Meta-analysis: a unifying meta-likelihood approach framing unobserved heterogeneity, study covariates, publication bias, and study quality

OBJECTIVES: This contribution provides a unifying concept for meta-analysis integrating the handling of unobserved heterogeneity, study covariates, publication bias and study quality. It is important to consider these issues simultaneously to avoid the occurrence of artifacts, and a method for doing so is suggested here. METHODS: The approach is based upon the meta-likelihood in combination with a general linear nonparametric mixed model, which lays the ground for all inferential conclusions suggested here. RESULTS: The concept is illustrated at hand of a meta-analysis investigating the relationship of hormone replacement therapy and breast cancer. The phenomenon of interest has been investigated in many studies for a considerable time and different results were reported. In 1992 a meta-analysis by Sillero-Arenas et al. concluded a small, but significant overall effect of 1.06 on the relative risk scale. Using the meta-likelihood approach it is demonstrated here that this meta-analysis is due to considerable unobserved heterogeneity. Furthermore, it is shown that new methods are available to model this heterogeneity successfully. It is argued further to include available study covariates to explain this heterogeneity in the meta-analysis at hand. CONCLUSIONS: The topic of HRT and breast cancer has again very recently become an issue of public debate, when results of a large trial investigating the health effects of hormone replacement therapy were published indicating an increased risk for breast cancer (risk ratio of 1.26). Using an adequate regression model in the previously published meta-analysis an adjusted estimate of effect of 1.14 can be given which is considerably higher than the one published in the meta-analysis of Sillero-Arenas et al. In summary, it is hoped that the method suggested here contributes further to a good meta-analytic practice in public health and clinical disciplines.

CAMCR: Computer assisted mixture model analysis for capture-recapture count data

Population size estimation with discrete or nonparametric mixture models is considered, and reliable ways of construction of the nonparametric mixture model estimator are reviewed and set into perspective. Construction of the maximum likelihood estimator of the mixing distribution is done for any number of components up to the global nonparametric maximum likelihood bound using the EM algorithm. In addition, the estimators of Chao and Zelterman are considered with some generalisations of Zelterman’s estimator. All computations are done with CAMCR, a special software developed for population size estimation with mixture models. Several examples and data sets are discussed and the estimators illustrated. Problems using the mixture model-based estimators are highlighted.

Revisiting Youden's index as a useful measure of the misclassification error in meta-analysis of diagnostic studies

The paper considers meta-analysis of diagnostic studies that use a continuous Score for classification of study participants into healthy, or diseased groups. Classification is often done on the basis of a threshold or cut-off value, which might vary between Studies. Consequently, conventional meta-analysis methodology focusing solely on separate analysis of sensitivity and specificity might he confounded by a potentially unknown variation of the cut-off Value. To cope with this phenomena it is suggested to use, instead an overall estimate of the misclassification error previously suggested and used as Youden's index and; furthermore, it is argued that this index is less prone to between-study variation of cut-off values. A simple Mantel-Haenszel estimator as a summary measure of the overall misclassification error is suggested, which adjusts for a potential study effect. The measure of the misclassification error based on Youden's index is advantageous in that it easily allows an extension to a likelihood approach, which is then able to cope with unobserved heterogeneity via a nonparametric mixture model. All methods are illustrated at hand of an example on a diagnostic meta-analysis on duplex doppler ultrasound, with angiography as the standard for stroke prevention.

CAMCR: Computer-Assisted Mixture model analysis for Capture–Recapture count data

Population size estimation with discrete or nonparametric mixture models is considered, and reliable ways of construction of the nonparametric mixture model estimator are reviewed and set into perspective. Construction of the maximum likelihood estimator of the mixing distribution is done for any number of components up to the global nonparametric maximum likelihood bound using the EM algorithm. In addition, the estimators of Chao and Zelterman are considered with some generalisations of Zelterman’s estimator. All computations are done with CAMCR, a special software developed for population size estimation with mixture models. Several examples and data sets are discussed and the estimators illustrated. Problems using the mixture model-based estimators are highlighted.

Geostatistical radar-raingauge combination with nonparametric correlograms: methodological considerations and application in Switzerland

Modelling spatial covariance is an essential part of all geostatistical methods. Traditionally, parametric semivariogram models are fit from available data. More recently, it has been suggested to use nonparametric correlograms obtained from spatially complete data fields. Here, both estimation techniques are compared. Nonparametric correlograms are shown to have a substantial negative bias. Nonetheless, when combined with the sample variance of the spatial field under consideration, they yield an estimate of the semivariogram that is unbiased for small lag distances. This justifies the use of this estimation technique in geostatistical applications. Various formulations of geostatistical combination (Kriging) methods are used here for the construction of hourly precipitation grids for Switzerland based on data from a sparse realtime network of raingauges and from a spatially complete radar composite. Two variants of Ordinary Kriging (OK) are used to interpolate the sparse gauge observations. In both OK variants, the radar data are only used to determine the semivariogram model. One variant relies on a traditional parametric semivariogram estimate, whereas the other variant uses the nonparametric correlogram. The variants are tested for three cases and the impact of the semivariogram model on the Kriging prediction is illustrated. For the three test cases, the method using nonparametric correlograms performs equally well or better than the traditional method, and at the same time offers great practical advantages. Furthermore, two variants of Kriging with external drift (KED) are tested, both of which use the radar data to estimate nonparametric correlograms, and as the external drift variable. The first KED variant has been used previously for geostatistical radar-raingauge merging in Catalonia (Spain). The second variant is newly proposed here and is an extension of the first. Both variants are evaluated for the three test cases as well as an extended evaluation period. It is found that both methods yield merged fields of better quality than the original radar field or fields obtained by OK of gauge data. The newly suggested KED formulation is shown to be beneficial, in particular in mountainous regions where the quality of the Swiss radar composite is comparatively low. An analysis of the Kriging variances shows that none of the methods tested here provides a satisfactory uncertainty estimate. A suitable variable transformation is expected to improve this.

An item response analysis of the motor and behavioral subscales of the unified Huntington's disease rating scale in huntington disease gene expansion carriers

Although the Unified Huntington's Disease Rating Scale (UHDRS) is widely used in the assessment of Huntington disease (HD), the ability of individual items to discriminate individual differences in motor or behavioral manifestations has not been extensively studied in HD gene expansion carriers without a motor-defined clinical diagnosis (ie, prodromal-HD or prHD). To elucidate the relationship between scores on individual motor and behavioral UHDRS items and total score for each subscale, a nonparametric item response analysis was performed on retrospective data from 2 multicenter longitudinal studies. Motor and behavioral assessments were supplied for 737 prHD individuals with data from 2114 visits (PREDICT-HD) and 686 HD individuals with data from 1482 visits (REGISTRY). Option characteristic curves were generated for UHDRS subscale items in relation to their subscale score. In prHD, overall severity of motor signs was low, and participants had scores of 2 or above on very few items. In HD, motor items that assessed ocular pursuit, saccade initiation, finger tapping, tandem walking, and to a lesser extent, saccade velocity, dysarthria, tongue protrusion, pronation/supination, Luria, bradykinesia, choreas, gait, and balance on the retropulsion test were found to discriminate individual differences across a broad range of motor severity. In prHD, depressed mood, anxiety, and irritable behavior demonstrated good discriminative properties. In HD, depressed mood demonstrated a good relationship with the overall behavioral score. These data suggest that at least some UHDRS items appear to have utility across a broad range of severity, although many items demonstrate problematic features.

Decline and recovery of total column ozone using a multimodel time series analysis

Simulations of 15 coupled chemistry climate models, for the period 1960–2100, are presented. The models include a detailed stratosphere, as well as including a realistic representation of the tropospheric climate. The simulations assume a consistent set of changing greenhouse gas concentrations, as well as temporally varying chlorofluorocarbon concentrations in accordance with observations for the past and expectations for the future. The ozone results are analyzed using a nonparametric additive statistical model. Comparisons are made with observations for the recent past, and the recovery of ozone, indicated by a return to 1960 and 1980 values, is investigated as a function of latitude. Although chlorine amounts are simulated to return to 1980 values by about 2050, with only weak latitudinal variations, column ozone amounts recover at different rates due to the influence of greenhouse gas changes. In the tropics, simulated peak ozone amounts occur by about 2050 and thereafter total ozone column declines. Consequently, simulated ozone does not recover to values which existed prior to the early 1980s. The results also show a distinct hemispheric asymmetry, with recovery to 1980 values in the Northern Hemisphere extratropics ahead of the chlorine return by about 20 years. In the Southern Hemisphere midlatitudes, ozone is simulated to return to 1980 levels only 10 years ahead of chlorine. In the Antarctic, annually averaged ozone recovers at about the same rate as chlorine in high latitudes and hence does not return to 1960s values until the last decade of the simulations.

Pooled analysis of recent studies on magnetic fields and childhood leukaemia

BACKGROUND: Previous pooled analyses have reported an association between magnetic fields and childhood leukaemia. We present a pooled analysis based on primary data from studies on residential magnetic fields and childhood leukaemia published after 2000. METHODS: Seven studies with a total of 10 865 cases and 12 853 controls were included. The main analysis focused on 24-h magnetic field measurements or calculated fields in residences. RESULTS: In the combined results, risk increased with increase in exposure, but the estimates were imprecise. The odds ratios for exposure categories of 0.1-0.2 mu T, 0.2-0.3 mu T and >= 0.3 mu T, compared with <0.1 mu T, were 1.07 (95% Cl 0.81-1.41), 1.16 (0.69-1.93) and 1.44 (0.88-2.36), respectively. Without the most influential study from Brazil, the odds ratios increased somewhat. An increasing trend was also suggested by a nonparametric analysis conducted using a generalised additive model. CONCLUSIONS: Our results are in line with previous pooled analyses showing an association between magnetic fields and childhood leukaemia. Overall, the association is weaker in the most recently conducted studies, but these studies are small and lack methodological improvements needed to resolve the apparent association. We conclude that recent studies on magnetic fields and childhood leukaemia do not alter the previous assessment that magnetic fields are possibly carcinogenic. British Journal of Cancer (2010) 103, 1128-1135. doi: 10.1038/sj.bjc.6605838 www.bjcancer.com (c) 2010 Cancer Research UK

Factors affecting the technical efficiency of production of the Brazilian banking system : a comparison of four statistical models in the context of data envelopment analysis

This paper uses an output oriented Data Envelopment Analysis (DEA) measure of technical efficiency to assess the technical efficiencies of the Brazilian banking system. Four approaches to estimation are compared in order to assess the significance of factors affecting inefficiency. These are nonparametric Analysis of Covariance, maximum likelihood using a family of exponential distributions, maximum likelihood using a family of truncated normal distributions, and the normal Tobit model. The sole focus of the paper is on a combined measure of output and the data analyzed refers to the year 2001. The factors of interest in the analysis and likely to affect efficiency are bank nature (multiple and commercial), bank type (credit, business, bursary and retail), bank size (large, medium, small and micro), bank control (private and public), bank origin (domestic and foreign), and non-performing loans. The latter is a measure of bank risk. All quantitative variables, including non-performing loans, are measured on a per employee basis. The best fits to the data are provided by the exponential family and the nonparametric Analysis of Covariance. The significance of a factor however varies according to the model fit although it can be said that there is some agreements between the best models. A highly significant association in all models fitted is observed only for nonperforming loans. The nonparametric Analysis of Covariance is more consistent with the inefficiency median responses observed for the qualitative factors. The findings of the analysis reinforce the significant association of the level of bank inefficiency, measured by DEA residuals, with the risk of bank failure.

Effect of the Insertion and Polymerization Technique in Composite Resin Restorations: Analysis of Marginal Gap by Atomic Force Microscopy

This in vitro study evaluated the marginal gap at the composite tooth/resin interface in class V cavities under the influence of two insertion techniques and a curing system by means of atomic force microscopy (AFM). Forty enamel and dentin cavities were prepared on the buccal surface in bovine teeth with quadratic forms measuring 2 mm X 2 mm and depth of 1.5 mm. The teeth were then divided into four groups: group A, 10 cavities were restored in one increment, light cured by halogen light; group B, 10 cavities filled with bulk filling, light cured by the light emitting diodes (LED); group C, 10 cavities were restored by the incremental technique, light cured by halogen light; group D, 10 cavities were restored by the incremental technique, light cured by the LED. The teeth underwent the polishing procedure and were analyzed by AFM for tooth/restoration interface evaluation. The data were compared between groups using the nonparametric Kruskall-Wallis and Mann-Whitney tests (p < 0.05). The results showed a statistically significant difference between groups A and B and groups A and C. It was concluded that no insertion and polymerization technique was able to completely seal the cavity.

Morphometric analysis of the venom gland in worker bees of Apis mellifera (Hymenoptera : Apidae) from the pantanal region of Mato Grosso do Sul

In Apis mellifera the acid or venom gland is composed of secretory cells that surround a channel that opens into a reservoir devoid of musculature. This gland can at times present apical branching. In this study we recorded the frequency of branched venom glands in workers of Africanized bees (Apis mellifera Linnaeus) from six localities in the Pantanal region of Mato Grosso do Sul, and analyzed the relation among the length of the main duct, the length of the duct from the reservoir to the beginning of branching, the length of the branched segment (when present) and the total length of the gland. We sought to determine the probable genotypes of the bees from each population by using the model proposed by Alves-Junior. The frequency of branched glands varied from 50% to 83% in the worker bees coming from those places, indicating that this characteristic is primitive in these bees. The results of the Analysis of Discriminant Functions indicated significant differences in the morphometrical segments of the venom gland (Wilk's Lambda = 0.065; F-(27,F-30) = 4.507; P < 0.001), and permitted a differentiation of the populations studied. The genotypes inferred for the bees of each locality agree with the results obtained in the Analysis of Discriminant Functions and form three distinct groups, with some overlapping areas among them. In all of the populations considered the phenotype largevenom gland was predominant. It is inferred that bees with this phenotype (venom gland larger than S. 15 mm) have Gm(1) Gm(1) genotype, being therefore homozygotes for the major alleles and also for the modifier genes that codify this morphological trait. The high frequency of worker bees with large venom gland in all the places considered makes viable the development of a selection program in order to obtain bees with longer venom glands, aimed at the commercial production of venom by the beekeepers of the Pantanal region of Mato Grosso do Sul.

The use of nonparametric contrasts in one-way layouts and random block designs

Nonparametric simple-contrast estimates for one-way layouts based on Hodges-Lehmann estimators for two samples and confidence intervals for all contrasts involving only two treatments are found in the literature.Tests for such contrasts are performed from the distribution of the maximum of the rank sum between two treatments. For random block designs, simple contrast estimates based on Hodges-Lehmann estimators for one sample are presented. However, discussions concerning the significance levels of more complex contrast tests in nonparametric statistics are not well outlined.This work aims at presenting a methodology to obtain p-values for any contrast types based on the construction of the permutations required by each design model using a C-language program for each design type. For small samples, all possible treatment configurations are performed in order to obtain the desired p-value. For large samples, a fixed number of random configurations are used. The program prompts the input of contrast coefficients, but does not assume the existence or orthogonality among them.In orthogonal contrasts, the decomposition of the value of the suitable statistic for each case is performed and it is observed that the same procedure used in the parametric analysis of variance can be applied in the nonparametric case, that is, each of the orthogonal contrasts has a chi(2) distribution with one degree of freedom. Also, the similarities between the p-values obtained for nonparametric contrasts and those obtained through approximations suggested in the literature are discussed.

Analysis of Apical Root Transportation Associated with Protaper Universal F3 and F4 Instruments by Using Digital Subtraction Radiography

Introduction: The aim of this study was to assess the occurrence of apical root transportation after the use of Pro Taper Universal rotary files sizes 3 (F3) and 4 (F4). Methods: Instruments were worked to the apex of the original canal, always by the same operator. Digital subtraction radiography images were produced in buccolingual and mesiodistal projections. A total of 25 radiographs were taken from root canals of human maxillary first molars with curvatures varying from 23-31 degrees. Quantitative data were analyzed by intraclass correlation coefficient and Wilcoxon nonparametric test (P = .05). Results: Buccolingual images revealed a significantly higher degree of apical transportation associated with F4 instruments when compared with F3 instruments in relation to the original canal (Wilcoxon test, P = .007). No significant difference was observed in mesiodistal images (P = .492). Conclusions: F3 instruments should be used with care in curved canals, and F4 instruments should be avoided in apical third preparation of curved canals. (J Endod 2010;36:1052-1055)

Elicitation of multivariate prior distributions: A nonparametric Bayesian approach

In the context of Bayesian statistical analysis, elicitation is the process of formulating a prior density f(.) about one or more uncertain quantities to represent a person's knowledge and beliefs. Several different methods of eliciting prior distributions for one unknown parameter have been proposed. However, there are relatively few methods for specifying a multivariate prior distribution and most are just applicable to specific classes of problems and/or based on restrictive conditions, such as independence of variables. Besides, many of these procedures require the elicitation of variances and correlations, and sometimes elicitation of hyperparameters which are difficult for experts to specify in practice. Garthwaite et al. (2005) discuss the different methods proposed in the literature and the difficulties of eliciting multivariate prior distributions. We describe a flexible method of eliciting multivariate prior distributions applicable to a wide class of practical problems. Our approach does not assume a parametric form for the unknown prior density f(.), instead we use nonparametric Bayesian inference, modelling f(.) by a Gaussian process prior distribution. The expert is then asked to specify certain summaries of his/her distribution, such as the mean, mode, marginal quantiles and a small number of joint probabilities. The analyst receives that information, treating it as a data set D with which to update his/her prior beliefs to obtain the posterior distribution for f(.). Theoretical properties of joint and marginal priors are derived and numerical illustrations to demonstrate our approach are given. (C) 2010 Elsevier B.V. All rights reserved.