Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Multivariate statistics”

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.

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

At least 397 records · Page 22Linked to original sources

Soluble metals in the atmosphere and their biological implications. A study to identify important aerosol components by statistical analysis of PIXE data.

Multivariate statistical analysis has been applied to time series measurements of aerosol elemental composition from PIXE analysis of filter samples, and principal components have been resolved that represent distinct particle types in an external mixture in the atmosphere. In this study, it is argued that a combination of chemical and statistical analyses of the data may be more powerful in determining chemical species in atmospheric aerosols than studied that employ mainly direct chemical analysis of chemical species in unresolved mixtures of aerosol particle samples. Sulfur is generally associated with mineral dust elements. It is reasoned that the association may represent sulfuric acid coatings on particles that can lead to mineral dissolution and solubilization of significant amounts of aluminum, iron, and other metals. Upon wet or dry deposition to the surface, the fluxes of these metals in biologically-available form may be sufficient to affect primary productivity in the world ocean and cause ecological damage in lakes. As a consequence, the fluxes of biogenic trace gases to the atmosphere may be changed, possibly leading to changes in the tropospheric concentration of ozone. The inputs to lakes of soluble aluminum, which is toxic to fish, may be partly by deposition directly from the atmosphere, thus not limited to leaching of soils by acid deposition. Human inhalation of soluble aluminum and other solubilized mineral metals may account, in part, for the observed geographic pattern of deaths attributed to chronic obstructive pulmonary disease (COPD) that show high rates in cities of the Western US and the southeast region, but low in most of the midwest and northeast.

Aerosols↗

An electrophysiological technique for assessment of the development of spatial vision.

An objective visual evoked potential (VEP) technique was developed to evaluate spatial processing in humans over a wide range of ages. The constellation of stimulus conditions and analysis methods constitute a novel tool for the assessment of neural development. The key points that delineate this VEP technique are: (1) A brief, 6-s, swept-parameter stimulus with spatial frequency of square-wave grating patterns varied in octave steps, which facilitates correct accommodation and increases the likelihood of collecting uninterrupted, useable data; (2) data collection synchronous with stimulus presentation, which prevents contamination of the relevant frequency component from other frequency components in the response, thereby increasing the signal-to-noise ratio; (3) noise estimation at the response frequency of interest (second harmonic), based on a multivariate statistic (Tcirc2), which yields a realistic measure of signal-to-noise; (4) estimation of grating acuity from linear interpolation of the signal-to-noise measure; (5) monocular testing followed by multivariate statistical comparison of fellow eye data for each spatial frequency condition, which enables the determination of asymmetries within monocular neural pathways; (6) evaluation of maturation of the visual system based on vector-averaged amplitude and phase measures. Preliminary results indicate that reliable response functions are obtained from infants, children, and adults. Acuity estimates increased as a function of age. Phase values decreased consistently with increases in spatial frequency greater than 4 c/deg. Infants produced larger peak amplitude responses than did older observers, consistent with known developmental changes in cortical synaptic density. Phase data for the 2 c/deg condition provided additional evidence for the lack of maturity in the infant visual system as compared with that of older observers.

Adolescent↗

Metabolites from cerebrospinal fluid in aneurysmal subarachnoid haemorrhage correlate with vasospasm and clinical outcome: a pattern-recognition 1H NMR study.

Following subarachnoid haemorrhage the most significant complication is sustained cerebral vascular contraction (vasospasm), which may result in terminal brain damage from cerebral infarction. Despite this, the biochemical cause of vasospasm remains poorly understood. In this study, the global high-concentration metabolite composition of CSF has been correlated with patient outcome after subarachnoid haemorrhage using multivariate statistics and 1H NMR spectroscopy. In total, 16 patients with aneurysmal subarachnoid haemorrhage (aSAH) were compared with 16 control patients who required a procedure where CSF was obtained but did not have aSAH. Multivariate statistics readily distinguished the aSAH group from the heterogeneous control group, even when only those controls with blood contamination in the CSF were used. Using principal components analysis and orthogonal signal correction, vasospasm was correlated to the concentrations of lactate, glucose and glutamine. These pattern recognition models of the NMR data also predicted Glasgow Coma Score (54% within +/- 1 of the actual score on a scale of 1-15 for the whole patient group), Hunt and Hess SAH severity score (88% within +/- 1 of the actual score on a scale of 1-5 for the aSAH group) and cognitive outcome scores (78% within +/- 3 of the actual score on a 100% scale for the whole patient group). Thus, the approach allowed the prediction of outcome as well as confirming the presence of aSAH.

Adult↗

Tracheal width and left double-lumen tube size: a formula to estimate left-bronchial width.

STUDY OBJECTIVE: To determine which patient parameters best predict left bronchial width (LBW) when selecting the correct size double-lumen tube (DLT). If LBW is known, a DLT that will fit that bronchus can be chosen. DESIGN: Prospective study. SETTING: University medical center. PATIENTS: Three hundred twenty-one consecutive patients scheduled for thoracic surgery and for whom there was a chest radiograph and for whom tracheal width (TW) and LBW could be measured. MEASUREMENTS: Tracheal width and LBW were directly measured from the chest radiograph. Patient demographic data were recorded and then analyzed to see which factor(s) best predicted LBW. Parameters often used for DLT selection (age, sex, height, and weight) as well as TW were compared by univariate and multivariate statistical analysis to see which factor(s) most accurately predicted LBW. MAIN RESULTS: There were weak but significant correlations between age and height and LBW in men, and height and LBW in women. Multivariate statistical analysis showed that, for both men and women, TW was the best predictor of LBW. Sex, height, and weight did not improve predictability over TW alone. The equation that best predicts LBW for both sexes is: LBWmm = (0.50)(TWmm) + 3.7 mm. This model explains 46% of the variance in LBW. As structures measured from a chest radiograph are magnified by 10%, the formula to predict LBW, which normalizes for this magnification factor, is: LBWmm = (0.45)(TWmm(CXR)) + 3.3 mm. CONCLUSIONS: Direct airway measurement is the most accurate way to select an appropriate DLT. However, when direct measurement of LBW cannot be performed, estimating LBW from TW is a better predictor of LBW than either sex, height, or weight.

Adult↗

Agricultural produces: synopsis of employed quality control methods for the authentication of foods and application of chemometrics for the classification of foods according to their variety or geographical origin.

A review of quality control methods and applications of multivariate statistical techniques on the authentication and classification of agricultural products is presented. The products reported within the frame of this article were vegetables, fruits, juices, jams, wines, cereals, bakery products, oils, tea, coffee, honey, sugar-syrups, salad dressings, and gums. The perspective of multivariate statistics as a promising tool to authenticate and classify these food products according to their geographical origin or variety was demonstrated. Several representative figures and informative synoptical tables for agricultural food products were provided both for the quality control methods employed and the multivariate analyses implemented.

Cluster Analysis↗

Treating missing data in a clinical neuropsychological dataset--data imputation.

Missing data frequently reduce the applicability of clinically collected data in research requiring multivariate statistics. In data imputation, missing values are replaced by predicted values obtained from models based on auxiliary information. Our aim was to complete a clinical child neuropsychological data set containing 5.2% of missing observations. This was to be used in research requiring multivariate statistics. We compared four data imputation methods by artificially deleting some data. A real-donor imputation method which preserved the parameter estimates and which predicted the observed values with acceptable accuracy was used to complete the data set. In addressing the lack of studies with regard to treatment of missing data in neuropsychological data sets, this study presents information on the outcomes of applying data imputation methods to such data. The imputation modeling described can be applied to a variety of clinical neuropsychological data sets.

Child↗

A multivariate strategy for prediction of psychoacoustic performance from electroacoustic characteristics of hearing aids.

Sentence length psychoacoustic material was processed through 16 hearing aids and presented to 220 listeners. Twenty-nine indices of electroacoustic performance were abstracted from a testing program under laboratory conditions. Through a multivariate statistical strategy, psychoacoustic achievement was shown to be positively correlated to and could be predicted by a knowledge of white noise gain, bandwidth below and above 1 kHz, frequency response regularity, and transiet distortion (multiple R = 0.77; F = 2.04; df = 5,10). It was concluded that a multivariate statistical tactic, when used with discretion, can be a useful and powerful tool to predict psychoacoustic performance from a knowledge of hearing aid electroacoustic characteristics.

Amplifiers, Electronic↗

Alteration of subcellular and cellular expression patterns of cyclin B1 in renal cell carcinoma is significantly related to clinical progression and survival of patients.

Cyclin B1, identified as a regulator of late cell cycle, is involved in the development and progression of a variety of human malignancies. To clarify the role of cyclin B1 in the pathogenesis and prognosis of renal cell carcinoma (RCC), protein expression was compared with clinicopathological characteristics of patients as well as the long-term survival after surgical therapy. Expression analysis was carried out by immunohistochemistry and tissue microarray analysis. The microarrays that represented the primary tumors, their invasion front and normal peritumoral renal parenchyma contained 753 tissue cores obtained from 251 randomly selected nephrectomy specimens. Immunopositivity within the primary tumors was significantly associated with tumor stage (pT) (p < 0.01), lymph node status (pN) (p < 0.01) as well as the presence of systemic metastatic disease (p = 0.01). Subcellular expression in the cytoplasm of tumor cells significantly correlated with pT (p = 0.02) and pN (p = 0.03). When peritumoral tissue samples exhibited a relative amount of <10% of positively reacting epithelial cells, cyclin B positivity was identified to predict long-term survival of patients in univariate analysis (p < 0.01) whereas borderline significance was observed in multivariate statistical analysis (p = 0.05). Increased intratumoral cyclin B1 positivity and aberrant localization of signals within the cytoplasm of tumor cells is positively correlated with the tendency towards tumor progression, indicating the significant role of cyclin B1 in the development and pathogenesis of RCC. The result of uni- and multivariate statistical analysis suggests the prognostic value of cyclin B1 for RCC patients.

Adult↗

Autofluorescence characterization for the early diagnosis of neoplastic changes in DMBA/TPA-induced mouse skin carcinogenesis.

BACKGROUND AND OBJECTIVE: Squamous cell carcinoma (SCC), the second most common skin cancer, usually remains confined to the epidermis for some time but eventually penetrates the underlying tissues, if left untreated. The non-invasive early detection of the SCC is important for appropriate therapeutic strategies. In this study, we aim to characterize the tissue transformation in DMBA/TPA induced mouse skin tumor model using autofluorescence excitation emission matrix (EEM) in conjunction with a multivariate statistical method for early detection of the neoplastic changes. STUDY DESIGN/MATERIALS AND METHODS: The fluorescence EEM from experimental group (n = 40; DMBA/TPA application), control group (n = 6; acetone application), and the blank group (n = 6; no application of DMBA/TPA or acetone) were measured every week using a spectrofluorometer coupled with a fiber optic bundle. The EEM was recorded at excitation wavelengths from 280 to 460 nm at 10 nm intervals and the fluorescence emission was scanned from 300 to 750 nm. The fluorescence emission characteristics corresponding to different fluorophores were extracted from the EEM and the spectral data were used in a multiple/linear discriminant statistical algorithm. RESULTS: The changes in the fluorescence emission intensity were observed as early as the 1st week of tumor initiation by DMBA. Morphological changes as well as differences in the gross appearance of the skin surface were observed during the entire tumor initiation and promotion period of 15 weeks. The statistical analysis was performed for each excitation wavelength in the EEM and better classification accuracy was obtained for 280 and 410 nm excitations, corresponding to tryptophan and endogenous porphyrins, respectively. The statistical analysis of the combination wavelengths resulted in 11.6% increase in the overall classification accuracy when compared to the highest classification accuracy obtained with single wavelength analysis. CONCLUSION: The intensity ratio mapping using the combination of emission intensities of key fluorophores such as tryptophan, collagen, NADH, and endogenous porphyrins from the measured EEM in conjunction with a simple multivariate statistical analysis can be used as a potential tool for the discrimination of early neoplastic changes with improved classification accuracy. Tryptophan and endogenous porphyrins may be used as biomarkers for the discrimination of early neoplastic changes when single wavelength excitations are used.

9,10-Dimethyl-1,2-benzanthracene↗

Cluster analysis of contaminated sediment data: nodal analysis.

The objective of the present study was to explore the use of multivariate statistical methods as a means to discern relationships between contaminants and biological and/or toxicological effects in a representative data set from the National Status and Trends (NS&T) Program. Data from the National Oceanic and Atmospheric Administration, NS&T Program's Bioeffects Survey of Delaware Bay, USA, were examined using various univariate and multivariate statistical techniques, including cluster analysis. Each approach identified consistent patterns and relationships between the three types of triad data. The analyses also identified factors that bias the interpretation of the data, primarily the presence of rare and unique species and the dependence of species distributions on physical parameters. Sites and species were clustered with the unweighted pair-group method using arithmetic averages clustering with the Jaccard coefficient that clustered species and sites into mutually consistent groupings. Pearson product moment correlation coefficients, normalized for salinity, also were clustered. The most informative analysis, termed nodal analysis, was the intersection of species cluster analysis with site cluster analysis. This technique produced a visual representation of species association patterns among site clusters. Site characteristics, such as salinity and grain size, not contaminant concentrations, appeared to be the primary factors determining species distributions. This suggests the sediment-quality triad needs to use physical parameters as a distinct leg from chemical concentrations to improve sediment-quality assessments in large bodies of water. Because the Delaware Bay system has confounded gradients of contaminants and physical parameters, analyses were repeated with data from northern Chesapeake Bay, USA, with similar results.

Animals↗

Combined survivorship and multivariate analyses of revisions in 799 hip prostheses. A 10- to 20-year review of mechanical loosening.

From 1970 to 1980 cemented metal-on-plastic total hip replacement was performed on 799 hips with primary osteoarthritis using one surgical technique. At the 10- to 20-year follow-up there had been 97 revisions for mechanical loosening. Univariate survivorship analysis showed that an increased risk of revision was associated with male gender, young age at primary THR, the Brunswik and Lubinus snap-fit prostheses with large femoral heads (as compared with the Charnley prosthesis), and varying experience of the surgeon. Multivariate statistical analysis showed a three-fold increased risk of revision for men (p < 0.0001), an increase in relative risk of 1.8 per 10 years younger at surgery (p < 0.0001), a fivefold increase in risk for the Brunswik prosthesis (p < 0.0001) and a twofold increase for the Lubinus prosthesis (p = 0.0067). Inexperience of the surgeon, however, was not validated as a risk factor. The study shows that the true risk factors for revision can be identified accurately by combining univariate survivorship and multivariate statistical analyses.

Aged↗

A metabolomic comparison of urinary changes in type 2 diabetes in mouse, rat, and human.

Type 2 diabetes mellitus is the result of a combination of impaired insulin secretion with reduced insulin sensitivity of target tissues. There are an estimated 150 million affected individuals worldwide, of whom a large proportion remains undiagnosed because of a lack of specific symptoms early in this disorder and inadequate diagnostics. In this study, NMR-based metabolomic analysis in conjunction with multivariate statistics was applied to examine the urinary metabolic changes in two rodent models of type 2 diabetes mellitus as well as unmedicated human sufferers. The db/db mouse and obese Zucker (fa/fa) rat have autosomal recessive defects in the leptin receptor gene, causing type 2 diabetes. 1H-NMR spectra of urine were used in conjunction with uni- and multivariate statistics to identify disease-related metabolic changes in these two animal models and human sufferers. This study demonstrates metabolic similarities between the three species examined, including metabolic responses associated with general systemic stress, changes in the TCA cycle, and perturbations in nucleotide metabolism and in methylamine metabolism. All three species demonstrated profound changes in nucleotide metabolism, including that of N-methylnicotinamide and N-methyl-2-pyridone-5-carboxamide, which may provide unique biomarkers for following type 2 diabetes mellitus progression.

Animals↗

An exploratory analysis of multiple mutation spectra.

The last decade has witnessed a remarkable increase in the number of mutations identified both in human disease-related genes and mutation reporter genes including those in mammalian cells and transgenic animals. This has led to the curation of a number of computerised databases, which make mutation data freely available for analysis. A primary interest of both the clinical researcher and the genetic toxicologist is determination of location and types of mutation within a gene of interest. Collections of mutation data observed for a disease-related gene or, for a gene exposed to a particular chemical, permits discovery of regions of sequence along the gene prone to mutagenesis and may provide clues to the origin of a mutation. The principal tool for visualising the distribution pattern of mutant data along a gene is the mutation spectrum: the distribution and frequency of mutations along a nucleotide sequence. In genetic toxicology, the current wealth of mutation data available allows us to construct many mutation spectra of interest to investigate the mutagenic mechanisms and mutational sites for one or a group of mutagens. Using the multivariate statistical methods principal components analysis (PCA) and cluster analysis (CA) we have tested the ability of these methods to establish the underlying patterns within and between 60 UV-induced, mitomycin C-induced and spontaneous mutations in the supF gene. The spectra were derived from human, monkey and mouse cells including both repair efficient and repair deficient cell lines. We demonstrate and support the successful application of multivariate statistical methods for exploring large sets of mutation spectra to reveal underlying patterns, groupings and similarities. The methods clearly demonstrate how different patterns of spontaneous and UV-induced supF mutation spectra can result from variation in plasmid, culture medium, species origin of cell line and whether mutations arose in vivo or in vitro.

Animals↗

Study of amine composition of botrytized grape berries.

Aliphatic primary and biogenic amines of grape varieties from two vintages were studied. We established that appearance and/or increase of both primary aliphatic and biogenic amines is due to microbiota living in/on grape berries. Aszú, gray rotten grapes infected mainly with Botrytis cinerea, grape berries infected mainly with Penicillium species, and intact grape berries were compared on the basis of amine composition using t-test, analysis of variance, and multivariate statistical analysis (principal component analysis and linear discriminant analysis). The amine composition and amine content of Aszú grapes were significantly different (p < 0.05) from those of intact grapes despite the effect of the vineyards and the vintages. Grape samples coming from the same growing location, intact, Aszú grapes, and grape berries infected mainly with Penicillium species could be separated from each other with multivariate statistical analysis. We distinguished intact, Aszú (noble rotten), and gray rotten berries from each other as well. Evaluating amine values of grape samples independently of the place of origin, the Aszú and green rotten berries could not be differentiated. The varieties and vineyards have affected the amine composition of Aszú grapes, while these effects on intact grapes appeared only slightly.

Biogenic Amines↗

[Analysis on prognostic factors of liver failure in children].

OBJECTIVE: To analyze the prognostic factors of liver failure in children. METHODS: The clinical data of 105 children with liver failure treated in the No. 302 Hospital in the past 17 years were retrospectively analyzed. The related factors were analysed by EXCELL 2000 and STATA 7.0, multivariate statistical analysis was performed by Logistic regression. RESULTS: (1) A total of 72 children died and the mortality was 68.6%. (2) Univariate statistical analysis showed that the factors significantly correlated with death were age, clinical type and stage of liver failure, decrease in prothrombin activity (PTA) and albumin (AIB) level, increase in serum level of total bilirubin (TBIL), appearance of deviation of TBIL and ALT, complications and hepatic encephalopathy. There was no significant difference between boys and girls. (3) There was no significant difference among etiological diagnoses such as HBV infection, Wilson's disease, and unknown pathogeny. (4) Multivariate statistical analysis showed that PTA (P = 0.000) and TBIL (P = 0.029) were independent risk factors of mortality of the children. CONCLUSION: The prognosis of liver failure in children is poor and mortality is high. PTA and TBIL might be useful for indicating prompt diagnosis and treatment to improve survival rate of the children with liver failure.

Adolescent↗

Assessing impacts of typhoons and the Chi-Chi earthquake on Chenyulan watershed landscape pattern in central Taiwan using landscape metrics.

The Chi-Chi earthquake (ML=7.3) occurred in the central part of Taiwan on September 21, 1999. After the earthquake, typhoons Xangsane and Toraji produced heavy rainfall that fell across the eastern and central parts of Taiwan on November 2000 and July 2001. This study uses remote sensing data, landscape metrics, multivariate statistical analysis, and spatial autocorrelation to assess how earthquake and typhoons affect landscape patterns. It addresses variations of the Chenyulan watershed in Nantou County, near the earthquake's epicenter and crossed by Typhoon Toraji. The subsequent disturbances have gradually changed landscape of the Chenyulan watershed. Disturbances of various types, sizes, and intensities, following various tracks, have various effects on the landscape patterns and variations of the Chenyulan watershed. The landscape metrics that are obtained by multivariate statistical analyses showed that the disturbances produced variously fragmented patches, interspersed with other patches and isolated from patches of the same type across the entire Chenyulan watershed. The disturbances also affected the isolation, size, and shape-complexity of patches at the landscape and class levels. The disturbances at the class level more strongly affected spatial variations in the landscape as well as patterns of grasslands and bare land, than variations in the watershed farmland and forest. Moreover, the earthquake with high magnitude was a starter to create these landscape variations in space in the Chenyulan watershed. The cumulative impacts of the disturbances on the watershed landscape pattern had existed, especially landslides and grassland in the study area, but were not always evident in space and time in landscape and other class levels.

Conservation of Natural Resources↗

Crossover design in pharmacy research.

OBJECTIVE: Reports of pharmacy research using crossover designs were reviewed to determine if the studies adequately consider interaction effects and use appropriate statistical analyses. DATA SOURCES: All crossover studies published in DICP, The Annals of Pharmacotherapy during 1988 and 1989 were analyzed. STUDY SELECTION: Reports of crossover studies were included only if at least two treatments were applied in a different order to two or more groups of subjects. DATA EXTRACTION: The principal characteristics of crossover studies and the critical design variables were listed and each study analyzed according to these variables. The critical design variables included consideration of period, sequence, and carryover effects as well as the presentation of data by groups and the use of multivariate statistical analysis. The analysis was conducted independently by each author and conflicts were discussed until consensus was obtained. RESULTS: A total of 11 crossover studies were identified: 6 were bioavailability trials, 3 were treatment comparisons, and 2 had multiple objectives. The possibility of period, sequence, or carryover effects was less with bioavailability studies than with treatment comparisons. Only 1 study presented data by group and only 4 studies used multivariate analysis. CONCLUSIONS: The crossover design appears more appropriate for bioavailability trials than for treatment trials in pharmacy research. Analysis of data from crossover designs could be improved by presenting the data for each treatment group and using multivariate statistical analysis.

Analysis of Variance↗

Predicting functional capacity outcome 12 months after hospitalized injury.

BACKGROUND: There is a recognized need to move from mortality to morbidity outcome predictions following traumatic injury. However, there are few morbidity outcome prediction scoring methods and these fail to incorporate important comorbidities or cofactors. This study aims to develop and evaluate a method that includes such variables. METHODS: This was a consecutive case series registered in the Queensland Trauma Registry that consented to a prospective 12-month telephone conducted follow-up study. A multivariable statistical model was developed relating Trauma Registry data to trichotomized 12-month post-injury outcome (categories: no limitations, minor limitations and major limitations). Cross-validation techniques using successive single hold-out samples were then conducted to evaluate the model's predictive capabilities. RESULTS: In total, 619 participated, with 337 (54%) experiencing no limitations, 101 (16%) experiencing minor limitations and 181 (29%) experiencing major limitations 12 months after injury. The final parsimonious multivariable statistical model included whether the injury was in the lower extremity body region, injury severity, age, length of hospital stay, pulse at admission and whether the participant was admitted to an intensive care unit. This model explained 21% of the variability in post-injury outcome. Predictively, 64% of those with no limitations, 18% of those with minor limitations and 37% of those with major limitations were correctly identified. CONCLUSION: Although carefully developed, this statistical model lacks the predictive power necessary for its use as a basis of a useful prognostic tool. Further research is required to identify variables other than those routinely used in the Trauma Registry to develop a model with the necessary predictive utility.

Adolescent↗