Matching Items (3)
Filtering by
- All Subjects: Analysis of variance
- All Subjects: Health facilities
- Creators: Lines, Brian
- Creators: Enders, Stephen G
Description
Random Forests is a statistical learning method which has been proposed for propensity score estimation models that involve complex interactions, nonlinear relationships, or both of the covariates. In this dissertation I conducted a simulation study to examine the effects of three Random Forests model specifications in propensity score analysis. The results suggested that, depending on the nature of data, optimal specification of (1) decision rules to select the covariate and its split value in a Classification Tree, (2) the number of covariates randomly sampled for selection, and (3) methods of estimating Random Forests propensity scores could potentially produce an unbiased average treatment effect estimate after propensity scores weighting by the odds adjustment. Compared to the logistic regression estimation model using the true propensity score model, Random Forests had an additional advantage in producing unbiased estimated standard error and correct statistical inference of the average treatment effect. The relationship between the balance on the covariates' means and the bias of average treatment effect estimate was examined both within and between conditions of the simulation. Within conditions, across repeated samples there was no noticeable correlation between the covariates' mean differences and the magnitude of bias of average treatment effect estimate for the covariates that were imbalanced before adjustment. Between conditions, small mean differences of covariates after propensity score adjustment were not sensitive enough to identify the optimal Random Forests model specification for propensity score analysis.
ContributorsCham, Hei Ning (Author) / Tein, Jenn-Yun (Thesis advisor) / Enders, Stephen G (Thesis advisor) / Enders, Craig K. (Committee member) / Mackinnon, David P (Committee member) / Arizona State University (Publisher)
Created2013
Description
Owner organizations in the architecture, engineering, and construction (AEC) industry are presented with a wide variety of project delivery approaches. Implementation of these approaches, while enticing due to their potential to save money, reduce schedule delays, or improve quality, is extremely difficult to accomplish and requires a concerted change management effort. Research in the field of organizational behavior cautions that perhaps more than half of all organizational change efforts fail to accomplish their intended objectives. This study utilizes an action research approach to analyze change message delivery within owner organizations, model owner project team readiness and adoption of change, and identify the most frequently encountered types of resistance from lead project members. The analysis methodology included Spearman's rank order correlation, variable selection testing via three methods of hierarchical linear regression, relative weight analysis, and one-way ANOVA. Key findings from this study include recommendations for communicating the change message within owner organizations, empirical validation of critical predictors for change readiness and change adoption among project teams, and identification of the most frequently encountered resistive behaviors within change implementation in the AEC industry. A key contribution of this research is the recommendation of change management strategies for use by change practitioners.
ContributorsLines, Brian (Author) / Sullivan, Kenneth (Thesis advisor) / Wiezel, Avi (Committee member) / Badger, William (Committee member) / Arizona State University (Publisher)
Created2014
Description
The purpose of this paper is to present a case study on the application of the Lean Six Sigma (LSS) quality improvement methodology and tools to study the analysis and improvement of facilities management (FM) services at a healthcare organization. Research literature was reviewed concerning whether or not LSS has been applied in healthcare-based FM, but no such studies have been published. This paper aims to address the lack of an applicable methodology for LSS intervention within the context of healthcare-based FM. The Define, Measure, Analyze, Improve, and Control (DMAIC) framework was followed to test the hypothesis that LSS can improve the service provided by an FM department responsible for the maintenance and repair of furniture and finishes at a large healthcare organization in the southwest United States of America. Quality improvement curricula and resources offered by the case study organization equipped the FM department to apply LSS over the course of a five-month period. Qualitative data were gathered from pre- and post-intervention surveys while quantitative data were gathered with the Organization’s computerized maintenance management system (CMMS) software. Overall, LSS application proved to be useful for the intended purpose. The author proposes that application of LSS by other FM departments to improve their services could also be successful, which is noteworthy and deserving of continued research.
ContributorsShirey, William T (Author) / Sullivan, Kenneth (Thesis advisor) / Smithwick, Jake (Committee member) / Lines, Brian (Committee member) / Arizona State University (Publisher)
Created2017