Variance estimation with Chao's sampling scheme

We show that the Hájek (Ann. Math Statist. (1964) 1491) variance estimator can be used to estimate the variance of the Horvitz–Thompson estimator when the Chao sampling scheme (Chao, Biometrika 69 (1982) 653) is implemented. This estimator is simple and can be implemented with any statistical packages. We consider a numerical and an analytic method to show that this estimator can be used. A series of simulations supports our findings.

Estimators in capture-recapture studies with two sources

This paper investigates the applications of capture-recapture methods to human populations. Capture-recapture methods are commonly used in estimating the size of wildlife populations but can also be used in epidemiology and social sciences, for estimating prevalence of a particular disease or the size of the homeless population in a certain area. Here we focus on estimating the prevalence of infectious diseases. Several estimators of population size are considered: the Lincoln-Petersen estimator and its modified version, the Chapman estimator, Chao's lower bound estimator, the Zelterman's estimator, McKendrick's moment estimator and the maximum likelihood estimator. In order to evaluate these estimators, they are applied to real, three-source, capture-recapture data. By conditioning on each of the sources of three source data, we have been able to compare the estimators with the true value that they are estimating. The Chapman and Chao estimators were compared in terms of their relative bias. A variance formula derived through conditioning is suggested for Chao's estimator, and normal 95% confidence intervals are calculated for this and the Chapman estimator. We then compare the coverage of the respective confidence intervals. Furthermore, a simulation study is included to compare Chao's and Chapman's estimator. Results indicate that Chao's estimator is less biased than Chapman's estimator unless both sources are independent. Chao's estimator has also the smaller mean squared error. Finally, the implications and limitations of the above methods are discussed, with suggestions for further development.

A novel variant on chromosome 7q22.3 associated with mean platelet volume, counts, and function

Mean platelet volume (MPV) and platelet count (PLT) are highly heritable and tightly regulated traits. We performed a genome-wide association study for MPV and identified one SNP, rs342293, as having highly significant and reproducible association with MPV (per-G allele effect 0.016 +/- 0.001 log fL; P < 1.08 x 10(-24)) and PLT (per-G effect -4.55 +/- 0.80 10(9)/L; P < 7.19 x 10(-8)) in 8586 healthy subjects. Whole-genome expression analysis in the 1-MB region showed a significant association with platelet transcript levels for PIK3CG (n = 35; P = .047). The G allele at rs342293 was also associated with decreased binding of annexin V to platelets activated with collagen-related peptide (n = 84; P = .003). The region 7q22.3 identifies the first QTL influencing platelet volume, counts, and function in healthy subjects. Notably, the association signal maps to a chromosome region implicated in myeloid malignancies, indicating this site as an important regulatory site for hematopoiesis. The identification of loci regulating MPV by this and other studies will increase our insight in the processes of megakaryopoiesis and proplatelet formation, and it may aid the identification of genes that are somatically mutated in essential thrombocytosis. (Blood. 2009; 113: 3831-3837)

A simple variance formula for population size estimators by conditioning

This note considers the variance estimation for population size estimators based on capture–recapture experiments. Whereas a diversity of estimators of the population size has been suggested, the question of estimating the associated variances is less frequently addressed. This note points out that the technique of conditioning can be applied here successfully which also allows us to identify sources of variation: the variance due to estimation of the model parameters and the binomial variance due to sampling n units from a population of size N. It is applied to estimators typically used in capture–recapture experiments in continuous time including the estimators of Zelterman and Chao and improves upon previously used variance estimators. In addition, knowledge of the variances associated with the estimators by Zelterman and Chao allows the suggestion of a new estimator as the weighted sum of the two. The decomposition of the variance into the two sources allows also a new understanding of how resampling techniques like the Bootstrap could be used appropriately. Finally, the sample size question for capture–recapture experiments is addressed. Since the variance of population size estimators increases with the sample size, it is suggested to use relative measures such as the observed-to-hidden ratio or the completeness of identification proportion for approaching the question of sample size choice.

Estimation following selection of the largest of two normal means

This paper considers the problem of estimation when one of a number of populations, assumed normal with known common variance, is selected on the basis of it having the largest observed mean. Conditional on selection of the population, the observed mean is a biased estimate of the true mean. This problem arises in the analysis of clinical trials in which selection is made between a number of experimental treatments that are compared with each other either with or without an additional control treatment. Attempts to obtain approximately unbiased estimates in this setting have been proposed by Shen [2001. An improved method of evaluating drug effect in a multiple dose clinical trial. Statist. Medicine 20, 1913–1929] and Stallard and Todd [2005. Point estimates and confidence regions for sequential trials involving selection. J. Statist. Plann. Inference 135, 402–419]. This paper explores the problem in the simple setting in which two experimental treatments are compared in a single analysis. It is shown that in this case the estimate of Stallard and Todd is the maximum-likelihood estimate (m.l.e.), and this is compared with the estimate proposed by Shen. In particular, it is shown that the m.l.e. has infinite expectation whatever the true value of the mean being estimated. We show that there is no conditionally unbiased estimator, and propose a new family of approximately conditionally unbiased estimators, comparing these with the estimators suggested by Shen.

Adjusted jackknife for imputation under unequal probability sampling without replacement

Imputation is commonly used to compensate for item non-response in sample surveys. If we treat the imputed values as if they are true values, and then compute the variance estimates by using standard methods, such as the jackknife, we can seriously underestimate the true variances. We propose a modified jackknife variance estimator which is defined for any without-replacement unequal probability sampling design in the presence of imputation and non-negligible sampling fraction. Mean, ratio and random-imputation methods will be considered. The practical advantage of the method proposed is its breadth of applicability.

A theoretical adaptive model of thermal comfort – Adaptive Predicted Mean Vote (aPMV)

This paper presents in detail a theoretical adaptive model of thermal comfort based on the “Black Box” theory, taking into account factors such as culture, climate, social, psychological and behavioural adaptations, which have an impact on the senses used to detect thermal comfort. The model is called the Adaptive Predicted Mean Vote (aPMV) model. The aPMV model explains, by applying the cybernetics concept, the phenomena that the Predicted Mean Vote (PMV) is greater than the Actual Mean Vote (AMV) in free-running buildings, which has been revealed by many researchers in field studies. An Adaptive coefficient (λ) representing the adaptive factors that affect the sense of thermal comfort has been proposed. The empirical coefficients in warm and cool conditions for the Chongqing area in China have been derived by applying the least square method to the monitored onsite environmental data and the thermal comfort survey results.

Evaluation of milk urea nitrogen as a diagnostic of protein feeding

An evaluation of milk urea nitrogen (MUN) as a diagnostic of protein feeding in dairy cows was performed using mean treatment data (n = 306) from 50 production trials conducted in Finland (n = 48) and Sweden (n = 2). Data were used to assess the effects of diet composition and certain animal characteristics on MUN and to derive relationships between MUN and the efficiency of N utilization for milk production and urinary N excretion. Relationships were developed using regression analysis based on either models of fixed factors or using mixed models that account for between-experiment variations. Dietary crude protein (CP) content was the best single predictor of MUN and accounted for proportionately 0.778 of total variance [ MUN (mg/dL) = -14.2 + 0.17 x dietary CP content (g/kg dry matter)]. The proportion of variation explained by this relationship increased to 0.952 when a mixed model including the random effects of study was used, but both the intercept and slope remained unchanged. Use of rumen degradable CP concentration in excess of predicted requirements, or the ratio of dietary CP to metabolizable energy as single predictors, did not explain more of the variation in MUN (R-2 = 0.767 or 0.778, respectively) than dietary CP content. Inclusion of other dietary factors with dietary CP content in bivariate models resulted in only marginally better predictions of MUN (R-2 = 0.785 to 0.804). Closer relationships existed between MUN and dietary factors when nutrients (CP to metabolizable energy) were expressed as concentrations in the diet, rather than absolute intakes. Furthermore, both MUN and MUN secretion (g/d) provided more accurate predictions of urinary N excretion (R-2 = 0.787 and 0.835, respectively) than measurements of the efficiency of N utilization for milk production (R-2 = 0.769). It is concluded that dietary CP content is the most important nutritional factor influencing MUN, and that measurements of MUN can be utilized as a diagnostic of protein feeding in the dairy cow and used to predict urinary N excretion.

Modeling the variability of single-cell lag times for Listeria innocua populations after sublethal and lethal heat treatments

Optical density measurements were used to estimate the effect of heat treatments on the single-cell lag times of Listeria innocua fitted to a shifted gamma distribution. The single-cell lag time was subdivided into repair time ( the shift of the distribution assumed to be uniform for all cells) and adjustment time (varying randomly from cell to cell). After heat treatments in which all of the cells recovered (sublethal), the repair time and the mean and the variance of the single-cell adjustment time increased with the severity of the treatment. When the heat treatments resulted in a loss of viability (lethal), the repair time of the survivors increased with the decimal reduction of the cell numbers independently of the temperature, while the mean and variance of the single-cell adjustment times remained the same irrespective of the heat treatment. Based on these observations and modeling of the effect of time and temperature of the heat treatment, we propose that the severity of a heat treatment can be characterized by the repair time of the cells whether the heat treatment is lethal or not, an extension of the F value concept for sublethal heat treatments. In addition, the repair time could be interpreted as the extent or degree of injury with a multiple-hit lethality model. Another implication of these results is that the distribution of the time for cells to reach unacceptable numbers in food is not affected by the time-temperature combination resulting in a given decimal reduction.

What do we mean when we refer to Bacteroidetes populations in the human gastrointestinal microbiota?

Recent large-scale cloning studies have shown that the ratio of Bacteroidetes to Firmicutes may be important in the obesity-associated gut microbiota, but the species these phyla represent in this ecosystem has not been examined. The Bacteroidetes data from the recent Turnbaugh study were examined to determine those members of the phylum detected in human faecal samples. In addition, FISH analysis was performed on faecal samples from 17 healthy, nonobese donors using probe Bac303, routinely used by gut microbiologists to enumerate BacteroidesPrevotella populations in faecal samples, and another probe (CFB286) whose target range has some overlap with that of Bac303. Sequence analysis of the Turnbaugh data showed that 23/519 clones were chimeras or erroneous sequences; all good sequences were related to species of the order Bacteroidales, but no one species was present in all donors. FISH analysis demonstrated that approximately one-quarter of the healthy, nonobese donors harboured high numbers of Bacteroidales not detected by probe Bac303. It is clear that Bacteroidales populations in human faecal samples have been underestimated in FISH-based studies. New probes and complementary primer sets should be designed to examine numerical and compositional changes in the Bacteroidales during dietary interventions and in studies of the obesity-associated microbiota in humans and animal model systems.

Borg's rating of perceived exertion scales: do the verbal anchors mean the same for different clinical groups?

Objective: To examine the interpretation of the verbal anchors used in the Borg rating of perceived exertion (RPE) scales in different clinical groups and a healthy control group. Design: Prospective experimental study. Setting: Rehabilitation center. Participants: Nineteen subjects with brain injury, 16 with chronic low back pain (CLBP), and 20 healthy controls. Interventions: Not applicable. Main Outcome Measures: Subjects used a visual analog scale (VAS) to rate their interpretation of the verbal anchors from the Borg RPE 6-20 and the newer 10-point category ratio scale. Results: All groups placed the verbal anchors in the order that they occur on the scales. There were significant within-group differences (P > .05) between VAS scores for 4 verbal anchors in the control group, 8 in the CLBP group, and 2 in the brain injury group. There was no significant difference in rating of each verbal anchor between the groups (P > .05). Conclusions: All subjects rated the verbal anchors in the order they occur on the scales, but there was less agreement in rating of each verbal anchor among subjects in the brain injury group. Clinicians should consider the possibility of small discrepancies in the meaning of the verbal anchors to subjects, particularly those recovering from brain injury, when they evaluate exercise perceptions.

Improvement of classification accuracy for stochastic discrimination - Multi-class classification

In this paper, an improved stochastic discrimination (SD) is introduced to reduce the error rate of the standard SD in the context of multi-class classification problem. The learning procedure of the improved SD consists of two stages. In the first stage, a standard SD, but with shorter learning period is carried out to identify an important space where all the misclassified samples are located. In the second stage, the standard SD is modified by (i) restricting sampling in the important space; and (ii) introducing a new discriminant function for samples in the important space. It is shown by mathematical derivation that the new discriminant function has the same mean, but smaller variance than that of standard SD for samples in the important space. It is also analyzed that the smaller the variance of the discriminant function, the lower the error rate of the classifier. Consequently, the proposed improved SD improves standard SD by its capability of achieving higher classification accuracy. Illustrative examples axe provided to demonstrate the effectiveness of the proposed improved SD.

Kernel classifier construction using orthogonal forward selection and boosting with Fisher ratio class separability measure

A greedy technique is proposed to construct parsimonious kernel classifiers using the orthogonal forward selection method and boosting based on Fisher ratio for class separability measure. Unlike most kernel classification methods, which restrict kernel means to the training input data and use a fixed common variance for all the kernel terms, the proposed technique can tune both the mean vector and diagonal covariance matrix of individual kernel by incrementally maximizing Fisher ratio for class separability measure. An efficient weighted optimization method is developed based on boosting to append kernels one by one in an orthogonal forward selection procedure. Experimental results obtained using this construction technique demonstrate that it offers a viable alternative to the existing state-of-the-art kernel modeling methods for constructing sparse Gaussian radial basis function network classifiers. that generalize well.

OFDM joint data detection and phase noise cancellation based on minimum mean square prediction error

This paper proposes a new iterative algorithm for orthogonal frequency division multiplexing (OFDM) joint data detection and phase noise (PHN) cancellation based on minimum mean square prediction error. We particularly highlight the relatively less studied problem of "overfitting" such that the iterative approach may converge to a trivial solution. Specifically, we apply a hard-decision procedure at every iterative step to overcome the overfitting. Moreover, compared with existing algorithms, a more accurate Pade approximation is used to represent the PHN, and finally a more robust and compact fast process based on Givens rotation is proposed to reduce the complexity to a practical level. Numerical Simulations are also given to verify the proposed algorithm. (C) 2008 Elsevier B.V. All rights reserved.