Statistics from the inside. 6. Data structures (continued).
Explore the source record for details and available documents.
Data Interpretation, Statistical↗
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.
Phenotypes of the heavy chains of immunoglobulins in patients with diabetic microangiopathy: evidence for an immunogenetic predisposition.
The B3 allotype of the fourth component of complement (C4B3) is associated with microangiopathy. As C4 is important in the humoral immune response phenotypic variation of other inherited components of the response such as the immunoglobulins could also be associated with microangiopathy. Phenotypes of the heavy chains of immunoglobulins (Gm) were compared in 48 insulin dependent diabetics with and 74 without microangiopathic complications. The Gm(zafnbg) phenotype was found significantly more often in insulin dependent diabetics with complications than in those without (16 (33%) out of 48 v 7 (9%) out of 74, respectively, p less than 0.01). Insulin dependent diabetics with both C4B3 and Gm(zafnbg) had an increased risk of complications compared with insulin dependent diabetics with neither or only one factor. Statistical analysis suggested that these two associations were additive, indicating that they increased risk by independent mechanisms. These findings suggest that susceptibility to diabetic microangiopathy is influenced by genes at or in linkage disequilibrium with both the major histocompatibility complex and the Gm loci.
Adult↗
Air pollution and cause specific mortality in Athens.
STUDY OBJECTIVE: The aim was to investigate the reported association between air pollution and cause specific mortality in the city of Athens. DESIGN: Cause specific mortality was contrasted between 199 d with high values of air pollution and 2*199 comparison days with low pollution, matched in a 1:2 ratio on the basis of various confounding factors. Statistical analysis was done, taking matching into account, using analysis of variance for randomised blocks. SETTING: The study was confined to the city of Athens, using data obtained between 1975 and 1982. PARTICIPANTS: Cause of death was assessed in all 25 138 persons dying in the 3*199 d studied. MEASUREMENTS AND MAIN RESULTS: Causes of death were evaluated blindly by two medically qualified investigators on the basis of information in the death certificates. Mortality was generally higher during the high pollution days but the difference was more pronounced and more significant for respiratory conditions, even though the number of deaths in this category was smaller than the corresponding numbers in the other two categories examined (cardiac and "other" deaths). CONCLUSION: The results show that the short term association between air pollution and overall mortality in Athens is likely to be causal, since it is particularly evident with respect to respiratory conditions, for which a biological air pollution link is more plausible.
Air Pollution↗
Study of the patients' difficulties in ending brief psychoanalytic psychotherapy.
Brief psychotherapy implies a limitation of the time needed, which should meet both the patient's acceptance and the therapist's awareness. However, some patients have difficulties in ending therapy. The material of this study consists of 27 patients. Of these patients, 5 dropped out in the termination phase, while for another 8 it became apparent a little before or after the final phase that psychotherapy would have to be continued. The results of the statistical analysis--factor analysis and analysis of variance for the investigation of therapists' difficulties, and discriminant analysis to assess differences concerning the suitability of patients for brief psychotherapy--showed that: (1) the less a therapist feels self-confident, the more likely his/her patient is to break off therapy at the termination point, and (2) the suitability score, determined during evaluation, emerges as the main differentiating parameter of the three groups (dropouts, continuers, completers).
Countertransference↗
Consumer perceptions of medical information sources: an application of multidimensional scaling.
Multidimensional scaling is widely used in marketing research to characterize the perceived relationships among a set of consumer products. The technique is also well suited to study a number of issues that are of interest to health care marketers. This paper explains multidimensional scaling and provides an illustrative example of a health care application. In the research study reported here, the perceptions of various sources of medical information give important insights to a health care organization that is designing a new medical information service for consumers. Other potential applications of the technique for health care marketing are also explored.
Consumer Behavior↗
[Effect of smoking during pregnancy on anthropometric characteristics at birth].
OBJECTIVE: To assess the effect of tobacco consumption during pregnancy on height and birth weight of newborns. MATERIAL AND METHODS: Two cohort studies on lead exposure conducted in Mexico City between 1993 and 2000 were analyzed. Data were analyzed to assess the differences in height and birth weight between children of women who smoked during pregnancy and those who did not, adjusting for other important factors. Statistical analysis consisted of multiple linear regression models. RESULTS: The proportion of women who smoked during pregnancy was 4.7%. The birth weight of children of mothers who smoked during pregnancy was 154 grams less on average (95% confidence interval [CI] -284.7, -24.7) and their height was 0.79 cm less (95% CI -1.5, -0.1) than the children of non-smokers during pregnancy. CONCLUSIONS: These findings evidence the deleterious effect of tobacco consumption on children.
Adult↗
The Friedrich-Lively Instrument to Assess the Impact of Schizophrenia on Siblings (FLIISS): Part II--reliability and validity assessment.
Siblings of persons with schizophrenia who provide primary or secondary care for their sibling and support to parents may experience stress, decreased quality of life, grief, chronic illness, depression, and anxiety. The effects on siblings have not been widely studied and there have not been appropriate instruments to measure the types and degree of stress and associated mental, emotional, and physical distress. The Friedrich-Lively Instrument to Assess the Impact of Schizophrenia on Siblings (FLIISS) is a comprehensive instrument based on extensive research and work with siblings of persons with schizophrenia. Construction of the FLIISS and its relationship to a conceptual model of stress is presented in an article (Part I) elsewhere in this issue. In this article (Part II), reliability results and construct validity are reported for the FLIISS. The FLIISS demonstrates appropriate usefulness and content, acceptable internal consistency, and strong construct validity. Health professionals can use the instrument for collecting information that will increase their ability to identify sources of stress faced by siblings of persons with schizophrenia and develop interventions to help these siblings.
Adult↗
One operation after percutaneous diagnosis of nonpalpable breast cancer: frequency and associated factors.
OBJECTIVE: The purpose of this study was to determine the frequency of and factors associated with performing one therapeutic operation after percutaneous diagnosis of nonpalpable breast cancer. MATERIALS AND METHODS: Retrospective review was performed of records of 350 consecutive women who had therapeutic surgery after percutaneous imaging-guided core biopsy diagnosis of nonpalpable breast cancer. Records were reviewed to determine the frequency of performing one operation and associated factors. Statistical analysis was performed. RESULTS: One operation was performed in 283 (80.9%) of 350 women, including 106 (95.5%) of 111 women who had mastectomy and 177 (74.1%) of 239 women who had breast conserving surgery. At bivariate analysis, one operation was significantly more likely in women who had no underestimation (p < 0.001), mastectomy rather than breast conservation (p < 0.001), axillary dissection during the first operation (p < 0.001), percutaneous diagnosis of infiltrating carcinoma (p = 0.001), or mammographic mass (p = 0.006). At multivariate analysis, one operation was significantly more likely if underestimation was absent (odds ratio [OR] = 10.1, 95% confidence interval [CI] = 4.2-24.7) or if mastectomy was performed (OR = 8.7, 95% CI = 3.2-23.5); for women who had breast-conserving surgery, one operation was significantly more likely if underestimation was absent (OR = 11.4, 95% CI = 3.9-33.2) or if a mammographic mass was present (OR = 2.4, 95% CI = 1.3-4.6). CONCLUSION: One operation was performed in 80.9% of women with percutaneously proven nonpalpable breast cancer, including 74.1% of women who had breast-conserving surgery and 95.5% of women who had mastectomy. Among women who had breast conservation, one operation was significantly more likely if histologic underestimation was absent or if a mammographic mass was present.
Adult↗
Least sum of Euclidean regression residuals: estimation of effect size.
A universal measure of the magnitude of effect size is introduced for Euclidean-based regression analyses of experimental designs. The measure is based on the ratio of the sums of Euclidean residuals obtained under the alternative and null hypotheses.
Data Interpretation, Statistical↗
[The substitution effect of leadership substitutes for transformational leadership in nursing organization].
PURPOSE: This paper was conducted to examine the effects of transformational leadership behaviors, within the substitutes for leadership model (Kerr & Jermier, 1978). METHOD: Data was collected from 181 staff nurses in 3 general hospitals, with self-reporting questionnaires (MLQ developed by Bass, rd-SLS developed by Podsakoff, et al., and MSQ developed by Weiss, et al.). Descriptive statistics, factor analysis, Cronbach's alpha and moderated regression analysis were used. RESULT: 1) The transformational leader behaviors and substitutes for leadership each had correlations with job satisfaction. 2) The total amount of variance accounted for by the substitutes for leadership was substantially greater than by the transformational leadership behaviors. 3) Few of the substitutes variables moderated the relationships between the transformational leader behaviors and job satisfaction in a manner consistent with that specified by Howell, Dorfman, and Kerr (1986). CONCLUSION: The finding of this study suggest that leaders need to have a better understanding of those contextual variables that influence job satisfaction. Thus future research should focus attention on the moderating effects of substitutes, as well as the things that leaders can do to influence them. In addition, it may be good to examine the effects of substitutes on other criterion variables.
Adult↗
Dynamic characteristics of laser-Doppler flux data.
Methods for tracking the dynamics of the blood flow microcirculation obtained by laser-Doppler flowmetry (LDF) technique are described. It was shown that LDF signals have complex dynamics. It was mainly characterized by fractal structures and chaos, though multiperiodic, trend-like and stochastic components were also established. Procedures for (i) describing the dynamic structure and (ii) tracking the dynamic changes in time of LDF data are proposed. Examples illustrating the efficiency of these procedures are given using both simulated and LDF data collected in experiments with reactive hyperemia. Irrespective of the universality of the methods, the procedures should be specified according to the problem-oriented clinical and experimental studies.
Algorithms↗
Personal Construct Theory: a strategy for the study of multidimensional phenomena in nursing.
Explore the source record for details and available documents.
Adaptation, Psychological↗
[Study on serum proteome of rat endotoxemia treated by figwort root].
OBJECTIVE: To study the serum proteome of rat endotoxemia treated by figwort root (FR). METHOD: The differences of serum proteome among rats treated with lipopolysaccharide (LPS), FR, LPS + FR and saline respectively were analyzed by two-dimensional electrophoresis (2DE) assay. RESULT: The volumes of sixteen serum proteins (xPr) in LPS induced-endotoxemia group were greatly changed compared with those of the control group. Among them, the volumes of xPr 16, 19 were significantly decreased, and the volumes of xPr 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 14, 18, 23 were significantly increased. When treated with FR, the volumes of xPr 1, 6, 7, 8, 9, 11, 12, 14, 18, 23 were significantly decreased, and the volumes of xPr 8, 9, 11, 12, 23, 14 were back to normal level. Two factors statistic analysis showed that FR had interaction with LPS for xPr 1, 5, 8, 10, 11, 12, 18, 19, 20, 21, 22, and FR might be the functional antagonist of LPS. We also observed that the volumes of xPr 10, 13, 15, 20, 21, 22 were found to change significantly only in FR treated group but not in LPS treated group or control group. Interestingly, the volume of xPr 13, 20, 21, 22 were increased and the volume of xPr 10, 15 were decreased. CONCLUSION: The molecular basis of therapeutic effect of FR on endotoxemia might be through the regulation of xPr 1, 6, 7, 8, 9, 11, 12, 14, 18, 23. We can use proteomic techniques to study the molecular mechanisms of diseases treated by functional Chinese herbs and the combination of different herbs is necessary for the treatment of endotoxemia, as FR can not regulated all the changed proteins induced by LPS.
Animals↗
[Morphological prognostic criteria in skin melanoma].
The value of morphologic features to be used prognosing dissemination and survival in skin malignant melanoma is discussed. Single-factor statistical analysis showed tumor thickness, extent of invasion or local spreading, clinico-morphologic pattern, lymphoid-plasmocytic infiltration, mitotic activity and cell composition to be the most reliable in predicting survival and dissemination in clinical stage I malignant melanoma of the skin. These parameters should be evaluated at microscopic evaluation of the tumor. Two-, five- and ten-year prognosis was obtained by multifactorial analysis yielding credibilities of 86.2, 78.5 and 71% for survival and 61.5, 68.7 and 74.3% for lethality, respectively.
Humans↗
Nurses' job satisfaction: a proposed measure.
Thirty-three items originally developed to measure three dimensions of nurses' job satisfaction were subjected to a series of checks designed to determine the number of dimensions being measured and the reliability and validity of the measures of these dimensions. Although the hypothesis of only three dimensions was not supported, the eight interpretable factors that did emerge could meaningfully be placed within these three dimensions. The eight factors were satisfaction with extrinsic rewards, scheduling, family/work balance, co-workers, interaction, professional opportunities, praise/recognition, and control/responsibility. Internal consistency and test-retest reliabilities are reported, as well as checks for criterion-related and construct validity.
Data Interpretation, Statistical↗
[Attitude patterns of the elderly to technical innovation].
This article investigates how older adults react to new technology. The concepts of "social integration", "control", "learning new material", and "mediation" concepts are shown. One-hundred-sixty-four subjects from 58 to 88 years old judged 83 items dealing with computers. The statistical analysis (factor analysis) revealed a complex structure of perception and judgement. Three independent dimensions were found: 1) "danger", 2) "positive aspects", and 3) "motivation". Whereas the first two factors are of very general dimensions, "motivation" is specifically influenced by educational level in interaction with previous experience. The importance of computers for life-long learning is discussed. Possibilities for computer-based training are demonstrated.
Aged↗
Treating ordinal scales as ordinal scales.
Explore the source record for details and available documents.
Chi-Square Distribution↗
[A case-control study of the risk factors for lung cancer among Chinese women who have never smoked].
OBJECTIVE: To investigate the risk factors for lung cancer among women who had never smoked. Methods A 1:2 matched case-control study was carried out. The cases are the no-smoking female patients with the primary lung cancer diagnosed by pathology mothed from hospitals in Beijing, Shanghai and Chengdu between September 2001 and February 2004. One hospital control and one population control matched for age, sex and no-smoking et al., were enrolled. The case and control were interviewed about the exposure information of related factors using the uniform questionnaire. Statistical analysis of single-factor and multivariate conditional Logistic regression were performed to screen the risk factors of lung cancer. RESULTS: During the single-factoranalysis, 28 exposure factors were identified as risk factors for lung cancer. The multivariate conditional Logistic regression show that passive smoking index > or = 50 person * year (OR = 1.77,95% CI, 1.07 - 2.92), consumption of internal organs of animals (OR = 1.85,95% CI, 1.06 - 3.22), and occupational exposure to dust (OR = 2.47,95% CI, 1.21 - 5.03) and bad ventilation in workplace( OR = 4.02,95% CI, 1.74 - 9.29) are risk factors for lung cancer, but consumption of vegetables( OR = 0.26, 95% CI, 0.12 - 0.59), taking vitamins often (OR = 0.53, 95% CI, 0.30 - 0.93), average month income per person after married > or = 500 yuan ( OR = 0.50, 95% CI, 0.28 - 0.91) and the first procreation occurred between 24 and 30 years old (OR = 0.53, 95% CI, 0.32 - 0.90) are the protective factors for lung cancer. The dose-response were observed between passive smoking and risk rate of lung cancer by trend test. CONCLUSION: Some factors such as passive smoking, consumption of internal organs of animals, occupational exposure to dust and bad ventilation in workplace can increase the risk of lung cancer for women who had never smoked. Other factors such as consumption of vegetables, taking vitamins, and so on, can reduce the risk of lung cancer for women who had never smoked.
Adolescent↗