Problems of correlations between explanatory variables in multiple regression analyses in the dental literature

Tu, Yu–Kang; Kellett, Margaret; Clerehugh, V.; Gilthorpe, Mark S.

doi:10.1038/sj.bdj.4812743

Cited by 136 publications

(92 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bivariate correlations among all covariates were examined to assess potential problems due to collinearity, as such collinearity might confound the analyses (Tu et al, 2001(Tu et al, , 2005. Where strong correlations were observed between time (year of diagnosis) and the Calman -Hine implementation scores, analyses were undertaken across two time periods -1995 to 2000 and 1996 to 1998, separately -in an attempt to limit the effect of collinearity.…”

Section: Methodsmentioning

confidence: 99%

The impact of the Calman–Hine report on the processes and outcomes of care for Yorkshire's colorectal cancer patients

et al. 2006

Self Cite

View full text Add to dashboard Cite

The 1995 Calman -Hine plan outlined radical reform of the UK's cancer services with the aim of improving outcomes and reducing inequalities in NHS cancer care. Its main recommendation was to concentrate care into the hands of site-specialist, multi-disciplinary teams. This study aimed to determine if the implementation of Calman -Hine cancer teams was associated with improved processes and outcomes of care for colorectal cancer patients. The design included longitudinal survey of 13 colorectal cancer teams in Yorkshire and retrospective study of population-based data collected by the Northern and Yorkshire Cancer Registry and Information Service. The population was all colorectal cancer patients diagnosed and treated in Yorkshire between 1995 and 2000. The main outcome measures were: variations in the use of anterior resection and preoperative radiotherapy in rectal cancer, chemotherapy in Dukes stage C and D patients, and five-year survival. Using multilevel models, these outcomes were assessed in relation to measures of the extent of Calman -Hine implementation throughout the study period, namely: (i) each team's degree of adherence to the Manual of Cancer Service Standards (which outlines the specification of the 'ideal' colorectal cancer team) and (ii) the extent of site specialisation of each team's surgeons. Variation was observed in the extent to which the colorectal cancer teams in Yorkshire had conformed to the Calman -Hine recommendations. An increase in surgical site specialisation was associated with increased use of preoperative radiotherapy (OR ¼ 1.43, 95% CI ¼ 1.04 -1.98, Po0.04) and anterior resection (OR ¼ 1.43, 95% CI ¼ 1.16 -1.76, Po0.01) in rectal cancer patients. Increases in adherence to the Manual of Cancer Service Standards was associated with improved five-year survival after adjustment for the casemix factors of age, stage of disease, socioeconomic status and year of diagnosis, especially for colon cancer (HR ¼ 0.97, 95% CI ¼ 0.94 -0.99 Po0.01). There was a similar trend of improved survival in relation to increased surgical site specialisation for rectal cancer, although the effect was not statistically significant (HR ¼ 0.93, 95% CI ¼ 0.84 -1.03, P ¼ 0.15). In conclusion, the extent of implementation of the Calman -Hine report has been variable and its recommendations are associated with improvements in processes and outcomes of care for colorectal cancer patients.

show abstract

Section: Methodsmentioning

confidence: 99%

The impact of the Calman–Hine report on the processes and outcomes of care for Yorkshire's colorectal cancer patients

et al. 2006

Self Cite

View full text Add to dashboard Cite

show abstract

“…Generally, our seasonal models have the optimal performance with three auxiliary variables, and less or more variables than three would bring about instability or redundancy of the GWR models. Adding extra auxiliary variables shows little improvement in the GWR model but even reduces the model performance and aggravates the overfitting, due to the increasing risk of intra-correlations among variables [41]. We further analyzed the auxiliary variables in four seasonal model "AOD + 3" and guessed that they coincided with three meteorological effects in PM 2.5 concentrations.…”

Section: Discussionmentioning

confidence: 99%

Modelling Seasonal GWR of Daily PM2.5 with Proper Auxiliary Variables for the Yangtze River Delta

et al. 2017

View full text Add to dashboard Cite

Abstract:Over the past decades, regional haze episodes have frequently occurred in eastern China, especially in the Yangtze River Delta (YRD). Satellite derived Aerosol Optical Depth (AOD) has been used to retrieve the spatial coverage of PM 2.5 concentrations. To improve the retrieval accuracy of the daily AOD-PM 2.5 model, various auxiliary variables like meteorological or geographical factors have been adopted into the Geographically Weighted Regression (GWR) model. However, these variables are always arbitrarily selected without deep consideration of their potentially varying temporal or spatial contributions in the model performance. In this manuscript, we put forward an automatic procedure to select proper auxiliary variables from meteorological and geographical factors and obtain their optimal combinations to construct four seasonal GWR models. We employ two different schemes to comprehensively test the performance of our proposed GWR models: (1) comparison with other regular GWR models by varying the number of auxiliary variables; and (2) comparison with observed ground-level PM 2.5 concentrations. The result shows that our GWR models of "AOD + 3" with three common meteorological variables generally perform better than all the other GWR models involved. Our models also show powerful prediction capabilities in PM 2.5 concentrations with only slight overfitting. The determination coefficients R 2 of our seasonal models are 0.8259 in spring, 0.7818 in summer, 0.8407 in autumn, and 0.7689 in winter. Also, the seasonal models in summer and autumn behave better than those in spring and winter. The comparison between seasonal and yearly models further validates the specific seasonal pattern of auxiliary variables of the GWR model in the YRD. We also stress the importance of key variables and propose a selection process in the AOD-PM 2.5 model. Our work validates the significance of proper auxiliary variables in modelling the AOD-PM 2.5 relationships and provides a good alternative in retrieving daily PM 2.5 concentrations from remote sensing images in the YRD.

show abstract

“…We also determined the synergism between peer smoking and perceived accessibility, that is, the degree to which peer smoking enhances the effects of perceived accessibility on smoking rates, as has been previously described by Hallqvist et al 40 and Andersson et al 41 We used the variance infl ation factor and correlation coeffi cient to assess for collinearity or multicollinearity in the multivariable models. 42 After consideration of multicollinearity, we retained the following covariates for potential inclusion in the multivariable models: age; sex; race-ethnicity; number of siblings; knowledge of product affi liation of the Joe Camel character; having a favorite cigarette advertisement; parental permissiveness of watching R-rated movies; parental smoking; perceived parental or peer approval of smoking; belief that smoking makes a person popular, look cool, or fi t in; involvement in community activities or Boy or Girl Scouts; impulsivity; concerns about weight; anger coping; …”

mentioning

confidence: 99%

Perceived Accessibility as a Predictor of Youth Smoking

Doubeni¹,

Li²,

Fouayzi³

et al. 2008

The Annals of Family Medicine

View full text Add to dashboard Cite

PURPOSE Youths who smoke are more likely to perceive that cigarettes are easily accessible, but the relationship between perceived accessibility of cigarettes and the risk of smoking is not clear. The objective of this study was to determine whether perceived accessibility predicted future smoking among youths.METHODS This study used data from the second Development and Assessment of Nicotine Dependence in Youth (DANDY-2) study, a 4-year (2002)(2003)(2004)(2005)(2006) cohort study that began with 1,246 sixth-grade students in 6 Massachusetts communities. DANDY-2 comprised 11 waves of in-person interviews. A total of 1,195 students who were aged 11 to 14 years at the baseline interview in 2002 were eligible for inclusion in this report. The outcomes for this study were the onset of smoking initiation and regular tobacco use. RESULTSAt baseline 1,027 students had never smoked cigarettes, and 168 had previously initiated smoking. During the 4 years of the study, 177 students newly initiated smoking, and 109 became regular smokers. In unadjusted citystratifi ed Cox proportional hazard models, perceived accessibility increased the risk for smoking initiation among nonsmokers and regular smoking among all participants in a dose-response fashion. Perceived accessibility also increased the risk for smoking progression among initiators in a dose-response fashion. The associations between perceived accessibility and smoking were robust to adjustment for peer and parental smoking. Youths with both perceived accessibility and peer-smokers had a higher risk of regular smoking and progression after initiation than either factor alone. These associations were stable to adjustment for potential confounders other than peer smoking.CONCLUSIONS Perceived accessibility increases the risk for smoking among youths and has a stronger effect among those with peer smokers. There may be a role for identifying this group of youths for targeted interventions in child health care settings. Perceived accessibility should be carefully considered and measured in smoking intervention programs for teens. Ann Fam Med 2008:6;323-330. DOI: 10.1370/afm.841. INTRODUCTIONC igarette smoking is a major public health challenge worldwide. In developed countries many adult smokers initiated tobacco use during their teenage years; therefore, smoking experimentation and progression to regular tobacco use in adolescence represent potentially preventable milestones that may lead to nicotine addiction 1,2 and preventable major adverse health consequences. Although several factors have been shown to increase the risk of smoking in adolescence, [3][4][5][6][7] the relationship between perceived accessibility and youth tobacco use is poorly understood.In the United States, a combination of excise taxation, litigation against tobacco companies, and enforcement of laws prohibiting the sale of tobacco products to minors have increased the cost of and the diffi culty in obtaining tobacco products. [8][9][10][11][12][13][14] Despite these measures, many youths ...

show abstract

Problems of correlations between explanatory variables in multiple regression analyses in the dental literature

Cited by 136 publications

References 19 publications

The impact of the Calman–Hine report on the processes and outcomes of care for Yorkshire's colorectal cancer patients

The impact of the Calman–Hine report on the processes and outcomes of care for Yorkshire's colorectal cancer patients

Modelling Seasonal GWR of Daily PM2.5 with Proper Auxiliary Variables for the Yangtze River Delta

Perceived Accessibility as a Predictor of Youth Smoking

Contact Info

Product

Resources

About