Poisson Estimator Research Articles

The safety of sea transport: determinants of crew injuries

This study investigates determinants of fatal and nonfatal crew injuries in ship accidents, utilizing detailed data of individual tanker, container and bulk ship (US and foreign) accidents investigated by the US Coast Guard. Poisson and negative binomial regression estimates suggest that fatal and nonfatal injuries are greater: (1) if the accident cause is human rather than environmental or ship related and (2) for fire/explosion and multiple-ship accidents. The results provide strong evidence of a positive relationship between crew injuries and human causes of ship accidents, thereby providing support for the current shift in safety focus towards regulating human actions aboard ships rather than just the condition of ships.

Spatial pattern of the Rio Cuarto corn disease vector, Delphacodes kuscheli Fennah (Hom., Delphacidae), in oat fields in Argentina and design of sampling plans

The spatial pattern of the Rio Cuarto Corn Disease vector, Delphacodes kuscheli (Hom., Delphacidae), was analysed in oat fields within the endemic area of the disease, during the growing seasons 1993 and 1994. The spatial pattern was analysed by fitting the probabilistic models Poisson and negative binomial and estimation of single-date and overall aggregation indices. The population of the different stage classes, sex, and wing forms showed a significant trend to aggregation as the negative binomial model fitted the observed frequency distributions in more than 78% of the cases (sampling dates) while the Poisson model fitted well in only 28% of cases or less. Single-date aggregation index, C A , ranged from 0.3 to 0.84. Overall (whole season) aggregation index, C A * , estimated through the Bliss and Owen's regression method, ranged from 0.18 (female adults) to 1.08 (nymphs I-II), indicating a moderate degree of aggregation compared with other planthopper species. There were no significant relationships between aggregation and population density. The minimum number of sampling units and critical lines for sequential sampling plans were calculated based on the estimation of C A * for the precision levels (D) 0.1, 0.2 and 0.3. Even low degrees of aggregation, like that of adults, demand much more sampling effort than randomly distributed populations, particularly at high densities. General implications and limitations of the proposed sampling plans for monitoring the vector population abundance are discussed.

Analysis of a Monte Carlo boundary propagation method

A modified Monte Carlo technique, first developed in estimating a solution to Poisson's equation, is described and estimates of its computational complexities are derived. The method yields better estimates than the standard Monte Carlo approach by incorporating boundary information more efficiently and by the implicit reuse of random walk information gathered throughout the course of the computation. The new approach reduces the computational complexity of the length of a random walk by one order of magnitude as compared to a standard method described in many text books. Also, the number of walks necessary to achieve a desired accuracy is reduced.

Statistics of Microlensing Optical Depth

We show that the statistical error, $\sigma_{\tau}$, in estimating the optical depth, $\tau$, due to microlensing is substantially higher than the naive Poisson estimate: $\sigma_{\tau} = \sqrt{\eta / N} \tau$, where $N$ is the number of detections and $1.65 \leq \eta \lsim 3$. We construct a ``microlensing map'' using an observationally well-constrained barred bulge model and compare this with a map based on a spherical bulge model. The result indicates a significant differences in the distribution of optical depths. If the optical depths are determined over a wide range of positions around the Galactic center, one could make a rudimentary determination of the geometry of the mass distribution of the Galactic bulge by observing $\sim 200$ events. About 800 events are required to determine the relative contributions to the event rate by bulge and disk Machos.

Improving Poisson Approximations

LetX1,…,Xn, be indicator random variables, and setWe present a method for estimating the distribution ofWin settings whereWhas an approximately Poisson distribution. Our method is shown to yield estimates significantly better than straight Poisson estimates when applied to Bernoulli convolutions, urn models, the circularkofn:Fsystem, and a matching problem. Error bounds are given.

THE REGIONAL DIMENSION OF TAKEOVER ACTIVITY IN THE UNITED KINGDOM

This paper seeks to identify and account for the regional incidence of external takeover in the United Kingdom during the years 1969, 1977, and 1985. The factors expected to influence interregional takeover flows are identified and a model specification based on the gravity principle is suggested. Results derived from Poisson estimation indicate that the share of U.K. firms headquartered in origin and destination regions, distance deterrence, the size of companies in origin regions and the dominating effect of South east England play a key role in the process. Copyright 1994 by Scottish Economic Society.

Estimating a System of Recreation Demand Functions Using a Seemingly Unrelated Poisson Regression Approach

In this article, a seemingly unrelated Poisson regression model is presented as an alternative to using Zellner's seemingly unrelated regression model for estimating a system of recreation demand functions. The seemingly unrelated Poisson regression model provides estimates that are asymptotically more efficient than equation-by-equation Poisson estimates and circumvents the bias and inconsistency problems that result when using A. Zellner's seemingly unrelated regression model. Additionally, the seemingly unrelated Poisson regression model is applied to an empirical problem dealing with the value of recreational boating and the findings indicate that the seemingly unrelated regression model consumer surplus estimates are substantially different from those of the seemingly unrelated Poisson regression model. Copyright 1994 by MIT Press.

Bias and variance of angular correlation functions

view Abstract Citations (1537) References (17) Co-Reads Similar Papers Volume Content Graphics Metrics Export Citation NASA/ADS Bias and Variance of Angular Correlation Functions Landy, Stephen D. ; Szalay, Alexander S. Abstract We present a general method for calculating the bias and variance of estimators for w(θ) based on galaxy-galaxy (DD), random-random (RR), and galaxy-random (DR) pair counts and describe a procedure for quickly estimating these quantities given an arbitrary two-point correlation function and sampling geometry. These results, based conditionally upon the number counts, are accurate for both high and low number counts. We show explicit analytical results for the variances in the estimators DD/RR, DD/DR, which turn out to be considerably larger than the common wisdom Poisson estimate and report a small bias in DD/DR in addition to that due to the integral constraint. Further, we introduce and recommend an improved estimator (DD - 2DR + RR)/RR, whose variance is nearly Poisson. Publication: The Astrophysical Journal Pub Date: July 1993 DOI: 10.1086/172900 Bibcode: 1993ApJ...412...64L Keywords: Angular Correlation; Bias; Computational Astrophysics; Galactic Clusters; Variance; Correlation Coefficients; Monte Carlo Method; Random Variables; Astrophysics; GALAXIES: CLUSTERING; METHODS: NUMERICAL full text sources ADS |

Sampling to Detect Rare Species

Often a sampling program has the objective of detecting the presence of one or more species. One night wish to obtain a species list for the habitat, or to detect the presence of a rare and possibly endangered species. How can the sampling effort necessary for the detection of a rare species can be determined? The Poisson and the negative binomial are two possible spatial distributions that could be assumed. The Poisson assumption leads to the simple relationship n = -(1/m)log @b, where n is the number of quadrats needed to detect the presence of a species having density m, with a chance @b (the Type 2 error probability) that the species will not be collected in any of the n quadrats. Even if the animals are not randomly distributed the Poisson distribution will be adequate if the mean density is very low (i.e., the species is rare, which we arbitrarily define as a true mean density of <0.1 individuals per sample unit), and the spatial distribution is not highly aggregated. Otherwise a more complicated relationship based on the negative binomial distribution would have to be used. Published sampling distributions of 37 unionid mollusc species over river miles (distance measured along the path of the river; 1 mile = 1.609347 km) in two southern Appalachian rivers were evaluated to determine the appropriateness of the simple Poisson-based formula for estimation of necessary sample size to detect species presence. For each of 273 species x river mile combinations we estimated the mean, the variance, and the negative binomial parameter k, and then estimated "necessary n" from both the Poisson- and the negative-binomial-based formulae. We defined "Poisson adequacy" to be the proportion that the Poisson estimate is of the negative binomial estimate of necessary sample size, and stated the requirement that it be >0.95. Only 8 of the 273 cases represented rare species that failed this requirement. Thus we conclude that a Poisson-based estimate of necessary sample size will generally be adequate and appropriate.

Long-range earthquake forecasting based on a single predictor with clustering

SUMMARY The methodology for formulating and testing a predictive hypothesis of earthquake occurrence based on a single predictor (Rhoades & Evison 1979) has been extended to allow for a cluster of similar precursors being related to a subsequent cluster of mainshock events. The hazard is conveniently represented by conditional intensity, from which probability is readily derived, and which can be updated as new information becomes available. This method has been applied to the generalized swarm hypothesis, tests of which are in progress in New Zealand and Japan. Probability distributions for the mainshock origins are estimated from magnitude-weighted locations and origin times of all the swarm earthquakes in a cluster, and from the three largest magnitudes. Hazard refinement relative to the Poisson estimate is obtained by combining the contributions for principal and secondary mainshocks. As time passes, the hazard is adjusted for further swarm occurrences, and subsequently for the occurrence or non-occurrence of mainshock events. The application of these methods is illustrated by an example from Japan, using combined regression data.

Quantitative Methods for Estimating the Size of a Drug-Using Population

The author describes several of the most important quantitative procedures for estimating the size of an unobserved or partially observed population, with specific application to the estimation of the prevalence of drug use. The methods discussed include synthetic estimation, truncated Poisson estimates, multiple-capture surveys in both closed populations (the capture-recapture model and log-linear models) and open populations (the Jolly-Seber model and Markov models), and, more briefly, system dynamics models.

Estimating the Mean and Variance of Measurements from Serial Radioactive Decay Schemer with Emphasis on &lt;sup&gt;222&lt;/sup&gt;Rn and its Short-Lived Progeny

Classically, the mean and variance of radioactivity measurements are estimated from poisson distributions. However, the random distribution of observed events is not poisson when the half-life is short compared with the interval of observation or when more than one event can be associated with a single initial atom. Procedures were developed to estimate the mean and variance of single measurements of serial radioactive processes. Results revealed that observations from the three consecutive alpha emissions beginning with 222Rn are positively correlated. Since the poisson estimator ignores covariance terms, it underestimates the true variance of the measurement. The reverse is true for mixtures of radon daughters only.

Interpreting the reverse multinomial logit as a count data model

Abstract The reverse logit has been used with some success to predict trip demand, despite the lack of a theoretically plausible foundation. In this article, it is shown that the reverse logit can be derived from demand theory. Specifically, when demand is modeled with a fixed effects Poisson estimator, the results are analytically equivalent to the reverse logit.

Bank failures as Poisson variates

The elasticity of bank failures with respect to a set of explanatory variables is estimated using a maximum-likelihood Poisson estimator. The resulting estimates are compared with their OLS counterparts.

Teacher‐Friendly Transportation Program

A series of programs has been developed especially for educational purposes and to support the lectures on urban and interurban modelling. These programs are collectively called “Teacher‐Friendly Transportation Program/Student Proof Version” or TFTP/SPV.The programs consist of four levels. The first level illustrates the working of the calculation methods used in detail. The second level gives the interconnection between the different parts of the transportation forecasting model. The third level demonstrates the estimation of base year origindestination matrices, estimation of deterrence functions, and the nonlinear weighted Poisson estimation method for multidimensional matrices. The programs are used in lectures, but can also be used as prototypes in feasibility studies of new research developments (Level IV). The programs can be used on microcomputers working under MSDOS.

Highly precise field measurement of the Topaz magnet at the Tristan collider

The magnetic field distribution of the TOPAZ detector for the 30 × 30 GeV e +e − colliding beam experiment at TRISTAN, has been measured very precisely over a volume of 2.3 m in diameter and 4.2 m in length. This paper will describe the details of the reconstruction procedure of the field distribution from the measured data and the results of a comparison with a POISSON estimation. An accuracy of 10 −4 in the measurement of B ⊥/ B z has been achieved.

Bus journey times in medium size urban areas

AbstractThe predictive accuracy of the models based on the fundamental relation between journey time and passenger demand can be improved through data disaggregation or route segmentation. Primary reason for this is the improvement in the estimates of stopping delays and delays due to passenger boarding and/or alighting (dwell time). Both Poisson and Negative Binomial model estimates of stoppings for passenger boarding and alighting are shown to improve with disaggregation. These improvements, however, contribute little to the overall predictability of the fundamental models which are useful for gaining insight into the significance and variability of the stopping delays and dwell time, or testing sensitivity to changes in the long term. Site or route specific models of journey times which have better predictive capability exist, and may be used for short‐run planning. However, the interchangeability and performance over time of the latter, have to be evaluated before making definitive conclusions.