PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Factor Analysis, Statistical”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 91 records · Page 5Linked to original sources
PubMed2005

NZiDep: a New Zealand index of socioeconomic deprivation for individuals.

The aim of this research was to identify a small set of indicators of an individual's deprivation that is appropriate for all ethnic groups and can be combined into a single and simple index of individual socioeconomic deprivation in New Zealand. The NZiDep index of socioeconomic deprivation was derived using the same theoretical basis as the national census-based small-area indices of relative socioeconomic deprivation. The index has been created and validated from the analysis of representative sample survey data obtained from approximately 300 Maori, 300 Pacific, and 300 non-Maori, non-Pacific adults. Twenty-eight deprivation-related characteristics, derived from New Zealand and overseas surveys, were analysed by standard statistical techniques (factor analysis, Cronbach's coefficient alpha, item-total correlations, principal component analysis). The index was validated using information on tobacco smoking, which is known to be strongly related to deprivation. The NZiDep index is based on eight simple questions which take 2-3 min to administer. The index is a significant new (non-occupational) tool for measuring socioeconomic position for individuals. We argue that the index has advantages over existing measures, including a specific focus on deficits, applicability to all adults (not just the economically active), and usefulness for all ethnic groups. Its strengths include focus, simplicity, utility, acceptability across ethnic groups, construct validity, statistical validity, criterion validity (measured with reference to tobacco smoking), and relevance to the current New Zealand context. The index is indicative of deprivation in general, and is designed for use as a variable in research, and for elucidating the relationships between socioeconomic position and health/social outcomes.

Age Factors↗
PubMed2004

Alcohol expectancy mediation of biopsychosocial risk: complex patterns of mediation.

Alcohol expectancies' mediation of many known antecedents' influence on drinking has been well established, but most models have omitted theoretically relevant mediational pathways through both common (overlapping) and unique (nonshared) expectancy variance. The authors of this study evaluated expectancy mediation using a hierarchical expectancy model that specified both common and unique expectancy factors. The hierarchical model mediated a significantly (p <.05) larger percentage of the antecedent influences than a model specifying only common expectancy variance, revealed previously unseen mediational paths, and showed, to the authors' knowledge for the first time, expectancy mediation of protective as well as risk-related antecedents. It also allows the modeling of specific pathways for particular antecedents, rather than treating all expectancy mediation as though it flows through a general expectancy factor.

Adaptation, Psychological↗
PubMed2005

Multifactorial etiology of cervical cancer: a hypothesis.

Cancer of the cervix is the second most common life-threatening cancer among women worldwide, with incidence rates ranging from 4.8 per 100,000 women per year in the Middle East to 44.3 per 100,000 in East Africa. Epidemiologic and clinical data demonstrate that human papillomaviruses (HPV), especially HPV-16 and HPV-18, play at least a major if not a necessary role in the etiology of cervical cancer. However, many investigators acknowledge that HPV is not sufficient to induce cervical cancer and that a multifactorial etiology is likely. HPV can be found in a growing proportion of patients with cervical cancer, approaching 100%, but is not yet found in every patient with disease. Other factors, such as herpes simplex virus type 2 infections, cigarette smoking, vaginal douching, nutrition, and use of oral contraceptives, have been proposed as contributing factors. In the first half of the 20th century, Peyton Rous and colleagues demonstrated the joint action of tars and Shope papillomavirus to consistently induce squamous cell carcinomas in rabbits. Using the Rous model as a prototype, one might hypothesize that some cases of cervical cancer arise from an interaction between oncogenic viruses and cervical tar exposures. Cervical tar exposures include cigarette smoking, use of tar-based vaginal douches, and long years of inhaling smoke from wood- and coal-burning stoves in poorly ventilated kitchens.

Causality↗
PubMed2001

Risk factors for morbidity following liver surgery.

The aim of this study is to define risk factors for severe complications following anatomical liver resections. The study material consists of the first 50 patients (26 women, 24 men, at mean age 50.6 years) treated at 3rd Department of Surgery 2nd Faculty of Medicine, Medical University in Warsaw. The indications for resection included benign neoplasm in 19 cases and malignancy in 31 cases. All the patients underwent anatomical liver resection in accordance with Couinaund's segmental division. In order to define prognostic factors for severe postoperative complications, a multi-factor statistical analysis was conducted. The following parameters were analysed: patient's age, the levels of bilirubin, total protein, albumin, prothrombin time, kaolin-kephalin time, range of resection and blood loss during operation. Eleven patients (22%) died in postoperative period. In 8 cases the death was caused by liver failure. Statistical analysis showed that blood loss, albumin level on fifth postoperative day and kaolin-kephalin time before and after surgery are independent risk factors predisposing to the development of complications.

Adolescent↗
PubMed2003

Factors predicting radiation pneumonitis in lung cancer patients: a retrospective study.

PURPOSE: To evaluate clinical and lung dose-volume histogram based factors as predictors of radiation pneumonitis (RP) in lung cancer patients (PTs) treated with thoracic irradiation. METHODS AND MATERIALS: Records of all lung cancer PTs irradiated at our Institution between 1994 and 2000 were retrospectively reviewed. Eighty-four PTs with small or non-small-cell lung cancer, irradiated at >40 Gy, with full 3D dosimetry data and a follow-up time of >6 months from start of treatment, were analysed for RP. Pneumonitis was scored on the basis of SWOG toxicity criteria and was considered a complication when grade> or =II. The following clinical parameters were considered: gender, age, surgery, chemotherapy agents, presence of chronic obstructive pulmonary disease (COPD), performance status. Dosimetric factors including prescribed dose (Diso), presence of final conformal boost, mean lung dose (Dmean), % of lung receiving > or =20, 25, 30, 35, 40, and 45 Gy (respectively V20-->V45), and normal tissue complication probability (NTCP) values were analysed. DVHs data and NTCP values were collected for both lungs considered as a paired organ. Median and quartile values were taken as cut-off for statistical analysis. Factors that influenced RP were assessed by univariate (log-rank) and multivariate analyses (Cox hazard model). RESULTS: There were 14 PTs (16.6%) who had > or =grade II pulmonary toxicity. In the entire population, the univariate analysis revealed that many dosimetric parameters (Diso, V20, V30, V40, V45) were significantly associated with RP. No significant correlation was found between the incidence of RP and Dmean or NTCP values. Multivariate analysis revealed that the use of mitomycin (MMC) (P=0.005) and the presence of COPD (P=0.026) were the most important risk factor for RP. In the group without COPD (55 PTs, seven RP) a few dosimetric factors (Dmean, V20, V45) and NTCP values (all models) were associated with RP in the univariate analysis (P< or =0.06). According to the multivariate analysis, the use of MMC was independently associated with RP (P=0.007), while Dmean approached statistical significance (P=0.082). CONCLUSIONS: In this study the use of mitomycin or the presence of COPD is associated with a higher risk of RP. In the entire population NTCP values were not significantly correlated with the incidence of RP. Mean lung dose shows a clear trend toward statistical significance in the patient group without COPD.

Adult↗
PubMed1995

Automated exploration of two-level interrelations of differently-scaled variables.

The SAS macro EXPLORE is conceived as an exploratory data analysis tool. Its output is an extension to the traditional correlation matrix, allowing the assessment of both categorical and numerical data 'at one look'. Depending on the type of data, appropriate statistics and graphs are produced. An overview of the features of the program and their implementation is given. Program invocation and execution are explained. Potential misuses are discussed.

Algorithms↗
PubMed1994

Applications of standard error estimates in unrestricted factor analysis: significance tests for factor loadings and correlations.

Estimates of standard errors of factor loadings and factor correlations in the unrestricted factor analysis model can be computed for oblique or orthogonal solutions under maximum likelihood. This information can be used to test individual coefficients for significance, to evaluate whether an orthogonal or oblique structure is most consistent with sample data, or to compute confidence intervals for single parameters or confidence regions for arbitrary groups of coefficients. Because the number of parameters estimated in factor analysis is approximately the product of number of variables multiplied by number of factors, a Bonferroni correction for the critical point of the individual test statistics is recommended to control the probability of a Type I error. Several examples are presented.

Aptitude Tests↗
PubMedDate not supplied

[Risk factors involved in symmetrical distal diabetic neuropathy].

INTRODUCTION: Diabetic neuropathy is a common neurological complication in patients with diabetes mellitus which affects their quality of life. The risk factors involved in this are not completely clear. OBJECTIVE: To determine the frequency of symmetrical distal diabetic neuropathy and the risk factors associated with its occurrence in the group studied. PATIENTS AND METHODS: A transversal study was made in the Hospital Clinico Quirurgico Hermanos Ameijeiras of Ciudad de la Habana (Cuba), in 200 patients diagnosed as having type 1 or type 2 diabetes mellitus, between January 1997 and December 1999. A clinical neurological examination and neurophysiological investigations were done on all patients to make a diagnosis of diabetic neuropathy. Subsequently, we compared those with diabetic neuropathy and those without in relation to the risk factors. Statistical analysis included the chi squared test and estimation of the relative risk. RESULTS. The frequency of symmetrical distal diabetic neuropathy was 30.0%. Related risk factors were: smoking (p= 0.00, RR= 2.59), raised serum cholesterol (p= 0.00, RR= 4.12), poor metabolic control of diabetes mellitus (p= 0.00, RR= 4.13), associated disorders (p= 0.00, RR= 5.31) including arterial hypertension (p= 0.03, RR= 1.90) and duration of diabetes mellitus (p= 0.00, RR= 2.01). CONCLUSIONS: In our study symmetrical distal diabetic neuropathy was a common complication of diabetes mellitus associated with various risk factors.

Administration, Oral↗
PubMed2005

Statistical design of experiments: study of cross-linking process through the phase-resolved photoacoustic method as a multivariable response.

This work presents an add-on result of cross-linking using photoacoustic spectroscopy (PAS) phases in a multivariable process using the phase-resolved photoacoustic (PRPA) method. The method is tested to separate contributions from groupings -OH, -CH(2)-, -CH(3), and Si-OH overtones in the range from 700 to 2600 nm. Samples of the copolymers ethylene vinyltrimethoxysilane (EVS) and grafted vinyltrimethoxysilane (VTS) on low-density polyethylene (LDPE) were prepared having concentrations (C) of 3, 5, and 7% of catalyst and temperatures (T) of 70, 80, and 90 degrees C. By considering the condensation reaction, the reduction of -OH groups is monitored. The PRPA analysis was carried out using the surface response methodology and results indicated the optimum point for both answers (signal and phase-resolved) and for both factors of interest (C, T). For the copolymers, it was found that C approximately (5.00 +/- 1.14)% and T approximately (82.4 +/- 4.3) degrees C, while for grafted LDPE PE(g) it was found that C approximately (4.92 +/- 0.85)% and T approximately (80.8 +/- 2.5) degrees C. These results agreed with the chemical analysis for gel content, which showed as the optimum point 5% of catalyst and temperature of 80 degrees C. Further, it is an advantage that the photoacoustic method allows one to per- form a nondestructive analysis.

Acoustics↗
PubMed2004

Correlation of heavy metal concentrations with various factors in canned liver paste products using multivariate statistical strategies.

The content of Cu, Fe, Mn, Zn, Co, Cr, Ni, and Pb were determined in 496 samples of heat-treated canned liver pastes by atomic absorption spectrometry. Canned samples were classified according to the presence or absence of coated varnish on the inner side of the can. For each sample, two subsamples were taken: one from the area in contact with the side of the can, the other from the center of the container. Univariate (correlation, box and whisker) and multivariate (quality control charts, principal component analysis, and factor analysis) statistical techniques were applied to detect the presence of outliers and for exploratory data analysis. No significant differences (P < 0.05) were found between the subsamples considered, presence or absence of coated varnish, the sampling areas, or countries of origin. The multivariate analysis allows for the interpretation of grouping tendencies in samples. Cr, Ni, and Pb were associated with presence or absence of oxide in the can, and the essential metals (Fe, Cu, Zn, and Co) were associated with the kind of can. The samples tended to differentiate according to the type of container.

Analysis of Variance↗
PubMed2005

Risk factors and prognostic factors in patients with double primary cancer: epithelial ovarian cancer and breast cancer.

BACKGROUND AND OBJECTIVE: The most important known risk factor for ovarian cancer is the BRCA1-2 mutation, which is clinically often manifested through a positive family history of cancer of the breast and/or ovary. Whether other risk factors and prognostic factors in women with a positive family history of cancer of the breast and/or ovary and/or with BRCA1-2 mutation are important remains to be elucidated. Recent studies have shown that in the double primary breast and ovarian cancer (DPBOC), BRCA1-2 mutation is present in at least 86% of cases. Therefore, the group of patients with DPBOC, especially with epithelial ovarian cancer and breast cancer, is the most suitable for such an analysis. The aim of this study was to verify the hypothesis that, in this group, some other risk factors, in addition to a specific family history of cancer, as well as unfavourable pathomorphological prognostic factors, are more expressed than in a control group of patients with sporadic epithelial ovarian cancer only. METHODS: We compared the study group of 31 patients with DPBOC (epithelial ovarian cancer) to a control group of 62 patients with a single, sporadic epithelial ovarian cancer and negative specific family history. The data were obtained from the Cancer Registry of Slovenia and from clinical records. For every patient, we filled-in a protocol and analysed the data, comparing other risk factors in addition to specific family history and prognostic, clinical, and pathomorphological factors. Statistical analysis was performed using descriptive statistics, chi-square test and t-test. Multivariate analysis was also planned, but the necessary conditions were not met. RESULTS: In the study group, we found a higher percentage of positive non-specific family histories than in the control group, but the difference was not statistically significant. No difference in procreative risk factors was observed between the groups. There was a higher percentage of borderline significance of women from the study group that developed ovarian cancer between 45 and 59 years of age. In the study group, ovarian cancer was significantly more often found at Stage I, although the groups did not differ in detection procedures. Also, we did not find any differences in the distribution of tumour grades or histologic tumour types. CONCLUSION: The results did not confirm our hypothesis, yet they indicated some differences between the groups regarding the risk factors for ovarian cancer. Regarding the prognostic factors, we even found a significantly higher percentage of Stage I epithelial ovarian cancer in the study group, with no difference in the mode of detection. Considering the results that are not typical of BRCA-related cancer (what double primary cancer of the ovary and breast is supposed to be) and previous reports, we find it more likely that the patients with BRCA1-2 mutations represent only a subgroup within the group of patients with double primary breast and ovarian cancer.

Adult↗
PubMed2006

Mortality versus survival graphs: improving temporal consistency in perceptions of treatment effectiveness.

OBJECTIVE: Previous research has demonstrated that people perceive treatments as less effective when survival graphs show fewer years of data versus more data. We tested whether using mortality graphs would reduce this temporal inconsistency bias. METHODS: A demographically diverse sample of 1461 Internet users read about a hypothetical disease and then were randomized to view either survival or mortality graphs that showed either 5 years of data or 15 years of treatment outcomes data. Participants identified the most effective treatment, provided ratings comparing the effectiveness of two treatments, and answered comprehension questions. RESULTS: Treatment effectiveness ratings varied significantly between respondents seeing the 5 year and 15 year survival graphs even though the relative risk reduction was the same in both cases. This variation was significantly reduced in the mortality graph conditions. Responses on comprehension measures were mixed: viewers of mortality graphs were less able to identify which treatment was more effective but better able to correctly report individual data points. CONCLUSIONS: Perceptions of treatment effectiveness appear more temporally consistent with mortality graphs than with survival graphs. PRACTICE IMPLICATIONS: All line-based risk graphics (whether framed in survival or mortality terms) should highlight duration information to facilitate improved comprehension of treatment effectiveness.

Adult↗
PubMed1999

[Investigation on the prevalence and influencing factors to anemia in women at reproductive age].

OBJECTIVE: To investigate the prevalence of anemia in women of reproductive age and to analyze the influencing factors in anemia. METHODS: A total number of 1,529 women aged 15-49 years old including workers, farmers, cadres and students were tested with Hb and FEP and investigated through questionnaire including related influencing factors. Statistical analysis was performed using SPSS/PC statistical software. RESULTS: Mean value of Hb was 116.35 g/L (SD 14.67 g/L) in 1,529 cases and the prevalence rate of anemia was 31.2%. Majority of the anemia identified belonged to the 'iron deficiency type'. Influencing factors on anemia included occupation, education, marriage status, menstruation, status of family expenses and physical exercise. CONCLUSION: The prevalence rate of anemia in reproductive aged women was high, thus more attention should be paid. In order to lower the incidence of anemia, preventive and intervenient measurements should be conducted accordingly.

Adolescent↗
PubMed1994

The development and evaluation of hospital performance measures for policy analysis.

The purpose of this study was to develop and evaluate hospital performance measures to include aspects of hospital behavior beyond the traditional use of hospital profit margins for policy analysis. A number of measures have been used in the literature that are purported to reflect a variety of hospital behaviors. The reliability and validity of these and new measures were assessed using descriptive statistics and factor analysis on a sample of hospitals for a 3-year period. The sample consisted of all hospitals for which there were Medicare Cost Report and balance sheet data during the federal fiscal years 1987 through 1989. Using a subset of three hospital groups, 33 measures were evaluated, from which five were selected to represent the critical aspects of hospital performance important for policy analysis. The measures are: TEM, a new technical efficiency measure using data envelopment analysis techniques; the current ratio, depicting short-term financial performance; the ratio of longterm debt-to-net fixed assets, representing long-term viability; total margin, portraying profitability; and Medicare margin, characterizing Medicare's contribution to hospital financial position. Each represents different aspects of hospital efficiency and financially viability.

Capital Expenditures↗
PubMedDate not supplied

Do age, gender, or tumor location affect outcomes when using metallic stents in the palliative treatment of esophageal carcinoma?

UNLABELLED: Metallic esophageal stents are marketed as easier to insert with fewer placement and subsequent stent-related problems. Accordingly, we retrospectively/prospectively reviewed our experience placing metallic esophageal stents in malignant strictures. METHODS: The research design was a one-group pre- and post-test quasi-experimental design including all patients who underwent metallic stent placement at Virginia Mason Medical Center in Seattle between August 1987 and August 1997. Data included descriptive statistics of patient demographics, pre- and post-dysphagia scores, acute and subacute complications, repeated interventions, and patient survival outcomes. Descriptive statistics, paired t-test assessing pre- and post-dysphagia scores, and 2-way ANOVA were used to analyze the statistical relationship between complications and 1) stent location, 2) patient gender, and 3) patient age. FINDINGS: Seventy-five metallic stents were placed in 63 patients. Improvement in pre- and post-dysphagia scores was statistically significant. Factor analysis was not statistically significant for complications and stent location, complications and gender, and complications and age. CONCLUSIONS: Metallic esophageal stents showed statistically significant improvement for patient dysphagia. Complications of stent placement did not correlate with location of stent, age, or gender.

Age Factors↗
PubMed1988

[Statistical analysis of pathological factors influencing prognosis of colorectal carcinoma].

The pathological and follow-up data of 503 patients with colorectal carcinoma have been analysed to assess quantitatively prognostic values of 16 pathological factors and their sub-categories with aid of computer. Besides the routine procedure, Cox's proportional hazards model, Hayashi's quantification theory II, III, Akaike's information criteria, Kendall's rank correlation, relative risk, and linear trend test were used. Regardless of methods used, liver metastasis, peritoneal dissemination, lymph nodes metastasis, depth of penetration, venous and lymphatic invasion emerged as powerful prognostic variables. Most of the analyses indicated that venous invasion contained the largest amount of prognostic information including that of long-term survival. When venous invasion is graded not only by the number of veins involved but also by the depth of invasion, its prognostic capability was comparable with that of staging systems. The values of relative risks calculated for the factors' sub-category were more closely associated with prognosis than five-year survival rates or median survival rates, thus permitting detailed comparison of different categories. We conclude the modern statistical methods are indispensable tool for prognostic factor analysis.

Colonic Neoplasms↗
PubMed2001

Symptom factor analysis, clinical findings, and functional status in a population-based case control study of Gulf War unexplained illness.

Few epidemiological studies have been conducted that have incorporated clinical evaluations of Gulf War veterans with unexplained health symptoms and healthy controls. We conducted a mail survey of 2022 Gulf War veterans residing in the northwest United States and clinical examinations on a subset of 443 responders who seemed to have unexplained health symptoms or were healthy. Few clinical differences were found between cases and controls. The most frequent unexplained symptoms were cognitive/psychological, but significant overlap existed with musculoskeletal and fatigue symptoms. Over half of the veterans with unexplained musculoskeletal pain met the criteria for fibromyalgia, and a significant portion of the veterans with unexplained fatigue met the criteria for chronic fatigue syndrome. Similarities were found in the clinical interpretation of unexplained illness in this population and statistical factor analysis performed by this study group and others.

Adult↗