Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “canonical correlation analysis”

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 37 records · Page 2Linked to original sources
PubMed2001

Detection of neural activity in functional MRI using canonical correlation analysis.

A novel method for detecting neural activity in functional magnetic resonance imaging (fMRI) data is introduced. It is based on canonical correlation analysis (CCA), which is a multivariate extension of the univariate correlation analysis widely used in fMRI. To detect homogeneous regions of activity, the method combines a subspace modeling of the hemodynamic response and the use of spatial relationships. The spatial correlation that undoubtedly exists in fMR images is completely ignored when univariate methods such as as t-tests, F-tests, and ordinary correlation analysis are used. Such methods are for this reason very sensitive to noise, leading to difficulties in detecting activation and significant contributions of false activations. In addition, the proposed CCA method also makes it possible to detect activated brain regions based not only on thresholding a correlation coefficient, but also on physiological parameters such as temporal shape and delay of the hemodynamic response. Excellent performance on real fMRI data is demonstrated. Magn Reson Med 45:323-330, 2001.

Brain↗
PubMed2003

Generalized covariance-adjusted canonical correlation analysis with application to psychiatry.

The lack of control over covariates in practice motivates the need for their adjustment when measuring the degree of association between two sets of variables, for which canonical correlation is traditionally used. In most studies however, there is also a lack of control over the attributes of responses for the sets of variables of interest. In particular, a portion of the response variable may be continuous and the other discrete. For such settings, the traditional partial canonical correlation approach is restrictive, since a covariate-adjustment for a set of continuous variables is assumed. By ignoring the assumption of continuous variates and proceeding with a partial canonical correlation analysis in the presence of continuous and discrete variates, results in canonical correlation estimates that are not consistent. In this paper we generalize the traditional partial canonical correlation approach to covariate-adjustment by allowing the response variables to contain continuous, as well as discrete, variates. The methodology is illustrated with a psychiatric application for examining which sleep variables relate to which depressive symptoms, as measured by commonly used constructs that presents with both continuous and discrete outcomes.

Analysis of Variance↗
PubMed2005

Conducting and interpreting canonical correlation analysis in personality research: a user-friendly primer.

The purpose of this article is to reduce potential statistical barriers and open doors to canonical correlation analysis (CCA) for applied behavioral scientists and personality researchers. CCA was selected for discussion, as it represents the highest level of the general linear model (GLM) and can be rather easily conceptualized as a method closely linked with the more widely understood Pearson r correlation coefficient. An understanding of CCA can lead to a more global appreciation of other univariate and multivariate methods in the GLM. We attempt to demonstrate CCA with basic language, using technical terminology only when necessary for understanding and use of the method. We present an entire example of a CCA analysis using SPSS (Version 11.0) with personality data.

Analysis of Variance↗
PubMed2005

Exploring cancer register data to find risk factors for recurrence of breast cancer--application of Canonical Correlation Analysis.

BACKGROUND: A common approach in exploring register data is to find relationships between outcomes and predictors by using multiple regression analysis (MRA). If there is more than one outcome variable, the analysis must then be repeated, and the results combined in some arbitrary fashion. In contrast, Canonical Correlation Analysis (CCA) has the ability to analyze multiple outcomes at the same time. One essential outcome after breast cancer treatment is recurrence of the disease. It is important to understand the relationship between different predictors and recurrence, including the time interval until recurrence. This study describes the application of CCA to find important predictors for two different outcomes for breast cancer patients, loco-regional recurrence and occurrence of distant metastasis and to decrease the number of variables in the sets of predictors and outcomes without decreasing the predictive strength of the model. METHODS: Data for 637 malignant breast cancer patients admitted in the south-east region of Sweden were analyzed. By using CCA and looking at the structure coefficients (loadings), relationships between tumor specifications and the two outcomes during different time intervals were analyzed and a correlation model was built. RESULTS: The analysis successfully detected known predictors for breast cancer recurrence during the first two years and distant metastasis 2-4 years after diagnosis. Nottingham Histologic Grading (NHG) was the most important predictor, while age of the patient at the time of diagnosis was not an important predictor. CONCLUSION: In cancer registers with high dimensionality, CCA can be used for identifying the importance of risk factors for breast cancer recurrence. This technique can result in a model ready for further processing by data mining methods through reducing the number of variables to important ones.

Adult↗
PubMed1979

A canonical correlation analysis of the Alcohol-Use Inventory and the Human Service Scale.

The responses of 312 persons with alcoholism to the Alcohol-Use Inventory and Human Service Scale were subjected to canonical correlation analysis. Results indicate that the relationship between alcohol-use constructs and psychological need satisfaction can be explained by two axes: a personal security--social dimension and a personal stress--environmental dimension. Microanalysis of the variates indicated that emotional need satisfaction was differentially influenced by social and physiological variables.

Adolescent↗
PubMed2006

Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram.

The electroencephalogram (EEG) is often contaminated by muscle artifacts. In this paper, a new method for muscle artifact removal in EEG is presented, based on canonical correlation analysis (CCA) as a blind source separation (BSS) technique. This method is demonstrated on a synthetic data set. The method outperformed a low-pass filter with different cutoff frequencies and an independent component analysis (ICA)-based technique for muscle artifact removal. In addition, the method is applied on a real ictal EEG recording contaminated with muscle artifacts. The proposed method removed successfully the muscle artifact without altering the recorded underlying ictal activity.

Action Potentials↗
PubMed2004

Life skills and subjective well-being of people with disabilities: a canonical correlation analysis.

This study examined the canonical relationships between a set of life skill variables and a set of subjective well-being variables among a national sample of vocational rehabilitation clients in the USA. Self-direction, work tolerance, general employability, and self-care were related to physical, family and social, and financial well-being. This analysis also found that communication skill is related to family and social well-being, while psychological well-being is not related to any life skills in the set. The results showed that vocational rehabilitation services aimed to improve life functioning will lead to an improvement in subjective quality of life.

Adult↗
PubMed1979

Canonical correlation analysis: potential for environmental health planning.

There is a challenging need to identify the relationships between environmental quality and health status. It may be especially important to be able to isolate key variables which can be consolidated into a few indices of environmental conditions as they are related to health. Such indices might be used to identifying associations among groups of variables, such as specific geographic area. The indices may also provide insights into environmental health relationships which are worthy of further epidemiological investigation. Canonical correlation analysis is a multivariate statistical technique which provides a means of identifying associations among groups of variables, such as health and environmental measures. The technique can produce weighted indices of environmental conditions as they are related to health within a city or region. This paper describes what canonical correlation is, and outlines how it might be used for these purposes. An illustrative application based on data collected for Philadelphia, Pennsylvania is also presented.

Aged↗
PubMed1998

Comparison of partial least-square method and canonical correlation analysis in a quantitative structure-retention relationship study.

The retention of 7 monotetrazolium and 9 ditetrazolium salts was determined on alumina and reversed-phase (RP) alumina layers using n-hexane-1-propanol and water-1-propanol mixtures as eluents. The retention capacity and the specific surface area of solutes in contact with the stationary phases were calculated. The relationship between retention characteristics and physicochemical parameters of solutes was elucidated by canonical correlation analysis and partial least-square regression analysis. Both methods found significant relationships between the chromatographic and physicochemical parameters, however, the results were different according to the method applied. Calculations suggested that the retention on both alumina and RP alumina layers is of mixed character, hydrophobic, electronic and steric parameters are equally involved in the retention.

1-Propanol↗
PubMed1995

Contributions of facial morphology, age, and gender to EMG activity under biting and resting conditions: a canonical correlation analysis.

Theoretical studies suggest that facial morphology may confer a mechanical advantage to particular individuals during force production, but not during rest. However, prior studies on the relationship between facial morphology and EMG suffer from various methodological limitations. We examined the hypothesis that facial morphology variables contribute significantly and meaningfully to the variance in masticatory muscle EMG when subjects produce specific levels of interocclusal force, but not when subjects are at rest. Measures of facial morphology included gonial angle, ramus height, and maxillary height, as determined from lateral cephalograms. EMG data were obtained from surface electrodes placed on masseter and temporalis sites. Subjects (N = 96) sat in a darkened, sound-attenuated room while they watched a seven-minute segment of a movie. EMG activity obtained during the last two minutes was used as a baseline period. Using the central incisors, subjects then provided five different force levels ranging from 6.5 to 48 lb in random order on a bite-force device while EMG data were collected. A canonical correlation analysis, performed on the set of predictor variables (age, gender, and facial morphology measurements) and the set of criterion variables (EMG data), showed a significant canonical correlation between the two variable sets while biting, but not at rest. Age, but not the facial morphology variables, was highly related to the canonical variate.(ABSTRACT TRUNCATED AT 250 WORDS)

Adolescent↗
PubMed1995

Accounting for variance shared by measures of personality and stress-related variables: a canonical correlation analysis.

Correlations were computed among the five personality scales of the NEO Personality Inventory, two measures derived from the Hassles Scale, and eight ways of dealing with stress measured by the Ways of Coping Questionnaire. Subjects were 66 undergraduate psychology students. Canonical correlation analysis suggests that multivariate procedures treating the data set as a whole can detect underlying patterns obscured by large sampling errors at lower levels of analysis.

Adaptation, Psychological↗
PubMed2006

Canonical correlation analysis of factors involved in the occurrence of peptic ulcers.

The impact of risk factors on the development of peptic ulcers has been shown to vary among different populations. We sought to establish a correlation between these factors and their involvement in the occurrence of peptic ulcers for which a canonical correlation analysis was applied. We included 7,014 patient records (48.6% women, 18.4% duodenal ulcer [DU], 4.6% gastric ulcer [GU]) of those underwent upper gastroendoscopy for the last 5 years. The variables measured are endoscopic findings (DU, GU, antral gastritis, erosive gastritis, pangastritis, pyloric deformity, bulbar deformity, bleeding, atrophy, Barret esophagus and gastric polyp) and risk factors (age, gender, Helicobacter pylori infection, smoking, alcohol, and nonsteroidal anti-inflammatory drugs [NSAIDs] and aspirin intake). We found that DU had significant positive correlation with bulbar deformity (P=2.6 x 10(-23)), pyloric deformity (P=2.6 x 10(-23)), gender (P=2.6 x 10(-23)), H. pylori (P=1.4 x 10(-15)), bleeding (P=6.9 x 10(-15)), smoking (P=1.4 x 10(-7)), aspirin use (P=1.1 x 10(-4)), alcohol intake (P=7.7 x 10(-4)), and NSAIDs (P=.01). GU had a significantly positive correlation with pyloric deformity (P=1,6 x 10(-15)), age (P=2.6 x 10(-14)), bleeding (P=3.7 x 10(-8)), gender (P=1.3 x 10(-7)), aspirin use (P=1.1 x 10(-6)), bulbar deformity (P=7.4 x 10(-4)), alcohol intake (P=.03), smoking (P=.04), and Barret esophagus (P=.03). The level of significance was much higher in some variables with DU than with GU and the correlations with GU in spite of being highly significant the majority, were small in magnitude. In conclusion, Turkish patients with the following endoscopic findings bulbar deformity and pyloric deformity are high-risk patients for peptic ulcers with the risk of the occurrence of DU being higher than that of GU. Factors such as H. pylori, smoking, alcohol use, and NSAIDs use (listed in a decreasing manner) are risk factors that have significant impact on the occurrence of DU; aspirin has a significant impact on both DU and GU.

Adult↗
PubMed2005

Canonical correlation analysis for data reduction in data mining applied to predictive models for breast cancer recurrence.

Data mining methods can be used for extracting specific medical knowledge such as important predictors for recurrence of breast cancer in pertinent data material. However, when there is a huge quantity of variables in the data material it is first necessary to identify and select important variables. In this study we present a preprocessing method for selecting important variables in a dataset prior to building a predictive model.In the dataset, data from 5787 female patients were analysed. To cover more predictors and obtain a better assessment of the outcomes, data were retrieved from three different registers: the regional breast cancer, tumour markers, and cause of death registers. After retrieving information about selected predictors and outcomes from the different registers, the raw data were cleaned by running different logical rules. Thereafter, domain experts selected predictors assumed to be important regarding recurrence of breast cancer. After that, Canonical Correlation Analysis (CCA) was applied as a dimension reduction technique to preserve the character of the original data.Artificial Neural Network (ANN) was applied to the resulting dataset for two different analyses with the same settings. Performance of the predictive models was confirmed by ten-fold cross validation. The results showed an increase in the accuracy of the prediction and reduction of the mean absolute error.

Breast Neoplasms↗
PubMed1994

Personal incentives for exercise and body esteem: a canonical correlation analysis.

Two hundred twelve women and 93 men enrolled in physical education courses were administered the Personal Incentives for Exercise Questionnaire and the Body Esteem Scale. Canonical correlation was conducted. For women, it was determined that personal incentives for exercise have modest predictive power for the weight concern and physical conditioning dimensions of body esteem and very little predictive power for the sexual attractiveness dimension; the body esteem variates have slight predictive power for the competition and weight management dimensions of investment in exercise. For men, it was determined that personal incentives for exercise have modest predictive power for the physical conditioning dimension of body esteem, slight predictive power for physical attractiveness, and none for upper body strength; the body esteem variate has modest predictive power for the weight management dimension of incentives for exercise and slight predictive power for appearance and affiliation.

Adult↗
PubMed1992

A canonical correlation analysis of the influence of neuroticism and extraversion on chronic pain, suffering, and pain behavior.

The relationship between neuroticism and extraversion on the 4 major stages of pain processing, that of pain sensation intensity, pain unpleasantness, suffering, and pain behavior, were studied in 205 chronic pain patients (88 male and 117 female). Patients underwent psychological evaluation which included the Pain Experience visual analogue scales (VAS) (Price et al. 1983), NEO Personality Inventory (NEO-PI) (Costa and McCrae 1985), and the Psychosocial Pain Inventory (PPI) (Getto and Heaton 1980). Canonical correlation was used to control for pain sensation intensity in evaluating affective dimensions of pain and to control for neuroticism in assessing effects of extraversion on different stages and dimensions of pain. Neither neuroticism nor extraversion were related to pain sensation intensity. Only neuroticism was associated with pain unpleasantness. Personality factors had their greatest impact on stages 3 (suffering) and 4 (illness behavior) of pain processing. The results of multiple regression analyses indicated that life-long vulnerability to anxiety and depression is paramount in understanding the relationship between personality and suffering in chronic pain. These findings provide support for the idea that personality traits influence the ways in which people cognitively process the meanings that chronic pain holds for their life, and hence the extent to which they suffer.

Adult↗
PubMed1996

How long does DNA keep the memory of its conformation? A time-dependent canonical correlation analysis of molecular dynamics simulation.

The time dependence of the correlation between motions of different parts of DNA is analyzed from a 200 ps molecular dynamics simulation of the double-stranded self-complementary d(CTGATCAG) in the B form. Each nucleotide is decomposed into three subunits corresponding to the furanose ring (SU), the base (BA), and the backbone (SK). The motion of each subunit is considered as the superimposition of rigid body translation, rigid body rotation, and internal deformation. Canonical time-dependent correlation functions calculated with coordinates describing the different components of the subunits motion are defined and computed. This allows us to probe how long a particular type of motion of one subunit influences the other types of motions of other subunits (cross correlation functions) or how long a particular subunit keeps the memory of its own conformation or location (autocorrelation functions). From autocorrelation analysis it is found that deformation decorrelates within a few tenths of picoseconds, rotational correlation times are on the order of 8 ps, while translational motions are long-time correlated. The deformation of a subunit is not correlated to the deformation of another one (at the 200 ps time scale of our simulation), but influences slightly their translation and orientation as time increases.

Base Sequence↗