Bayesian semiparametric zero-inflated Poisson model for longitudinal count data

This paper presents new methods, using a Bayesian approach, for analyzing longitudinal count data with excess zeros and nonlinear effects of continuously valued covariates. In longitudinal count data there are many problems that can make the use of a zero-inflated Poisson (ZIP) model ineffective. These problems are unobserved heterogeneity and nonlinear effects of continuously valued covariates. Our proposed semiparametric model can simultaneously handle these problems in a unified framework. The framework accounts for heterogeneity by incorporating random effects and has two components. The parametric component of the model which deals with the linear effects of time invariant covariates and the non-parametric component which gives an arbitrary smooth function to model the effect of time or time-varying covariates on the logarithm of mean count. The proposed methods are illustrated by analyzing longitudinal count data on the assessment of an efficacy of pesticides in controlling the reproduction of whitefly.     

The gamma-frailty Poisson model for the nonparametric estimation of panel count data

In this article, we study nonparametric estimation of the mean function of a counting process with panel observations. We introduce the gamma frailty variable to account for the intracorrelation between the panel counts of the counting process and construct a maximum pseudo-likelihood estimate with the frailty variable. Three simulated examples are given to show that this estimation procedure, while preserving the robustness and simplicity of the computation, improves the efficiency of the nonparametric maximum pseudo-likelihood estimate studied in Wellner and Zhang (2000, Annals of Statistics 28, 779-814). A real example from a bladder tumor study is used to illustrate the method.     

Measuring the effect of including multiple cancers in survival analyses using data from the Canadian Cancer Registry

Background: In survival analyses using cancer registry data, second and subsequent primary cancers diagnosed in individuals are typically excluded. However, this approach may lead to biased comparisons of survival between cancer registries, or over time within a single registry. Purpose: To examine the impact of including multiple primary cancers in the derivation of survival estimates using data from a population-based national cancer registry. Methods: Five-year relative survival estimates for persons aged 15–99 years at diagnosis were derived using all eligible primary cases from the Canadian Cancer Registry (CCR)—a population-based registry containing information on cases diagnosed from 1992 onward—and then again using first primary cases only. Any pre-1992 cancer history of persons on the CCR was obtained by using auxiliary information. Results: The inclusion of multiple cancers resulted in lower estimates of 5-year relative survival for virtually all cancers studied. The effect was somewhat attenuated by age-standardization (e.g., from 1.3% to 1.0% for all cancers combined), and was greatest for bladder cancer (?2.4%) followed by oral cancer (?1.9%)—cancers that had the first and third lowest proportions of first cancers, respectively. For the majority of cancers the difference was less than 1.0%. Cancers for which there was virtually no difference (e.g., lung, pancreatic, ovarian and liver) tended to be those with a poor prognosis. Conclusion: Inclusion of second and subsequent primary cancers in the analysis tended to lower estimates of relative survival, the extent of which varied by cancer and age and depended in part on the proportion of first primary cancers.     

Mast cell tumours and other skin neoplasia in Danish dogs - data from the Danish Veterinary Cancer Registry

Background  

The Danish Veterinary Cancer Registry (DVCR) was established in May 2005 to gather information about neoplasms in the Danish dog and cat populations. Practitioners from more than 60 clinics throughout Denmark have submitted data on these species. The objectives of the current study were, with a special focus on mast cell tumours (MCT) to investigate the occurrence, gender distribution, biological behaviour, locations, types, the diagnostic method used and treatment of skin neoplasms in dogs based on information reported to the DVCR.     

Applicability of broken-rodlike chain model to conformational analysis of polypeptide chain

In order to check the applicability of the broken-rodlike (BR) chain model, consisting of several rods alternatively joined by flexible random coils, to the conformational analysis of a polypeptide chain in the helix-to-coil transition regions, two relations predicted by the Zimm and Bragg theory and the method with the BR chain model are compared. It is shown that, despite a clear difference between the models employed in the two methods, they give substantially identical results in both probability P(j) that a helical residue is in a helical sequence j units long and averaged helical fraction dependence of the mean-squared radius of gyration. Thus the use of the method with the BR chain model in the conformational analysis of a polypeptide chain could be rationalized, at least, with the same degree of approximation as is assumed in the Zimm and Bragg theory. Using the scattering function for the BR chain model, averaged helical-sequence lengths are evaluated for partially ionized poly(L-glutamic acid) (PGA) in added-salt aqueous solution and nonionized PGA in N-methylacetamide, both in a helical state. As a result, it is shown that the length in the latter molecule is approximately tenfold longer than that in the former one.     

New cases of melanoma as documented in the National Cancer Registry

The authors briefly survey general aspects of crucial importance for the proper functioning of the National Cancer Registry, such as legislation, collected data, identification of patients, the completeness and validity of its content in relation to the results and conclusions of a comprehensive, national supervision performed after the Melanoma Consensus Conference. Compared to earlier national controlling attempts, the present supervision was highly successful: doctors of various hospitals did perform the detailed control of diagnosis in 95.81% of 1361 melanoma patients announced in 2001. They checked whether patients given the C43 BNO code had melanoma indeed, searched for those who received a different BNO code and identified those not announced for any reason to the Registry. After correction the Registry included 1117 new cases of melanoma in 2001. The authors state that the conclusions from this supervision may enhance the reliability not only of the data base of the Registry but that of the hospitals as well.     

Some goodness-of-fit methods for the Poisson plus added zeros distribution

Methods for making inferences about the Poisson plus added zeros distribution and the truncated Poisson distribution are presented and illustrated with bacteriological data. Some of the methods are designed for testing the compatibility of the zero frequency with the Poisson distribution, whereas others are given for testing the goodness of fit for the truncated Poisson. In particular, a modified form of the Fisher index of dispersion is presented which is suitable for the truncated case. It is shown that the use of the usual expression of the index of dispersion for testing the adequacy of the truncated Poisson is not correct and leads to accepting inadequate fits more frequently than expected on the basis of test of significance. Furthermore, three test statistics are presented for testing the compatability of the zero frequency with the Poisson distribution. The results of the simulation show that two test statistics, one due to Cochran (W. G. Cochran, Biometrics 10:417-451, 1954) and the other to Rao and Chakravarti (C. R. Rao and I. M. Chakravarti, Biometrics 12:264-282, 1956), are preferable to those from the likelihood ratio test.     

Oral malignant melanomas and other head and neck neoplasms in Danish dogs - data from the Danish Veterinary Cancer Registry

Background  

Head and neck cancers (HNC) are relatively common and often very serious diseases in both dogs and humans. Neoplasms originating in the head and neck region are a heterogeneous group. HNC often has an unfavourable prognosis and the proximity of the tissue structures renders extirpation of tumours with sufficient margins almost incompatible with preservation of functionality. In humans oral malignant melanoma (OMM) is extremely rare, but represents a particular challenge since it is highly aggressive as is the canine counterpart, which thus may be of interest as a spontaneous animal model.     

A Poisson model of sequence comparison and its application to coronavirus phylogeny

In this paper, we propose two metrics to compare DNA and protein sequences based on a Poisson model of word occurrences. Instead of comparing the frequencies of all fixed-length words in two sequences, we consider (1) the probability of ‘generating’ one sequence under the Poisson model estimated from the other; (2) their different expression levels of words. Phylogenetic trees of 25 viruses including SARS-CoVs are constructed to illustrate our approach.     

Ethnic distribution of phenylketonuria in the north German population

Summary Results of neonatal screening for phenylketonuria (PKU) suggest a west-east gradient of PKU gene frequency in central Europe. In order to test the hypothesis that the unexpectedly high prevalence of PKU in northwestern Germany (northern region of the FRG) is due to the migration of Germans from eastern regions of prewar Germany in the decade after World War II. grandparental origin was determined in a group of 87 pediatric PKU patients and in a control group of 210 children. Grandparents of east German origin were significantly more frequent among the PKU patients. The observed frequency distribution of grandparental subgroups was described by a theoretical distribution in order to obtain a likely set of values for the ratio between the frequency of the PKU gene in the autochthonous populations of prewar northeastern and northwestern Germany. The most likely value for the PKU gene frequency ratio was 1.37, which indicates that the prevalence for PKU in prewar northeastern Germany was almost twice as high as in the autochthonous population of the northwest.Dedicated to Professor P. E. Becker on the occasion of his 75th birthday     

Some goodness-of-fit methods for the Poisson plus added zeros distribution.

Methods for making inferences about the Poisson plus added zeros distribution and the truncated Poisson distribution are presented and illustrated with bacteriological data. Some of the methods are designed for testing the compatibility of the zero frequency with the Poisson distribution, whereas others are given for testing the goodness of fit for the truncated Poisson. In particular, a modified form of the Fisher index of dispersion is presented which is suitable for the truncated case. It is shown that the use of the usual expression of the index of dispersion for testing the adequacy of the truncated Poisson is not correct and leads to accepting inadequate fits more frequently than expected on the basis of test of significance. Furthermore, three test statistics are presented for testing the compatability of the zero frequency with the Poisson distribution. The results of the simulation show that two test statistics, one due to Cochran (W. G. Cochran, Biometrics 10:417-451, 1954) and the other to Rao and Chakravarti (C. R. Rao and I. M. Chakravarti, Biometrics 12:264-282, 1956), are preferable to those from the likelihood ratio test.     

A Monte Carlo study of tests on data originating from quadrat sampling. I: Data from a Poisson distribution

Computer simulations are used to examine the significance levels and powers of several tests which have been employed to compare the means of Poisson distributions. In particular, attention is focused on the behaviour of the tests when the means are small, as is often the case in ecological studies when populations of organisms are sampled using quadrats. Two approaches to testing are considered. The first assumes a log linear model for the Poisson data and leads to tests based on the deviance. The second employs standard analysis of variance tests following data transformations, including the often used logarithmic and square root transformations. For very small means it is found that a deviance-based test has the most favourable characteristics, generally outperforming analysis of variance tests on transformed data; none of the latter appears consistently better than any other. For larger means the standard analysis of variance on untransformed data performs well.     

A finite mixture distribution model for data collected from twins.

Most analyses of data collected from a classical twin study of monozygotic (MZ) and dizygotic (DZ) twins assume that zygosity has been diagnosed without error. However, large scale surveys frequently resort to questionnaire-based methods of diagnosis which classify twins as MZ or DZ with less than perfect accuracy. This article describes a mixture distribution approach to the analysis of twin data when zygosity is not perfectly diagnosed. Estimates of diagnostic accuracy are used to weight the likelihood of the data according to the probability that any given pair is either MZ or DZ. The performance of this method is compared to fully accurate diagnosis, and to the analysis of samples that include some misclassified pairs. Conventional analysis of samples containing misclassified pairs yields biased estimates of variance components, such that additive genetic variance (A) is underestimated while common environment (C) and specific environment (E) components are overestimated. The bias is non-trivial; for 10% misclassification, true values of Additive genetic: Common environment: Specific Environment variance components of.6:.2:.2 are estimated as.48:.29:.23, respectively. The mixture distribution yields unbiased estimates, while showing relatively little loss of statistical precision for misclassification rates of 15% or less. The method is shown to perform quite well even when no information on zygosity is available, and may be applied when pair-specific estimates of zygosity probabilities are available.