Home About us Contact | |||
Hierarchical Regression (hierarchical + regression)
Terms modified by Hierarchical Regression Selected AbstractsAn application of hierarchical regression in the investigation of multiple paternal occupational exposures and neuroblastoma in offspring,AMERICAN JOURNAL OF INDUSTRIAL MEDICINE, Issue 5 2001Anneclaire J. De Roos MPH Abstract Background We used hierarchical regression to study the effects of 46 paternal occupational exposures on the incidence of neuroblastoma in offspring. Methods The study population included 405 cases and 302 controls. The effect of each exposure was estimated using both conventional maximum likelihood and hierarchical regression. Results Using hierarchical regression, overall precision was greatly enhanced compared to the conventional analysis. In addition, adjustment of effect estimates based on prespecified prior distributions of the true effect parameters allowed a more consistent interpretation across the entire panel of exposures. Estimates for several metals and solvents were shrunk close to the null value, whereas estimates for several thinner solvents, diesel fuel, solders, wood dust, and grain dust remained moderately elevated. Conclusions Hierarchical regression may mitigate some of the problems of the conventional approach by controlling for correlated exposures, enhancing the precision of estimates, and providing some adjustment of estimates based on prior knowledge. Am. J. Ind. Med. 39:477,486, 2001. © 2001 Wiley-Liss, Inc. [source] Rates and Impact of Trauma and Current Stressors Among Darfuri Refugees in Eastern ChadAMERICAN JOURNAL OF ORTHOPSYCHIATRY, Issue 2 2010Andrew Rasmussen Darfur refugees face hardships associated with chronic displacement, including lack of basic needs and safety concerns. Psychiatric research on refugees has focused on trauma, but daily stressors may contribute more to variance in distress. This article reports rates of past trauma and current stressors among Darfur refugees and gauges the contribution of each to psychological distress and functional impairment. A representative sample of 848 Darfuris in 2 refugee camps were interviewed about traumatic events, stressors faced in the camps, psychological distress, and functional impairment. Basic needs and safety concerns were more strongly correlated with measures of distress (rs = .19,.31) than were war-related traumatic events (rs = .09,.20). Hierarchical regression supported models in which effects of trauma on distress were mediated by current stressors. Although war-related traumatic events are the initial causes of refugees' hardship, findings suggest that the day-to-day challenges and concerns in camps mediate psychological distress associated with these events. [source] Relationship of prolactin response to meta-chlorophenylpiperazine with severity of drug use in cocaine dependenceHUMAN PSYCHOPHARMACOLOGY: CLINICAL AND EXPERIMENTAL, Issue 6 2006Ashwin A. Patkar Abstract Rationale Serotonergic (5-HT) mechanisms appear to mediate central effects of cocaine. Therefore 5-HT disturbances could be associated with drug severity. Objectives We investigated whether prolactin (PRL) response to meta-chlorophenylpiperazine (m-CPP), a mixed 5-HT agonist/antagonist were associated with severity of cocaine use. Methods Thirty-six cocaine-dependent subjects and 33 controls underwent a challenge with 0.5,mg/kg of oral m-CPP. Severity of drug use was assessed using the Addiction Severity Index (ASI). Results The PRL response to m-CPP was significantly blunted in cocaine patients compared to controls (F,=,21.86, p,<,0.001). ,PRL (peak PRL,baseline PRL) was negatively correlated with ASI-drug (r,=,,0.45, p,<,0.01), ASI-alcohol (r,=,,0.32, p,<,0.05), and ASI-psychological (r,=,,0.41, p,<,0.01) composite scores, and with the quantity, frequency and duration of drug use (r ranged from ,,0.41 to ,,0.32, p ranged from <,0.01 to 0.05). Hierarchical regressions showed that ASI-drug composite scores significantly predicted the variance in ,PRL after controlling for behavioral and demographic variables (F,=,4.27, p,<,0.05). Conclusions The results indicate that disturbances in 5-HT function as reflected by a blunted response to m-CPP seem to be primarily associated with severity of drug use and to a lesser, although significant extent with behavioral traits in cocaine-dependent patients. Copyright © 2006 John Wiley & Sons, Ltd. [source] ,And I was very very crying': Children's self-descriptions of distress as predictors of recallAPPLIED COGNITIVE PSYCHOLOGY, Issue 7 2010Carole Peterson One hundred and forty-five children's (2,13-year-olds) self-descriptions of how much they cried when injured and subsequently treated in a hospital emergency room were used as predictors of their recall accuracy, completeness and number of unique details in interviews occurring a week, a year and 2 years later. Hierarchical regressions showed that stress was related to all three ways of evaluating children's recall of their injury in initial interviews, although only the completeness of hospital recall was related to stress. For accuracy, stress compromised recall of 2,6-year-olds in initial but not later interviews; for completeness, stress compromised recall of both events in initial but not later interviews. In contrast, highly distressed children provided the most detail in their first two interviews and the oldest children still did so 2 years later. However, stress effects were modest. Copyright © 2009 John Wiley & Sons, Ltd. [source] Ethnicity-Related Stressors and Mental Health in Latino Americans: The Moderating Role of Parental Racial SocializationJOURNAL OF APPLIED SOCIAL PSYCHOLOGY, Issue 9 2007Noé Rubén Chávez The current study examined the moderating role of proactive and reactive parental racial socialization on the relationship between Latino American college students' mental health and 3 ethnicity-related stressors: perceived racial discrimination, stereotype confirmation concern, and own-group conformity pressure. In hierarchical regression, greater stereotype confirmation concern predicted more mental distress in 105 Latino American college students. Both proactive and reactive racial socialization moderated the effect of own-group conformity pressure on anxiety and loss of behavioral/emotional control. Specifically, greater proactive and reactive racial socialization predicted more mental distress under greater own-group conformity pressure. Findings are interpreted in a college environment of ethnic diversity and a context of acculturative stress. [source] An application of hierarchical regression in the investigation of multiple paternal occupational exposures and neuroblastoma in offspring,AMERICAN JOURNAL OF INDUSTRIAL MEDICINE, Issue 5 2001Anneclaire J. De Roos MPH Abstract Background We used hierarchical regression to study the effects of 46 paternal occupational exposures on the incidence of neuroblastoma in offspring. Methods The study population included 405 cases and 302 controls. The effect of each exposure was estimated using both conventional maximum likelihood and hierarchical regression. Results Using hierarchical regression, overall precision was greatly enhanced compared to the conventional analysis. In addition, adjustment of effect estimates based on prespecified prior distributions of the true effect parameters allowed a more consistent interpretation across the entire panel of exposures. Estimates for several metals and solvents were shrunk close to the null value, whereas estimates for several thinner solvents, diesel fuel, solders, wood dust, and grain dust remained moderately elevated. Conclusions Hierarchical regression may mitigate some of the problems of the conventional approach by controlling for correlated exposures, enhancing the precision of estimates, and providing some adjustment of estimates based on prior knowledge. Am. J. Ind. Med. 39:477,486, 2001. © 2001 Wiley-Liss, Inc. [source] Inferential confusion, obsessive beliefs and obsessive,compulsive symptoms: a multidimensional investigation of cognitive domainsCLINICAL PSYCHOLOGY AND PSYCHOTHERAPY (AN INTERNATIONAL JOURNAL OF THEORY & PRACTICE), Issue 4 2008Frederick Aardema Generally, research into the relationship between cognitive domains and obsessive,compulsive symptoms involves the use of scales that are highly intercorrelated with each other. The current study investigates the relationship between cognitive constructs and obsessive,compulsive symptoms using the item set of the Obsessive Beliefs Questionnaire and the Inferential Confusion Questionnaire. In order to create constructs that would not be excessively correlated with each other, factor scores were used to investigate the relationship between cognitive domains and obsessive,compulsive symptoms. Factor analysis followed by oblique rotation resulted in four moderately correlated cognitive constructs (importance/control of thoughts, inferential confusion/threat estimation, perfectionism/certainty and responsibility for preventing harm). With the exception of responsibility for preventing harm, the cognitive constructs under investigation were quite strongly related to obsessive,compulsive symptoms. In particular, hierarchical regression revealed the construct inferential confusion/threat estimation to be a global and strong predictor of obsessive,compulsive symptoms, followed by the constructs of perfectionism/certainty and the construct importance/control. Responsibility for preventing harm acted to be a negative predictor of obsessive,compulsive symptoms. It is concluded that the construct of inferential confusion acts as a more powerful predictor of obsessive,compulsive symptoms than any specific obsessive belief,Copyright © 2008 John Wiley & Sons, Ltd. [source] Paranoid beliefs and self-criticism in studentsCLINICAL PSYCHOLOGY AND PSYCHOTHERAPY (AN INTERNATIONAL JOURNAL OF THEORY & PRACTICE), Issue 5 2007A. Mills Paranoid beliefs are associated with negative and malevolent views of others. This study, however, explored hostile and compassionate self-to-self relating in regard to paranoid beliefs. A total of 131 students were given a series of scales measuring paranoid ideation, forms and functions of self-criticism, self-reassurance, self-compassion and depression. Test scores were subjected to correlation and hierarchical regression analyses to explore the relative contribution of study variables to paranoid beliefs. In this population, paranoid beliefs were associated with forms and functions of self-criticism, especially self-hating and self-persecution. Paranoid beliefs were negatively correlated with self-kindness and abilities to be self-reassuring. These variables were also associated with depression (as were paranoid beliefs). A hierarchical regression found that self-hatred remained a predictor of paranoid ideation even after controlling for depression and self-reassurance. Paranoid beliefs seem to be associated with a critical and even hating experience of self. These inner experiences of self may be profitable targets for therapeutic interventions.,Copyright © 2007 John Wiley & Sons, Ltd. [source] Health care funding levels and patient outcomes: a national studyHEALTH ECONOMICS, Issue 4 2007Margaret M. Byrne Abstract Background: Health care funding levels differ significantly across geographic regions, but there is little correlation between regional funding levels and outcomes of elderly Medicare beneficiaries. Our goal was to determine whether this relationship holds true in a non-Medicare population cared for in a large integrated health care system with a capitated budget allocation system. Methods: We explored the association between health care funding and risk-adjusted mortality in the 22 Veterans Affairs (VA) geographic Networks over a six-year time period. Allocations to Networks were adjusted for illness burden using Diagnostic Cost Groups. To test the association between funding and risk-adjusted three-year mortality, we ran logistic regressions with single-year patient cohorts, as well as hierarchical regressions on a six year longitudinal data set, clustering on VA Network. Results: A $1000 increase in funding per unit of patient illness burden was associated with a 2,8% reduction in three-year mortality in cross sectional regressions. However, in longitudinal hierarchical regressions clustering on Network, the significant effect of funding level was eliminated. Conclusions: When longitudinal data are used, the significant cross sectional effect of funding levels on mortality disappear. Thus, the factors driving differences in mortality are Network effects, although part of the Network effect may be due to past levels of funding. Our results provide a caution for cross sectional examinations of the association between regional health care funding levels and health outcomes. Copyright © 2006 John Wiley & Sons, Ltd. [source] THE INCREMENTAL VALIDITY OF INTERVIEW SCORES OVER AND ABOVE COGNITIVE ABILITY AND CONSCIENTIOUSNESS SCORESPERSONNEL PSYCHOLOGY, Issue 2 2000JOSE M. CORTINA Recent research has suggested that scores on measures of cognitive ability, measures of Conscientiousness, and interview scores are positively correlated with job performance. There remains, however, a question of incremental validity: To what extent do interviews predict above and beyond cognitive ability and Conscientiousness? This question was addressed in this paper by (a) conducting meta-analyses of the relationships among cognitive ability, Conscientiousness, and interviews, (b) combining these results with predictive validity results from previous meta-analyses to form a "meta-correlation matrix" representing the relationships among cognitive ability, Conscientiousness, interviews, and job performance, and (c) performing 9 hierarchical regressions to examine the incremental validity of 3 levels of structured interviews in best, actual, and worst case scenarios for prediction. Results suggested that interview scores contribute to the prediction of job performance over and above cognitive ability and Conscientiousness to the extent that they are structured, with scores from highly structured interviews contributing substantially to prediction. Directions for future research are discussed. [source] Sex,related self,concepts, cognitive styles and cultural values of traditionality,modernity as predictors of general and domain,specific sexismASIAN JOURNAL OF SOCIAL PSYCHOLOGY, Issue 1 2003Jolynn C. X. Pek Previous studies have determined that masculinity, femininity, need for closure and authoritarianism are significant predictors of sexism. The present study attempted to integrate these variables in order to better understand the nature of general ambivalent sexism and workplace,specific sexism in Singapore. Chinese traditionality and Chinese modernity were specifically examined as potential predictors of sexism. Robust results from hierarchical regressions indicated that these indigenous cultural variables were highly important in predicting general and workplace,specific sexism. Although masculinity and need for closure were unrelated to sexism, participant sex, femininity and authoritarianism significantly predicted sexist attitudes towards women. Most important, Chinese values were found to add significant incremental validity in predicting sexist attitudes beyond what was accounted by the aforementioned predictors. Chinese traditionality significantly predicted sexist attitudes towards women, but Chinese modernity was unrelated to sexism. Implications of these findings were discussed. [source] |