A covariate adjustment for zero-truncated approaches to estimating the size of hidden and elusive populations

In this paper we consider the estimation of population size from onesource capture–recapture data, that is, a list in which individuals can potentially be found repeatedly and where the question is how many individuals are missed by the list. As a typical example, we provide data from a drug user study in Bangkok from 2001 where the list consists of drug users who repeatedly contact treatment institutions. Drug users with 1, 2, 3, . . . contacts occur, but drug users with zero contacts are not present, requiring the size of this group to be estimated. Statistically, these data can be considered as stemming from a zero-truncated count distribution.We revisit an estimator for the population size suggested by Zelterman that is known to be robust under potential unobserved heterogeneity. We demonstrate that the Zelterman estimator can be viewed as a maximum likelihood estimator for a locally truncated Poisson likelihood which is equivalent to a binomial likelihood. This result allows the extension of the Zelterman estimator by means of logistic regression to include observed heterogeneity in the form of covariates. We also review an estimator proposed by Chao and explain why we are not able to obtain similar results for this estimator. The Zelterman estimator is applied in two case studies, the first a drug user study from Bangkok, the second an illegal immigrant study in the Netherlands. Our results suggest the new estimator should be used, in particular, if substantial unobserved heterogeneity is present.

Estimating the hidden number of scrapie affected holdings in great Britain using a simple, truncated count model allowing for heterogeneity.

None of the current surveillance streams monitoring the presence of scrapie in Great Britain provide a comprehensive and unbiased estimate of the prevalence of the disease at the holding level. Previous work to estimate the under-ascertainment adjusted prevalence of scrapie in Great Britain applied multiple-list capture–recapture methods. The enforcement of new control measures on scrapie-affected holdings in 2004 has stopped the overlapping between surveillance sources and, hence, the application of multiple-list capture–recapture models. Alternative methods, still under the capture–recapture methodology, relying on repeated entries in one single list have been suggested in these situations. In this article, we apply one-list capture–recapture approaches to data held on the Scrapie Notifications Database to estimate the undetected population of scrapie-affected holdings with clinical disease in Great Britain for the years 2002, 2003, and 2004. For doing so, we develop a new diagnostic tool for indication of heterogeneity as well as a new understanding of the Zelterman and Chao’s lower bound estimators to account for potential unobserved heterogeneity. We demonstrate that the Zelterman estimator can be viewed as a maximum likelihood estimator for a special, locally truncated Poisson likelihood equivalent to a binomial likelihood. This understanding allows the extension of the Zelterman approach by means of logistic regression to include observed heterogeneity in the form of covariates—in case studied here, the holding size and country of origin. Our results confirm the presence of substantial unobserved heterogeneity supporting the application of our two estimators. The total scrapie-affected holding population in Great Britain is around 300 holdings per year. None of the covariates appear to inform the model significantly.

Environmental control for layers

Light patterns have less effect on numbers of eggs laid by current stocks than on those of forty years ago, but the principles have not changed. Ovarian activity is stimulated by increasing photoperiods and suppressed by decreasing photoperiods. The light pattern used during rearing can still have large effects on age at 50% lay, even for modern stocks. Early sexual maturity maximises egg numbers but gives smaller eggs. Late maturity maximises egg size at the expense of numbers. The relationship between egg output (g/hen d) and age at first egg is curvilinear, with maximum yield occurring in flocks maturing in about the centre of their potential range. Fancy patterns of increasing daylength after maturity are probably not justified. A flock held on a constant 14h day will lay as many eggs as one given step up lighting. Intermittent lighting saves about 5% of feed consumption with no loss of output, provided that the feed has adequate amino acid content to allow for the reduced feed intake. Producers with light-proof laying houses should be taking advantage of intermittent lighting. The recommended light intensity for laying houses is still 10 lx, although the physiological threshold for response to changes in photoperiod is closer to 2 lx. Very dim (0.05 lx) light filtering into blacked out houses will not stimulate the hypothalamic receptors responsible for photo-sexual responses, but may affect the bird's biological clock, which can alter its response to a constant short photoperiod. Feed intake shows a curvilinear dependence on environmental temperature. At temperatures below the panting threshold, performance can be maintained by adjusting the feed so as to maintain an adequate intake of critical amino acids. Above the panting threshold, the hen is unable to take in enough energy to maintain normal output. There is no dietary modification which can effectively offset this problem. Diurnally cycling temperatures result in feed intake and egg production equivalent to that observed under a constant temperature equal to the mean of the cycle. When the poultry house is cooler at night than by day, it helps to provide light so that the birds can feed during the cooler part of the cycle.

Nutrition of chicks and layers

When formulating least-cost poultry diets, ME concentration should be optimised by an iterative procedure, not entered as a fixed value. This iteration must calculate profit margins by taking into account the way in which feed intake and saleable outputs vary with ME concentration. In the case of broilers, adjustment of critical amino acid contents in direct proportion to ME concentration does not result in birds of equal fatness. To avoid an increase in fat deposition at higher energy levels, it is proposed that amino acid specifications should be adjusted in proportion to changes in the net energy supplied by the feed. A model is available which will both interpret responses to amino acids in laying trials and give economically optimal estimates of amino acid inputs for practical feed formulation. Flocks coming into lay and flocks nearing the end of the pullet year have bimodal distributions of rates of lay, with the result that calculations of requirement based on mean output will underestimate the optimal amino acid input for the flock. Chick diets containing surplus protein can lead to impaired utilisation of the first-limiting amino acid. This difficulty can be avoided by stating amino acid requirements as a proportion of the protein.

Estimating the hidden number of scrapie affected holdings in great Britain using a simple, truncated count model allowing for heterogeneity

None of the current surveillance streams monitoring the presence of scrapie in Great Britain provide a comprehensive and unbiased estimate of the prevalence of the disease at the holding level. Previous work to estimate the under-ascertainment adjusted prevalence of scrapie in Great Britain applied multiple-list capture-recapture methods. The enforcement of new control measures on scrapie-affected holdings in 2004 has stopped the overlapping between surveillance sources and, hence, the application of multiple-list capture-recapture models. Alternative methods, still under the capture-recapture methodology, relying on repeated entries in one single list have been suggested in these situations. In this article, we apply one-list capture-recapture approaches to data held on the Scrapie Notifications Database to estimate the undetected population of scrapie-affected holdings with clinical disease in Great Britain for the years 2002, 2003, and 2004. For doing so, we develop a new diagnostic tool for indication of heterogeneity as well as a new understanding of the Zelterman and Chao's lower bound estimators to account for potential unobserved heterogeneity. We demonstrate that the Zelterman estimator can be viewed as a maximum likelihood estimator for a special, locally truncated Poisson likelihood equivalent to a binomial likelihood. This understanding allows the extension of the Zelterman approach by means of logistic regression to include observed heterogeneity in the form of covariates-in case studied here, the holding size and country of origin. Our results confirm the presence of substantial unobserved heterogeneity supporting the application of our two estimators. The total scrapie-affected holding population in Great Britain is around 300 holdings per year. None of the covariates appear to inform the model significantly.

Detecting recombination in 4-taxa DNA sequence alignments with Bayesian hidden Markov models and Markov chain Monte Carlo

This article presents a statistical method for detecting recombination in DNA sequence alignments, which is based on combining two probabilistic graphical models: (1) a taxon graph (phylogenetic tree) representing the relationship between the taxa, and (2) a site graph (hidden Markov model) representing interactions between different sites in the DNA sequence alignments. We adopt a Bayesian approach and sample the parameters of the model from the posterior distribution with Markov chain Monte Carlo, using a Metropolis-Hastings and Gibbs-within-Gibbs scheme. The proposed method is tested on various synthetic and real-world DNA sequence alignments, and we compare its performance with the established detection methods RECPARS, PLATO, and TOPAL, as well as with two alternative parameter estimation schemes.

Ovarian follicle development in the laying hen is accompanied by divergent changes in inhibin A, inhibin B, activin A and follistatin production in granulosa and theca layers

To study the potential involvement of inhibin A (inhA), inhibin B (inhB), activin A (actA) and follistatin (FS) in the recruitment of follicles into the preovulatory hierarchy, growing follicles (ranging from 1 mm to the largest designated F1) and the three most recent postovulatory follicles (POFs) were recovered from laying hens (n=11). With the exception of <4 mm follicles and POFs, follicle walls were dissected into separate granulosa (G) and theca (T) layers before extraction. Contents of inhA, inhB, actA and FS in tissue extracts were assayed using specific two-site ELISAs and results are expressed per mg DNA. InhB content of both G and T followed a similar developmental pattern, although the content was >4-fold higher in G than in T at all stages. InhB content was very low in follicles <4 nun but increased - 50-fold (P<0.0001) to peak in 7-9 mm follicles, before falling steadily as follicles entered and moved up the follicular hierarchy (40-fold; 8 mm vs F2). In stark contrast, inhA remained very low in prehierarchical follicles (&LE; 9 mm) but then increased progressively as follicles moved up the preovulatory hierarchy to peak in F1 (&SIM; 100-fold increase; P<0.0001); In F1 >97% of inhA was confined to the G layer whereas in 5-9 mm follicles inhA was only. detected in the T layer. Both inhA and inhB contents of POFs were significantly reduced compared with F1. Follicular actA was mainly confined to the T layer although detectable levels were present in G from 9 nun; actA was low between 1 and 9 mm but increased sharply as follicles entered the preovulatory hierarchy (&SIM;6-fold higher in F4; P<0.0001); levels then fell &SIM;2-fold as the follicle progressed to F1. Like actA, FS predominated in the T although significant amounts were also present in the G of prehierarchical follicles (4-9 mm), in contrast to actA, which was absent from the G. The FS content of T rose &SIM;3-fold from 6 mm to a plateau which was sustained until F1. In contrast, the FS content of G was greatest in prehierarchical follicles and fell &SIM;4-fold in F4-F1 follicles. ActA and FS contents of POFs were reduced compared with F1. In vitro studies on follicle wall explants confirmed the striking divergence in the secretion of inhA and inhB during follicle development. These findings of marked stage-dependent differences in the expression of inhA, inhB, actA and FS proteins imply a significant functional role for these peptides in the recruitment and ordered progression of follicles within the avian ovary.

Estimation of Hidden Markov Models parameters using differential evolution

Hidden Markov Models (HMMs) have been successfully applied to different modelling and classification problems from different areas over the recent years. An important step in using HMMs is the initialisation of the parameters of the model as the subsequent learning of HMM’s parameters will be dependent on these values. This initialisation should take into account the knowledge about the addressed problem and also optimisation techniques to estimate the best initial parameters given a cost function, and consequently, to estimate the best log-likelihood. This paper proposes the initialisation of Hidden Markov Models parameters using the optimisation algorithm Differential Evolution with the aim to obtain the best log-likelihood.

Vertical velocity variance and skewness in clear and cloud-topped boundary layers as revealed by Doppler lidar

In this paper, observations by a ground-based vertically pointing Doppler lidar and sonic anemometer are used to investigate the diurnal evolution of boundary-layer turbulence in cloudless, cumulus and stratocumulus conditions. When turbulence is driven primarily by surface heating, such as in cloudless and cumulus-topped boundary layers, both the vertical velocity variance and skewness follow similar profiles, on average, to previous observational studies of turbulence in convective conditions, with a peak skewness of around 0.8 in the upper third of the mixed layer. When the turbulence is driven primarily by cloud-top radiative cooling, such as in the presence of nocturnal stratocumulus, it is found that the skewness is inverted in both sign and height: its minimum value of around −0.9 occurs in the lower third of the mixed layer. The profile of variance is consistent with a cloud-top cooling rate of around 30Wm−2. This is also consistent with the evolution of the thermodynamic profile and the rate of growth of the mixed layer into the stable nocturnal boundary layer from above. In conditions where surface heating occurs simultaneously with cloud-top cooling, the skewness is found to be useful for diagnosing the source of the turbulence, suggesting that long-term Doppler lidar observations would be valuable for evaluating boundary-layer parametrization schemes. Copyright c 2009 Royal Meteorological Society

Hidden interlocutor misidentification in practical Turing Tests

Based on insufficient evidence, and inadequate research, Floridi and his students report inaccuracies and draw false conclusions in their Minds and Machines evaluation, which this paper aims to clarify. Acting as invited judges, Floridi et al. participated in nine, of the ninety-six, Turing tests staged in the finals of the 18th Loebner Prize for Artificial Intelligence in October 2008. From the transcripts it appears that they used power over solidarity as an interrogation technique. As a result, they were fooled on several occasions into believing that a machine was a human and that a human was a machine. Worse still, they did not realise their mistake. This resulted in a combined correct identification rate of less than 56%. In their paper they assumed that they had made correct identifications when they in fact had been incorrect.

Properties of thick evaporated layers of PbTe

The changes in the optical transparency of PbTe monolayers induced by post-evaporation heat treatment are described. The monolayers are typically a few microns in thickness and heat treatment reduces the carrier density from about 1018 (n-type) per cm3 to 1017 per cm3 : the source material is 1019 (ptype) per cm3. The process seems to involve the diffusion of O2 at a reaction rate equivalent to an energy of 0.83 eV.