amato
Keyword(s):  
Difference Equations ◽  
Count Data ◽  
Negative Binomial ◽  
Probability Model ◽  
Dispersion Parameter ◽  
Probability Models ◽  
Statistical Structure ◽  
Count Models ◽  
Count Distribution ◽  
The Common

In this article, the mathematical and probabilistic foundations of Gary King's “generalized event count” (GEC) model for dealing with unequally dispersed event count data are explored. It is shown that the GEC model is a probability model that joins together the binomial, negative binomial, and Poisson distributions. Some aspects of the GEC's reparameterization are described and extended and it is shown how different reparameterizations lead to different interpretations of the dispersion parameter. The common mathematical and statistical structure of “unequally dispersed” event count models as models that require estimation of the “number of trials” parameter along with the “probability” component is derived. Some questions pertaining to estimation of this class of models are raised for future discussion.

Adjustment for Maximum Likelihood Estimate of Negative Binomial Dispersion Parameter

2008 ◽  
Vol 2061 (1) ◽  
pp. 9-19 ◽  
Author(s):  
Byung-Jung Park ◽  
Dominique Lord
Keyword(s):  
Maximum Likelihood ◽  
Sample Size ◽  
Maximum Likelihood Estimate ◽  
Negative Binomial ◽  
Highway Safety ◽  
Likelihood Estimate ◽  
Dispersion Parameter ◽  
Dispersion Parameters ◽  
Sample Mean ◽  
Crash Data

The negative binomial (NB) (or Poisson–gamma) model has been used extensively by highway safety analysts because it can accommodate the overdispersion often exhibited in crash data. However, it has been reported in the literature that the maximum likelihood estimate of the dispersion parameter of NB models can be significantly affected when the data are characterized by small sample size and low sample mean. Given the important roles of the dispersion parameter in various types of highway safety analyses, there is a need to determine whether the bias could be potentially corrected or minimized. The objectives of this study are to explore whether a systematic relationship exists between the estimated and true dispersion parameters, determine the bias as a function of the sample size and sample mean, and develop a procedure for correcting the bias caused by these two conditions. For this purpose, simulated data were used to derive the relationship under the various combinations of sample mean, dispersion parameter, and sample size, which encompass all simulation conditions performed in previous research. The dispersion parameter was estimated by using the maximum likelihood method. The results confirmed previous studies and developed a reasonable relationship between the estimated and true dispersion parameters for reducing the bias. Details for the application of the correction procedure were also provided by using the crash data collected at 458 three-leg unsignalized intersections in California. Finally, the study provided several discussion points for further work.

Effects of Varying Dispersion Parameter of Poisson–Gamma Models on Estimation of Confidence Intervals of Crash Prediction Models

2008 ◽  
Vol 2061 (1) ◽  
pp. 46-54 ◽  
Author(s):  
Srinivas Reddy Geedipally ◽  
Dominique Lord
Keyword(s):  
Confidence Intervals ◽  
Negative Binomial ◽  
Prediction Models ◽  
Motor Vehicle ◽  
Dispersion Parameter ◽  
Transportation Safety ◽  
Dispersion Parameters ◽  
Crash Data ◽  
Varying Dispersion ◽  
Using Data

In estimating safety performance, the most common probabilistic structures of the popular statistical models used by transportation safety analysts for modeling motor vehicle crashes are the traditional Poisson and Poisson–gamma (or negative binomial) distributions. Because crash data often exhibit overdispersion, Poisson–gamma models are usually the preferred model. The dispersion parameter of Poisson–gamma models had been assumed to be fixed, but recent research in highway safety has shown that the parameter can potentially be dependent on the covari-ates, especially for flow-only models. Given that the dispersion parameter is a key variable for computing confidence intervals, there is reason to believe that a varying dispersion parameter could affect the computation of confidence intervals compared with confidence intervals produced from Poisson–gamma models with a fixed dispersion parameter. This study evaluates whether the varying dispersion parameter affects the computation of the confidence intervals for the gamma mean (m) and predicted response (y) on sites that have not been used for estimating the predictive model. To accomplish that objective, predictive models with fixed and varying dispersion parameters were estimated by using data collected in California at 537 three-leg rural unsignalized intersections. The study shows that models developed with a varying dispersion parameter greatly influence the confidence intervals of the gamma mean and predictive response. More specifically, models with a varying dispersion parameter usually produce smaller confidence intervals, and hence more precise estimates, than models with a fixed dispersion parameter, both for the gamma mean and for the predicted response. Therefore, it is recommended to develop models with a varying dispersion whenever possible, especially if they are used for screening purposes.

Sign in / Sign up

Export Citation Format

Share Document