Statistical methods for dependent competing risks

In this study, the kinetics of glomerular endothelial cells during the repair process following glomerular injury was investigated in a model of mesangial proliferative glomerulonephritis induced by Habu-snake venom (HSV) in rats. Intravenous injection of HSV led to a cystic ballooning type lesion at day 1. Subsequently a marked segmental proliferative lesion was observed in the cystic areas at day 5. Thereafter cellularity decreased and reconstruction of the glomerular tuft was gradually observed with time. The histological structure of the glomeruli had almost returned to normal 21 days following HSV injection. After prominent depletion at day 1, the number of endothelial cells increased rapidly and reached a plateau at day 7, not significantly different from that of the control group. Morphologically endothelial cell elongation from the vascular pole into the cystic lesion was seen together with premature capillary formation in the proliferative lesion. Accompanying the reduction of mesangial expansion, the endothelial cells gradually formed definite capillary lumens. We conclude that the mesangial proliferative glomerulonephritis induced by HSV recovers to its original structural state and that the migration and proliferation of endothelial cells with accompanying capillary formation are essential for the repair process, in addition to mesangial cell proliferation.     

Statistical methods for analyses of incomplete clinical service records: Concurrent use of longitudinal and cross-sectional data.

Statistical procedures that have become routine in other social sciences were used to analyze data from clinical service records. Despite the absence of control groups, nonrandom assignment of clients to treatment conditions, and incomplete records, effective analyses of psychotherapeutic processes were possible. Multivariate regression models, with variables that were transformed to significantly improve skewness and regression linearity, were controlled for heteroskedasticity and for end-point censoring of dependent variables. They were also used to measure the effects of a categorical variable (gender) and a scalable variable (intake distress) on a reactive outcome measure (of acute distress) and on an unreactive one (of long-term satisfaction). Graphical methods for summarizing large data sets helped identify intake variables that could control for attrition-related sampling biases. These longitudinal covariates and corrections to adjust degrees of freedom for cases with repeated measures were then used to construct statistical models that were equivalents of pure cross-sectional designs. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Statistical methods in computational anatomy

This paper reviews recent developments by the Washington/Brown groups for the study of anatomical shape in the emerging new discipline of computational anatomy. Parametric representations of anatomical variation for computational anatomy are reviewed, restricted to the assumption of small deformations. The generation of covariance operators for probabilistic measures of anatomical variation on coordinatized submanifolds is formulated as an empirical procedure. Populations of brains are mapped to common coordinate systems, from which template coordinate systems are constructed which are closest to the population of anatomies in a minimum distance sense. Variation of several one-, two- and three-dimensional manifolds, i.e. sulci, surfaces and brain volumes are examined via Gaussian measures with mean and covariances estimated directly from maps of templates to targets. Methods are presented for estimating the covariances of vector fields from a family of empirically generated maps, posed as generalized spectrum estimation indexed over the submanifolds. Covariance estimation is made parametric, analogous to autoregressive modelling, by introducing small deformation linear operators for constraining the spectrum of the fields.     

Statistical methods in psychiatric genetics

Most psychiatric disorders are determined by the complex interplay between genetic and environmental factors. Aetiological research into these complex disorders raises many different questions which require a variety of statistical methods. These include survival analysis for the estimation of morbid risk, structural equation models for the partitioning of phenotypic variances and covariances into genetic and other components, complex segregation analysis to detect loci of major effect, and linkage and association analysis for the localisation and identification of susceptibility genes. Future developments in psychiatric genetics will involve the integration of genetic and epidemiological statistics in order to study the interplay between genetic and environmental factors in the complex pathways which lead to mental disorders.     

When temporal terms belie conceptual order

We conceive of time as a sequential order of real-world events, one event following another from past to present to future. This conception colours the way we speak of time ("we look forward to the time") and, as we show here, the way we process written statements referring to the temporal order of events, in real time. Terms such as 'before' and 'after' give us the linguistic freedom to express a series of events (real or imaginary) in any order. However, sentences that present events out of chronological order require additional discourse-level computation. Here we examine how and when these computations are carried out by contrasting brain potentials across two sentence types that differ only in their initial word ('After' X, Y versus 'Before' X, Y). At sites on the left frontal scalp, the responses to 'before' and 'after' sentences diverge within 300 ms; the size of this difference increases over the course of the sentences and is correlated with individual working-memory spans. Thus, we show that there are immediate and lasting consequences for neural processing of the discourse implications of a single word on sentence comprehension.     

Statistical issues in periodontal research

In the past 10 to 12 years, there have been several statistical issues identified in periodontal research which require and have generated non-standard or new statistical approaches. The purpose of this paper is to give an overview of these issues and approaches. Three general categories of issues are described: (i) statistical methods for detecting when disease progression occurs, and biological theories and corresponding statistical models which attempt to describe how the disease progresses; (ii) design issues in studies of therapeutic efficacy; and (iii) analytic issues arising from periodontal data analysis.     

Statistical methods in factor analysis.

"A recent investigation of the efficiency of the centroid method of analysis is noted, and a recommendation is made regarding a valid test of the significance of residual matrices when this method is employed. The 'simple structure' concept is criticized and an alternative approach in the search for psychologically meaningful factors is recommended." 44 refs. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Individual variation for cognitive decline: Quantitative methods for describing patterns of change.

What are the best quantitative methods for studying cognitive decline? This question was investigated in a sample of 638 individuals aged 50 years and older from the Swedish Adoption/Twin Study of Aging. A battery of cognitive tests tapping multiple domains was administered to each individual from 2 to 7 times over a span of 10 years. Four methods of operationalizing cognitive decline were compared: change scores, a criterion-based method, least squares, and random effects regression (RER). The RER results were most consistent with a significant decline across measures and differences between demented and nondemented individuals. Predicted slopes from the RER model also showed the strongest interrelationships within and across cognitive domains as indicated by factor analysis results and stronger associations with demographic, health, and psychosocial predictors. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Judged temporal order and spatial context.

Studied the way pattern interpretations affect perceived temporal order in the brain. The coding system is presented as a method of predicting and interpreting pattern change. 40 Ss viewed 24 slides showing random shapes for 1 msec each and then viewed pairs of shapes for 2 sec. Ss then indicated which figure out of the pair had appeared 1st in the 1st stage. In each of these pairs, the interpretation of 1 pattern affected the interpretation of the other, but not the reverse. (French abstract) (7 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Auditory temporal order perception in younger and older adults

This investigation examined the abilities of younger and older listeners to discriminate and identify temporal order of sounds presented in tonal sequences. It was hypothesized that older listeners would exhibit greater difficulty than younger listeners on both temporal processing tasks, particularly for complex stimulus patterns. It was also anticipated that tone order discrimination would be easier than tone order identification for all listeners. Listeners were younger and older adults with either normal hearing or mild-to-moderate sensorineural hearing losses. Stimuli were temporally contiguous three-tone sequences within a 1/3 octave frequency range centered at 4000 Hz. For the discrimination task, listeners discerned differences between standard and comparison stimulus sequences that varied in tonal temporal order. For the identification task, listeners identified tone order of a single sequence using labels of relative pitch. Older listeners performed more poorly than younger listeners on the discrimination task for the more complex pitch patterns and on the identification task for faster stimulus presentation rates. The results also showed that order discrimination is easier than order identification for all listeners. The effects of hearing loss on the ordering tasks were minimal.     

Statistical methods in epidemiology: I. Statistical errors in hypothesis testing

PURPOSE: Although scientific journal editors are making use of statisticians in the review process, the quality of statistical reporting in many journals remains poor. In many cases the problem for the scientist would appear to be a lack of understanding of basic statistics. The focus of the scientist is on showing 'p < 0.05', when what is actually required is a statement about effect size and interval estimation. The aim of this paper is to show the inadequacy of reporting of results using p-values alone. This paper is the first in a series detailing common statistical methods, with a view to aiding potential authors in their statistical presentation of data. METHOD: A review of the basic hypothesis test, using examples from the author's own teaching experiences. RESULTS: Type I and type II errors are defined; the problem of multiple comparisons is highlighted; interval estimation is introduced. CONCLUSIONS: The case for considering the p-value as an error probability is made which suggests ways of improving statistical presentation and thus expediting the statistical review process.     

Statistical research needs in mechanistic modelling for carcinogenic risk assessment

This study reports the results of implant therapy involving a sinus membrane lift as well as conventional implant therapy in 24 periodontally compromised patients who were treated during the period between June 1990 and May 1995. Patients were included on the basis of being in need of at least 2 implants, 1 of which was to be placed in the maxillary sinus region, and at least 3 mm bone height was required in the sinus region. Following fenestration of the lateral sinus wall and lifting of the sinus membrane sinus implants were inserted as described for conventional implants. Annual follow-up visits included recording of plaque, probing pocket depth and bleeding on probing, and recording of the radiographic distance from the implant shoulder to the alveolar crest in mm. The Astra, Astra sinus, ITI, and ITI sinus were observed for an average of 30.8, 29.9, 29.4 and 25.3 months, respectively. Of the 80 implants inserted 1 Astra and 2 ITI had failed at 11-12 months and 1 ITI had failed at 42 months. The Kaplan-Meier estimate of the proportion of non-failed implants at 36 months were 100%, 95%, 91%, and 86% for the Astra, Astra sinus, ITI, and ITI sinus implants, respectively. Of the Astra, Astra sinus, and ITI implants, 71-82% remained free from bone-loss > or = 1.5 mm at 36 months, whereas this was the case for only 29% of the ITI sinus implants. About 80-90% of the implants remained free from plaque; 65-86% remained free from bleeding; and 44-80% remained free from pockets > or = 4 mm. These results indicate that the sinus lift technique can be used successfully in periodontally compromised patients.     

Statistical methods for the analysis of tumor multiplicity data

The fit of tumor multiplicity data from 93 mouse skin, lung, and liver carcinogenicity experiments to Poisson, negative binomial, and normal distributions was studied. The data were fitted well by the negative binomial distribution. This distribution has two parameters, the mean tumor multiplicity and an exponent determined by the interanimal homogeneity of tumor response. The value of the latter parameter was related to animal strain and the target tissue studied in the carcinogenicity experiments. The null distribution of the two-sample likelihood ratio test based on the negative binomial with common exponent model for tumor multiplicity data was shown by simulation studies to be approximately chi 2 with 1 d.f. Simulation also indicated that the likelihood ratio test has sufficiently better performance when the negative binomial model is valid to make its use more attractive than the more commonly used Wilcoxon test or Student t test. Charts for estimating the number of animals per group that are required to detect specified differences in tumor multiplicities are provided for several commonly used assays.     

Attention and the perception of temporal order.

The effect of directing attention to a particular location in space has been widely examined in the study of human information processing. Current models assume that attention modulates the speed of information flow such that attended signals are transmitted more rapidly through the perceptual system than unattended signals. This assumption that attention modulates the speed of information flow was examined in the present research by having observers judge the temporal order of two visual stimuli while directing their attention towards one of the stimuli or away from both stimuli. In one experiment, attended stimuli were perceived with a shorter latency than unattended stimuli, supporting the assumption that attention influences the speed of information transmission in the visual system. The results of another experiment indicate that attention alters the temporal profile of the visual responses, such that visual responses at the attended location are more sharply tuned than responses at the unattended location. It is concluded that attention has two effects on visual responses: It affects the transmission speed of information in the visual system and it alters the temporal profile of the responses. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Strategic processing and memory for temporal order in patients with frontal lobe lesions.

This study evaluated whether deficits in memory for temporal order in patients with frontal lobe lesions result from impaired automatic encoding of temporal information or are secondary to deficits in effortful processes, such as the use of organizational strategies and control of interference. Patients with lesions in the dorsolateral prefrontal cortex and control participants were tested on temporal order reconstruction of semantically related and unrelated word lists learned under intentional or incidental conditions. Memory for temporal order in patients with frontal lobe lesions was sensitive to semantic relatedness but not to intention to learn. Tests of item free recall and recognition using similar encoding manipulations indicated that order performance in these patients was dissociable from item memory. Results indicate that automatic processing of temporal information is intact in patients with frontal lobe lesions but that strategic processing of this information is impaired. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Evidence for auditory temporal distinctiveness: Modality effects in order and frequency judgments.

Two new, long-lasting phenomena involving modality of stimulus presentation are documented. In one series of experiments we investigated effects of modality of presentation on order judgments. Order judgments for auditory words were more accurate than order judgments for visual words at both the beginning and the end of lists, and the auditory advantage increased with the temporal separation of the successive items. A second series of experiments investigated effects of modality on estimates of presentation frequency. Frequency estimates of repeated auditory words exceeded frequency estimates of repeated visual words. The auditory advantage increased with frequency of presentation, and this advantage was not affected by the retention interval. These various effects were taken as support for a temporal coding assumption, that auditory presentation produces a more accurate encoding of time of presentation than does visual presentation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Statistical methods for the Ames Salmonella assay: a review

Exposure of Clone 9 cells, a rat liver cell line, to hydrogen peroxide (H2O2) resulted in a striking and rapid stimulation of glucose transport (8- to 10-fold in 1 h). A comparable response was found in 3T3-L1 preadipocytes, C2C12 myoblasts, and NIH 3T3 fibroblasts, which, similar to Clone 9 cells, express only the Glut 1 glucose transporter isoform. The enhancement of glucose transport in Clone 9 cells in response to H2O2 was significantly attenuated by genistein and the phospholipase C (PLC) inhibitor, U73122. Exposure to H2O2 resulted in a rise in cell sn-1,2-diacylglycerol content, and the rise was significantly inhibited by U73122. Moreover, the H2O2-induced stimulation of glucose transport was significantly blocked by thapsigargin. Neither staurosporine nor a 24-h preincubation in the presence of phorbol-12-myristate-13-acetate (TPA) affected the stimulatory effect of hydrogen peroxide on glucose transport. The activity of big mitogen-activated kinase (BMK1) and of stress-activated protein kinase (SAPK), both members of mitogen-activated protein kinases, were enhanced in response to exposure to H2O2; however, neither protein kinase appeared to be linked to the enhancement of glucose transport by H2O2. It is concluded that the stimulation of glucose transport in response to H2O2 is independent of changes in PKC, BMK1, and SAPK activity, and is mediated, at least in part, through H2O2-induced stimulation of protein tyrosine kinase and PLC pathways.