SEARCH · Search PubMed

Results for “statistical inference”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,279 records · Page 71Linked to original sources

PubMed2000

Homogeneity of kappa statistics in multiple samples.

The measurement of intra-observer agreement when the data are categorical has been the subject of several investigators since Cohen first proposed the kappa (kappa) as a chance-corrected coefficient of agreement for nominal scales. Subsequent procedures have been developed to assess the agreement of several raters using a dichotomous classification scheme, assess majority agreement among several raters using a polytomous classification scheme, and the use of kappa as an indicator of the quality of a measurement. Further developments include inference procedures for testing the homogeneity of k>/=2 independent kappa statistics. An executable FORTRAN code for testing the homogeneity of kappa statistics (kappa(h)) across multiple sites or studies is given. The FORTRAN program listing and/or executable programs are available from the author on request.

Analysis of Variance↗

PubMed2003

A review of the limitations of statistical analysis of treatment outcomes used in periodontal research.

Results of clinical trials are reported in terms of statistical significance, but interpretation of statistical significance in relation to clinical benefits is limited. Furthermore, the compromises inherent in the design of clinical trials, and in the statistical analysis techniques themselves cast doubts on the soundness of the inferences drawn from data from clinical trials. The aim of this paper is to review the published research on data management and interpretation in periodontal research, and to attempt to find ways in which the results of clinical trials could be reported in a more meaningful way, in terms of treatment outcomes. It is concluded that due to the limitations of current statistical methods and trial design, that clinical outcome variables should be reported in addition to statistical significance. Furthermore, due to the multiplicity of sites, subjects, and variables used to report on clinical conditions that may not be linear in their progression or regression, care needs to be exercised in interpretation of the results of clinical trials to avoid reporting positive outcome results that arise out of the limitations of current statistical analysis techniques or computational errors rather than clinical changes.

Clinical Trials as Topic↗

PubMed1997

A likelihood-based approach to the estimation of relative DNA copy number by comparative genomic hybridization.

A general approach is described for efficiently and objectively analyzing comparative genomic hybridization (CGH) profile data based on the use of realistic statistical models and the application of standard likelihood-based inference. In contrast to other methods in current use, the approach provides a most parsimonious explanation by identifying the smallest number of relative DNA copy number changes consistent with the data, together with estimates of their levels and positions and of their standard errors. By making efficient use of available data, it has the potential to enhance the resolution of CGH technology. The computational feasibility of the method is illustrated by application to real CGH profile data from human chromosome 4.

Chromosomes, Human, Pair 4↗

PubMed1965

SUICIDE IN SAN FRANCISCO: REPORTED AND UNREPORTED.

Reported suicide in San Francisco was investigated for the period between July 1956, through June 1964. During that time 1664 persons killed themselves, according to the Coroner's records. The method most frequently used was oral ingestion of toxic substances, which significantly deviates from national statistics, shooting being the method most frequently reported. The explanation for this deviation is probably the more valid mortality statistics of San Francisco, and from this it may be inferred that unreported suicide may be largely suicide by ingestion, unrecognized because of lack of postmortem studies. Unreported suicide is further classified into intentioned (masked, suppressed and undiscovered) and subintentioned (oral-dependent and aggressive). Despite the fact that suicide has been a leading cause of death, the public and the medical profession are largely apathetic. An attempt is being made by Suicide Prevention of San Francisco, Inc. to develop a clinical and research facility for the study and treatment of suicidal persons.

Adolescent↗

PubMed2004

Statistical parametric mapping for event-related potentials (II): a hierarchical temporal model.

In this paper, we describe a temporal model for event-related potentials (ERP) in the context of statistical parametric mapping (SPM). In brief, we project channel data onto a two-dimensional scalp surface or into three-dimensional brain space using some appropriate inverse solution. We then treat the spatiotemporal data in a mass-univariate fashion. This implicitly factorises the model into spatial and temporal components. The key contribution of this paper is the use of observation models that afford an explicit distinction between observation error and variation in the expression of ERPs. This distinction is created by employing a two-level hierarchical model, in which the first level models the ERP effects within-subject and trial type, while the second models differences in ERP expression among trial types and subjects. By bringing the analysis of ERP data into a classical hierarchical (i.e., mixed effects) framework, many apparently disparate approaches (e.g., conventional P300 analyses and time-frequency analyses of stimulus-locked oscillations) can be reconciled within the same estimation and inference procedure. Inference proceeds in the normal way using t or F statistics to test for effects that are localised in peristimulus time or in some time-frequency window. The use of F statistics is an important generalisation of classical approaches, because it allows one to test for effects that lie in a multidimensional subspace (i.e., of unknown but constrained form). We describe the analysis procedures, the underlying theory and compare its performance to established techniques.

Analysis of Variance↗

PubMed2005

Mixed-effects and fMRI studies.

This note concerns mixed-effect (MFX) analyses in multisession functional magnetic resonance imaging (fMRI) studies. It clarifies the relationship between mixed-effect analyses and the two-stage "summary statistics" procedure (Holmes, A.P., Friston, K.J., 1998. Generalisability, random effects and population inference. NeuroImage 7, S754) that has been adopted widely for analyses of fMRI data at the group level. We describe a simple procedure, based on restricted maximum likelihood (ReML) estimates of covariance components, that enables full mixed-effects analyses in the context of statistical parametric mapping. Using this procedure, we compare the results of a full mixed-effects analysis with those obtained from the simpler two-stage procedure and comment on the situations when the two approaches may give different results.

Brain↗

PubMed2004

Spot shape modelling and data transformations for microarrays.

MOTIVATION: To study lowly expressed genes in microarray experiments, it is useful to increase the photometric gain in the scanning. However, a large gain may cause some pixels for highly expressed genes to become saturated. Spatial statistical models that model spot shapes on the pixel level may be used to infer information about the saturated pixel intensities. Other possible applications for spot shape models include data quality control and accurate determination of spot centres and spot diameters. RESULTS: Spatial statistical models for spotted microarrays are studied including pixel level transformations and spot shape models. The models are applied to a dataset from 50mer oligonucleotide microarrays with 452 selected Arabidopsis genes. Logarithmic, Box-Cox and inverse hyperbolic sine transformations are compared in combination with four spot shape models: a cylindric plateau shape, an isotropic Gaussian distribution and a difference of two-scaled Gaussian distribution suggested in the literature, as well as a proposed new polynomial-hyperbolic spot shape model. A substantial improvement is obtained for the dataset studied by the polynomial-hyperbolic spot shape model in combination with the Box-Cox transformation. The spatial statistical models are used to correct spot measurements with saturation by extrapolating the censored data. AVAILABILITY: Source code for R is available at http://www.matfys.kvl.dk/~ekstrom/spotshapes/

Algorithms↗

PubMed2005

Harnessing the power of gene microarrays for the study of brain aging and Alzheimer's disease: statistical reliability and functional correlation.

During normal brain aging, numerous alterations develop in the physiology, biochemistry and structure of neurons and glia. Aging changes occur in most brain regions and, in the hippocampus, have been linked to declining cognitive performance in both humans and animals. Age-related changes in hippocampal regions also may be harbingers of more severe decrements to come from neurodegenerative disorders such as Alzheimer's disease (AD). However, unraveling the mechanisms underlying brain aging, AD and impaired function has been difficult because of the complexity of the networks that drive these aging-related changes. Gene microarray technology allows massively parallel analysis of most genes expressed in a tissue, and therefore is an important new research tool that potentially can provide the investigative power needed to address the complexity of brain aging/neurodegenerative processes. However, along with this new analytic power, microarrays bring several major bioinformatics and resource problems that frequently hinder the optimal application of this technology. In particular, microarray analyses generate extremely large and unwieldy data sets and are subject to high false positive and false negative rates. Concerns also have been raised regarding their accuracy and uniformity. Furthermore, microarray analyses can result in long lists of altered genes, most of which may be difficult to evaluate for functional relevance. These and other problems have led to some skepticism regarding the reliability and functional usefulness of microarray data and to a general view that microarray data should be validated by an independent method. Given recent progress, however, we suggest that the major problem for current microarray research is no longer validity of expression measurements, but rather, the reliability of inferences from the data, an issue more appropriately redressed by statistical approaches than by validation with a separate method. If tested using statistically defined criteria for reliability/significance, microarray data do not appear a priori to require more independent validation than data obtained by any other method. In fact, because of added confidence from co-regulation, they may require less. In this article we also discuss our strategy of statistically correlating individual gene expression with biologically important endpoints designed to address the problem of evaluating functional relevance. We also review how work by ourselves and others with this powerful technology is leading to new insights into the complex processes of brain aging and AD, and to novel, more comprehensive models of aging-related brain change.

Aging↗

PubMed1993

Human flash-VEP and quantitative EEG are independently affected by acute scopolamine.

Scopolamine in acute intramuscular doses of 0.25-0.75 mg reduced the P2-N3 flash-VEP amplitude and, in the quantitative EEG, the 8.5-12.0 Hz power and total power in 8 healthy young male volunteers. The effects on flash-VEP and EEG total power were dose dependent and were evident 30 min and 90 min respectively after drug administration, regardless of dose. The reduction in 8.5-12.0 Hz power was limited to the 0.50 and 0.75 mg doses. No systematic effects on the pattern-VEP were observed. Possible interferences with flash- or pattern-VEP amplitude of the scopolamine-induced EEG changes were identified and removed by regression analysis and computation of VEP residuals from the regression function. The P2-N3 flash-VEP residuals proved EEG independent and showed relationships with dose and time after drug administration that were superimposable on those of the original data, with comparable significance levels at the drug/placebo and pre/postdrug statistical comparisons. The results indicate that VEP estimates of drug effects which are independent from EEG changes can be identified in human studies and allow some inference on the cholinergic specificity of the systems affecting late flash-VEP components. The statistical approach used in this study is suitable for application in VEP studies when effects of interacting factors are to be expected.

Adult↗

PubMed1975

Left ventricular ejection time. multiple relation to physiological and biometrical data; prediction of reference standards.

The relationship between left ventricular ejection time, and physiological or biometrical data, is submitted to multivariate statistical analysis. Methodology is intended to attain three objectives: 1) to simulate a controlled-condition experiment in clinical research, by using the statistical method of multiple regression; 2) to get a wide inference of conclusions, by selecting a sample of two hundred subjects whose biological data cover a wide field; 3) to check the really prospective value of results, by applying the formula worked out in a group of a hundred subjects to another independent group of a hundred subjects. The prediction formula of ejection time takes into account: stroke volume, cardiac cycle duration, body height, sex, age, pulse pressure, blood capacity in oxygen, presence or absence of digitalis treatment or atrial fibrillation. The first aim of the formula is to better evaluate the normal relationship between considered variables. Secondarily it leads to a proposal for estimating mechanical performance of the left ventricle.

Adolescent↗

PubMed1998

Why morphometrics is not special: coding quantitative data for phylogenetic analysis.

Thorpe (1984) and Chappill (1989) argued that selection of a coding method should be [figure: see text] based on the purpose of coding. In our view, the purpose of coding is dictated by the principles of phylogenetic systematics. The foundation of phylogenetic systematics is the observation that monophyletic groups can be recognized if homologous character states, shared evolutionary novelties, can be identified (Hennig, 1966). Unfortunately, characters do not have labels indicating their homology. Instead, a systematist must propose a hypothesis of homology and evaluate its congruence with independent hypotheses based on other traits. In this context, the purpose of coding is to represent those hypotheses. The major obstacle to coding is that the a priori groups under analysis (i.e., taxa) often have ranges of variation that overlap to some degree. This is true whether traits are described qualitatively or quantitatively. One advantage of quantitative description is that it permits a more detailed analysis of how much the ranges of variation overlap. It may seem appropriate to use statistical methods to summarize the amount of overlap and even to decide objectively (on a priori grounds) whether taxa are similar or different. Above, we demonstrated some of the problems resulting from these uses of statistical analysis. In our view, the most important problem is the implication that similarity of the feature across taxa is the basis for inferring homology. The similarity that is relevant to phylogenetic analysis is not proximity in morphospace, but shared novelty. Statistical methods can describe proximity, but they cannot recognize novelty. The method of coding we recommend uses graphical displays of individual values. Coding decisions are based on all of the individuals in each taxon, not on summaries derived from models of expected distributions. Then, the evidence for inferring divergence is independently evaluated for each pair of overlapping taxa. Coding decisions are not based on a priori rules that have no bearing on recognition of evolutionary novelty. This is the same approach that is used to code qualitatively described traits.

Animals↗

PubMed1962