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 523 records · Page 29Linked to original sources
PubMed1988

A statistical approach to the discrimination of the cranial form.

In a study of lateral cephalographic dimensions, their multivariate statistical analysis was shown to discriminate between patients with gross cranial anomalies and controls exhibiting no abnormal morphology. Although the degree of discrimination depended upon the group of dimensions included in the analysis, discrimination was more consistent than when compared using univariate statistical techniques. As cephalographic dimensions combine both size and shape parameters together, however, the interpretation of such contrasts must await more specific analytic techniques development.

Cephalometry↗
PubMed2003

Predicting career decisions in primary care medicine: a theoretical analysis.

Entering the 1960s, more than half of the medical doctors in the United States were family physicians, pediatricians, or general internists. Today, about one-third of all U.S. physicians are primary care practitioners. Although opinions vary on the optimal ratio of primary care to specialty physicians, in the mid-1990s, the consensus among leaders in medicine was that more primary care physicians would be needed to ensure access to quality care. The target output of graduates was set for a minimum of 50% primary care physicians, and medical school admission committees responded. The present study examines research related to career decision making in primary care medicine. We address career decision making in primary care with the expectation that selection of a medical residency is based on multiple factors, and multivariate statistical techniques comprise the most appropriate statistical procedure for developing predictive models of medical student residency choice. Additional multivariate studies for simultaneous analysis of multiple dependent and multiple independent variables are needed to determine whether health policy planners and medical schools should continue to address the distribution of primary care physicians through medical school admissions. Further to enabling prediction, researchers must renew efforts to base investigations on theoretical models, summarizing and organizing previous research, and providing one another with means to focus future studies while building on previous work.

Career Choice↗
PubMed2000

Comparing Landslide Maps: A Case Study in the Upper Tiber River Basin, Central Italy.

/ The preparation of landslide maps is an important step in any landslide hazard assessment. Landslides maps are prepared around the world, but little effort is made to assess their reliability, outline their main characteristics, and pinpoint their limitations. In order to redress this imbalance, the results of a long-term research project in the Upper Tiber River basin in central Italy are used to compare reconnaissance and detailed landslide inventory maps, statistical and geomorphologically based density maps, and landslide hazard maps obtained by multivariate statistical modeling. An attempt is made to discuss advantages and limitations of the available maps, outlining possible applications for decision-makers, land developers, and environmental and civil defence agencies. The Tiber experiment has confirmed that landslides can be cost-effectively mapped by interpreting aerial photographs coupled with field surveys and that errors and uncertainties associated with the inventory can be quantified. The experiment has shown that GIS makes it easy to prepare landslide density maps and facilitates the production of statistically based landslide hazard models. The former supply an overview of the distribution of landslides that is easily comprehended but do not provide insight on the causes of instability. The latter, giving insight into the causes of instability, are diagnostically powerful, but are difficult to prepare and exploit.

Journal Article↗
PubMed2006

Impact of pediatric epilepsy on Indian families: influence of psychopathology and seizure related variables.

The impact of epilepsy on families has been little studied in the developing countries, where it is the most common neurological disorder among children. In Vellore, India, the impact on 132 families who had a child with epilepsy was rated with the Impact of Pediatric Epilepsy on the Family Scale (IPES). An adverse impact was experienced by 42% of families. Multivariate statistical analysis revealed four factors that were significantly associated with high impact: fewer years since diagnosis (OR=0.81, 95% CI=0.71-0.93), fewer months since last seizure (OR=0.58, 95% CI=0.39-0.87), treatment with multiple antiepileptic drugs (OR=4.34, 95% CI=1.22-15.52), and increased behavior problem scores on the Child Behavior Checklist (OR=1.10, 95% CI=1.05-1.14). Factor analysis of the IPES was also conducted as a comparison with earlier findings in a developed country. We suggest that early monotherapy should be employed whenever possible and that early recognition and treatment of associated psychological problems may help to reduce the burden on families.

Adaptation, Psychological↗
PubMed1997

Short-term keratometric variation in the human eye.

Previous studies of corneal and keratometric variation used statistical methods that were not entirely satisfactory. For the first time, proper multivariate statistical methods are applied to evaluate short-term keratometric variation in human eyes. Keratometric variation is represented graphically by means of stereo-pair scatter plots, ellipsoidal confidence regions for mean dioptric power, and meridional profiles of variation. There is great variability in the keratometric variation displayed by different subjects, although most subjects exhibit greatest variation in the vertical meridian of the eye on most of the measuring occasions. Variance-covariance matrices based on vector h are given. In some cases keratometric variation approaches neutral uniform variation. In many of the subjects, mean keratometric measurements change from morning to afternoon, usually showing an increase in curvature later in the day. Physical activity may increase keratometric variation and mean curvature.

Adult↗
PubMed2006

Surgical volume is related to the rate of positive surgical margins at radical prostatectomy in European patients.

OBJECTIVE: To assess the association between surgical volume (SV) and the rate of positive surgical margins (PSM) after radical prostatectomy (RP) in a large single-institution European cohort of patients. PATIENTS AND METHODS: In all, 2402 men had a RP by a group of 11 surgeons, all of whom were trained by the surgeon with the highest SV; all surgeons used the same surgical technique. Variables assessed before RP were prostate-specific antigen (PSA) level, clinical stage and biopsy Gleason sum; variables assessed after RP were PSA level, extracapsular extension, seminal vesicle invasion, lymph node invasion and pathological Gleason sum. These were used to predict the rate of PSM in models before or after RP. Multivariate models were complemented with SV to test its independent and multivariate statistical significance and to quantify its impact on the model's overall (and 200 bootstrap-corrected) predictive accuracy. RESULTS: The mean (range) SV was 201 (1-1293) RPs; the mean (median, range) rate of PSM was 20.2 (21.4, 0-32.9)%. In multivariate models, SV was a highly statistically significant independent predictor of PSM (P < 0.001) and increased the predictive accuracy in multivariate models both before (2.0%) and after RP (1.5%, both P < 0.001). However, when the surgeon with the highest SV, who contributed to 1293 cases, was removed from the analyses, the multivariate independent prediction and the gains in predictive accuracy related to adding SV, disappeared in the models both before (P = 0.9, accuracy gain 0.1%) and after (P = 0.4, accuracy gain - 0.3%) RP. CONCLUSIONS: These results indicate that patients treated by surgeons with a very high volume can expect to have a significantly lower rate of PSM, after accounting for clinical and pathological case-mix differences. However, SV is not a predictor of PSM when analyses are restricted to intermediate- and low-volume surgeons.

Clinical Competence↗
PubMed1988

Applications of statistical analysis in diagnostic histopathology and cytopathology.

Corresponding to the rapid increase in the amount of data available for use in clinical diagnoses, there is an increased need for procedures that can provide the diagnostician with meaningful statistical summaries of data and with statements concerning the statistical significance associated with a diagnostic evaluation. It has been demonstrated that multivariate statistical assessment of clinical material can provide consistent, reliable and highly sensitive diagnostic clues, even in instances in which trained personnel are unable to see any change. Several examples of applications of statistical analyses in diagnostic cytology and histopathology are given in this paper. The examples were chosen to be illustrative of the different types of problems for which statistical analyses have been found useful. These problems differ with respect to the extent of the statistical methods thus far developed and the difficulty involved in developing further analyses. For many problems, appropriate statistical analyses are readily available; other problems require definition of custom-made test statistics and, in some cases, also definition of new statistical distributions. The problems discussed here are only a small sample of the existing problems, but they provide at least an indication of the scope of the role that statistics plays in cytopathologic and histopathologic diagnosis.

Cytological Techniques↗
PubMed1996

[Risk factors of postoperative proliferative vitreoretinopathy in giant tears].

BACKGROUND: In eyes with giant retinal tears, the rate of severe postoperative PVR and failure to permanently reattach the retina remains especially high in spite of technical advances in surgical management. This study was conducted to elucidate the clinical and surgical risk factors for severe postoperative PVR in such eyes. PATIENTS AND METHODS: We reviewed the records of 68 consecutive patients (69 eyes) with giant retinal tears. Univariate and multivariate statistical analyses were used to evaluate the risk factors for severe PVR. RESULTS: The rate of severe postoperative and failure to permanently reattach the retina were 43.5% (30/69 eyes). It was influenced at a statistically significant level by two independent risk factors: 1) the presence and severity of preoperative PVR and 2) the use of cryotreatment as compared to the use of ALP treatment. Severe postoperative PVR occurred in 63.6% (14/22 eyes) of eyes managed with cryotreatment versus 31.1% (14/45 eyes) of eyes managed with ALP treatment (P < 0.02). The rate of severe postoperative PVR was 64% (16/25 eyes) in eyes with grade C-D PVR preoperatively versus 31.8% (14/44 eyes) in eyes with no PVR or grade B PVR preoperatively (P < 0.01). In eyes managed with the use of ALP treatment the rate of severe postoperative PVR remained influenced at a statistically significant level (P < 0.005) by the presence of grade C-D PVR preoperatively. Grade C-D PVR was significantly more frequent preoperatively in patients with visual symptoms of 3 week-duration or more at initial examination (23/24 patients, 95.8%), than in those with visul symptoms under 3 week-duration (8/41 patients, 19.5%) (P: 0.0005). CONCLUSION: The results suggest that the high incidence of severe postoperative PVR in giant retinal tears may be decreased by 1) early management before the occurrence of PVR and 2) the use of argon laser photocoagulation rather than cryotreatment as the method of creating a chorioretinal scar.

Adult↗
PubMed2004

Dentoalveolar reconstructive procedures as a risk factor for implant failure.

PURPOSE: Dentoalveolar reconstructive procedures (DRPs) are commonly used to enhance deficient implant recipient sites. It is unclear, however, if these procedures are independent risk factors for implant failure. The specific aim of this study was to assess the use of DRPs as a risk factor for implant failure. MATERIALS AND METHODS: To address the research aim, we used a retrospective cohort study design and a study sample derived from the population of patients who had one or more implants inserted between May 1992 and July 2000. The main predictor variable was the use of DRPs, such as external or internal sinus lifts, onlay bone grafting, or guided-tissue regeneration with autogenous bone grafts or autogenous bone graft substitutes, to enhance the recipient sites before implant insertion. The major outcome variable was implant failure. Appropriate descriptive, bivariate, and multivariate statistics were computed. RESULTS: The study sample was composed of 677 patients who had 677 implants randomly selected (1 implant per patient) for analysis. The overall 1- and 5-year implant survival rates were 95.2% and 90.2%, respectively. Bivariate analyses revealed 4 factors statistically or nearly statistically associated with implant failure: current tobacco use, implant length, implant staging, and type of prosthesis (P <.15). In the multivariate model, patients with DRPs did not have a statistically significant increased risk for implant failure (odds ratio = 1.4, P =.3). CONCLUSIONS: The results of this study suggest that the use of DRPs to reconstruct deficient implant recipient sites was not an independent risk factor for implant failure in either the unadjusted or adjusted analyses.

Adolescent↗
PubMed2005

Influence of air-sea fluxes on chlorine isotopic composition of ocean water: implications for constancy in delta37Cl--a statistical inference.

The behaviors of chlorine isotopes in relation to air-sea flux variables have been investigated through multivariate statistical analyses (MSA). The MSA technique provides an approach to reduce the data set and was applied to a set of 7 air-sea flux variables to supplement and describe the variation in chlorine isotopic compositions (delta37Cl) of ocean water. The variation in delta37Cl values of surface ocean water from 51 stations in 4 major world oceans--the Pacific, Atlantic, Indian and the Southern Ocean has been observed from -0.76 to +0.74 per thousand (av. 0.039+/-0.04 per thousand). The observed delta37Cl values show basic homogeneity and indicate that the air-sea fluxes act differently in different oceanic regions and help to maintain the balance between delta37Cl values of the world oceans. The study showed that it is possible to model the behavior of chlorine isotopes to the extent of 38-73% for different geographical regions. The models offered here are purely statistical in nature; however, the relationships uncovered by these models extend our understanding of the constancy in delta37Cl of ocean water in relation to air-sea flux variables.

Air↗
PubMed2005

Solving the protein sequence metric problem.

Biological sequences are composed of long strings of alphabetic letters rather than arrays of numerical values. Lack of a natural underlying metric for comparing such alphabetic data significantly inhibits sophisticated statistical analyses of sequences, modeling structural and functional aspects of proteins, and related problems. Herein, we use multivariate statistical analyses on almost 500 amino acid attributes to produce a small set of highly interpretable numeric patterns of amino acid variability. These high-dimensional attribute data are summarized by five multidimensional patterns of attribute covariation that reflect polarity, secondary structure, molecular volume, codon diversity, and electrostatic charge. Numerical scores for each amino acid then transform amino acid sequences for statistical analyses. Relationships between transformed data and amino acid substitution matrices show significant associations for polarity and codon diversity scores. Transformed alphabetic data are used in analysis of variance and discriminant analysis to study DNA binding in the basic helix-loop-helix proteins. The transformed scores offer a general solution for analyzing a wide variety of sequence analysis problems.

Amino Acid Sequence↗
PubMed2004

Recognition and separation of single particles with size variation by statistical analysis of their images.

Macromolecules may occupy conformations with structural differences that cannot be resolved biochemically. The separation of mixed molecular populations is a pressing problem in single-particle analysis. Until recently, the task of distinguishing small structural variations was intractable, but developments in cryo-electron microscopy hardware and software now make it possible to address this problem. We have developed a general strategy for recognizing and separating structures of variable size from cryo-electron micrographs of single particles. The method uses a combination of statistical analysis and projection matching to multiple models. Identification of size variations by multivariate statistical analysis was used to do an initial separation of the data and generate starting models by angular reconstitution. Refinement was performed using alternate projection matching to models and angular reconstitution of the separated subsets. The approach has been successful at intermediate resolution, taking it within range of resolving secondary structure elements of proteins. Analysis of simulated and real data sets is used to illustrate the problems encountered and possible solutions. The strategy developed was used to resolve the structures of two forms of a small heat shock protein (Hsp26) that vary slightly in diameter and subunit packing.

Computer Simulation↗
PubMed1996

Detecting Discrimination: Analyzing Racial Disparities in Public Contracting

In City of Richmond v. J. A. Croson Co. (1989), the Supreme Court established strict scrutiny as the standard applicable to affirmative action programs which set aside quotas of public contracts for minority-owned businesses, and Aderand v. Pena (1995) extended the strict scrutiny standard to federal programs. Although the requirements of these decisions clearly require multivariate statistical analysis, most "disparity studies" have used a univariate comparison between the expected and the observed shares of contracts going to minority-owned firms. We examine four statistical methods-ordinary least square multiple regression, logit and tobit models, and a multivariate procedure for comparing expected and observed outcomes. Because no data are presently available at the level of specificity required by Croson, we constructed synthetic data sets to represent typical variations among large U.S. cities. Applying the statistical methods to each data set allows evaluation of the extent to which each method is able to both remove spurious and detect valid estimates of racial disparity when relevant control variables are added. Findings: (a) All four models removed apparent disparities which, although significant in univariate analysis, were known to be spurious. (b) Tobit and logit models, whose underlying assumptions better fit the nature of public contracting data, provided more accurate and more sensitive estimates than OLS regression. (c) Comparison of expected and observed outcomes within categories of control variables yielded results very similar to logit and tobit models and, because of the nature of the comparison specified in Croson, produced slightly more sensitive probability estimates.

Journal Article↗
PubMed1996

Distribution of astigmatism in the adult population.

We have quantified statistically the astigmatic frequency distribution. Vectorial analysis was used, as it enables formal multivariate statistical techniques to be applied to astigmatic data, allowing the simultaneous inclusion of both modulus and axis in the analytical procedure. These methods were applied to population data for each of total, corneal, and residual astigmatism from a sample of 198 adults. Right and left eyes were analyzed separately. All the distributions were found to depart significantly from a normal distribution. All the distributions were significantly leptokurtic (p < 0.005), and the distributions of total right eye, corneal right eye, and residual left eye astigmatism were also found to be significantly skewed (p < 0.05). Significant mild correlations were found between total and corneal astigmatism (p < 0.05). These findings add to the database of knowledge of astigmatic refractive error and may be of interest to those investigating refractive-error development.

Adolescent↗
PubMed2000

Theoretical calculation and prediction of P-glycoprotein-interacting drugs using MolSurf parametrization and PLS statistics.

A method for the modelling and prediction of P-glycoprotein-associated ATPase activity using theoretically computed molecular descriptors and multivariate statistics has been investigated using 22 diverse drug-like compounds. The program MolSurf was used to compute theoretical molecular descriptors related to physicochemical properties such as lipophilicity, polarity, polarizability and hydrogen bonding. The multivariate partial least squares projections to latent structures (PLS) method was used to delineate the relationship between the P-glycoprotein-associated ATPase activity and the theoretically computed molecular descriptors. The PLS analysis of the entire data set, with the exclusion of tamoxifen, resulted in one significant PLS component according to cross-validation with R(2)=0.718, Q(2)=0. 695, S.D.=0.475, F=48.37, RMSE(tr)=0.452, p<0.001. Properties associated with the size of the molecular surface, polarizability and hydrogen bonding had the largest impact on the P-glycoprotein-associated ATPase activity. All these properties should be high to promote high ATPase activity.

ATP Binding Cassette Transporter, Subfamily B, Mem↗
PubMed2006

Using data mining to explore complex clinical decisions: A study of hospitalization after a suicide attempt.

BACKGROUND: Medical education is moving toward developing guidelines using the evidence-based approach; however, controlled data are missing for answering complex treatment decisions such as those made during suicide attempts. A new set of statistical techniques called data mining (or machine learning) is being used by different industries to explore complex databases and can be used to explore large clinical databases. METHOD: The study goal was to reanalyze, using data mining techniques, a published study of which variables predicted psychiatrists' decisions to hospitalize in 509 suicide attempters over the age of 18 years who were assessed in the emergency department. Patients were recruited for the study between 1996 and 1998. Traditional multivariate statistics were compared with data mining techniques to determine variables predicting hospitalization. RESULTS: Five analyses done by psychiatric researchers using traditional statistical techniques classified 72% to 88% of patients correctly. The model developed by researchers with no psychiatric knowledge and employing data mining techniques used 5 variables (drug consumption during the attempt, relief that the attempt was not effective, lack of family support, being a housewife, and family history of suicide attempts) and classified 99% of patients correctly (99% sensitivity and 100% specificity). CONCLUSIONS: This reanalysis of a published study fundamentally tries to make the point that these new multivariate techniques, called data mining, can be used to study large clinical databases in psychiatry. Data mining techniques may be used to explore important treatment questions and outcomes in large clinical databases and to help develop guidelines for problems where controlled data are difficult to obtain. New opportunities for good clinical research may be developed by using data mining analyses.

Adult↗
PubMed2000

Tissue factor expression in human colorectal carcinoma: correlation with hepatic metastasis and impact on prognosis.

BACKGROUND: It has been suggested that tissue factor (TF) plays an important role in tumor metastasis. Its expression in sarcoma cells was reported to up-regulate the vascular endothelial growth factor (VEGF) gene and thereby enhance tumor angiogenesis, which is essential to tumor metastasis. Although many malignant tumors have been reported to express this protein constitutively, recent clinical studies have focused mainly on the correlations among TF expression, tumor progression, and histologic grade. Therefore, to address the role of TF and the underlying mechanism of hematogenous metastasis of colorectal carcinoma, the authors analyzed the correlations among TF expression, hepatic metastasis, and VEGF gene expression in surgical specimens. Furthermore, they analyzed the prognostic significance of TF expression with respect to overall patient survival. METHODS: Expression of TF and VEGF genes in 67 advanced colorectal carcinoma specimens was studied by immunohistochemistry and Northern blot analysis, respectively. The correlations among TF expression, hepatic metastasis, and other factors were analyzed with univariate and multivariate statistics. Survival rates were calculated using the Kaplan-Meier method. RESULTS: Univariate and multivariate analyses showed TF expression to be a significant (P = 0.0001) and independent risk factor for hepatic metastasis, whereas a weak but insignificant correlation was observed between TF and VEGF gene expression. The outcomes in the TF positive group were significantly worse in all cases (P = 0.0001) and in the cases without synchronous hepatic metastasis (P = 0.0156). CONCLUSIONS: Although the precise mechanisms are unknown, TF expression is a suitable indicator of both hepatic metastasis and prognosis for colorectal carcinoma patients.

Aged↗
PubMed1996

Quantification of intensity variations in functional MR images using rotated principal components.

In functional MRI (fMRI), the changes in cerebral haemodynamics related to stimulated neural brain activity are measured using standard clinical MR equipment. Small intensity variations in fMRI data have to be detected and distinguished from non-neural effects by careful image analysis. Based on multivariate statistics we describe an algorithm involving oblique rotation of the most significant principal components for an estimation of the temporal and spatial distribution of the stimulated neural activity over the whole image matrix. This algorithm takes advantage of strong local signal variations. A mathematical phantom was designed to generate simulated data for the evaluation of the method. In simulation experiments, the potential of the method to quantify small intensity changes, especially when processing data sets containing multiple sources of signal variations, was demonstrated. In vivo fMRI data collected in both visual and motor stimulation experiments were analysed, showing a proper location of the activated cortical regions within well known neural centres and an accurate extraction of the activation time profile. The suggested method yields accurate absolute quantification of in vivo brain activity without the need of extensive prior knowledge and user interaction.

Algorithms↗