Some practical advice on polynomial regression analysis from blocked response surface designs

It is often necessary to run response surface designs in blocks. In this paper the analysis of data from such experiments, using polynomial regression models, is discussed. The definition and estimation of pure error in blocked designs are considered. It is recommended that pure error is estimated by assuming additive block and treatment effects, as this is more consistent with designs without blocking. The recovery of inter-block information using REML analysis is discussed, although it is shown that it has very little impact if thc design is nearly orthogonally blocked. Finally prediction from blocked designs is considered and it is shown that prediction of many quantities of interest is much simpler than prediction of the response itself.

Global transcriptional response of Caulobacter crescentus to iron availability

BACKGROUND: In the alpha subclass of proteobacteria iron homeostasis is controlled by diverse iron responsive regulators. Caulobacter crescentus, an important freshwater α-proteobacterium, uses the ferric uptake repressor (Fur) for such purpose. However, the impact of the iron availability on the C. crescentus transcriptome and an overall perspective of the regulatory networks involved remain unknown. RESULTS: In this work we report the identification of iron-responsive and Fur-regulated genes in C. crescentus using microarray-based global transcriptional analyses. We identified 42 genes that were strongly upregulated both by mutation of fur and by iron limitation condition. Among them, there are genes involved in iron uptake (four TonB-dependent receptor gene clusters, and feoAB), riboflavin biosynthesis and genes encoding hypothetical proteins. Most of these genes are associated with predicted Fur binding sites, implicating them as direct targets of Fur-mediated repression. These data were validated by β-galactosidase and EMSA assays for two operons encoding putative transporters. The role of Fur as a positive regulator is also evident, given that 27 genes were downregulated both by mutation of fur and under low-iron condition. As expected, this group includes many genes involved in energy metabolism, mostly iron-using enzymes. Surprisingly, included in this group are also TonB-dependent receptors genes and the genes fixK, fixT and ftrB encoding an oxygen signaling network required for growth during hypoxia. Bioinformatics analyses suggest that positive regulation by Fur is mainly indirect. In addition to the Fur modulon, iron limitation altered expression of 113 more genes, including induction of genes involved in Fe-S cluster assembly, oxidative stress and heat shock response, as well as repression of genes implicated in amino acid metabolism, chemotaxis and motility. CONCLUSIONS: Using a global transcriptional approach, we determined the C. crescentus iron stimulon. Many but not all of iron responsive genes were directly or indirectly controlled by Fur. The iron limitation stimulon overlaps with other regulatory systems, such as the RpoH and FixK regulons. Altogether, our results showed that adaptation of C. crescentus to iron limitation not only involves increasing the transcription of iron-acquisition systems and decreasing the production of iron-using proteins, but also includes novel genes and regulatory mechanisms

Medication errors in a swiss cardiovascular surgery department: a cross-sectional study based on a novel medication error report method

The purpose of this study was (1) to determine frequency and type of medication errors (MEs), (2) to assess the number of MEs prevented by registered nurses, (3) to assess the consequences of ME for patients, and (4) to compare the number of MEs reported by a newly developed medication error self-reporting tool to the number reported by the traditional incident reporting system. We conducted a cross-sectional study on ME in the Cardiovascular Surgery Department of Bern University Hospital in Switzerland. Eligible registered nurses (n = 119) involving in the medication process were included. Data on ME were collected using an investigator-developed medication error self reporting tool (MESRT) that asked about the occurrence and characteristics of ME. Registered nurses were instructed to complete a MESRT at the end of each shift even if there was no ME. All MESRTs were completed anonymously. During the one-month study period, a total of 987 MESRTs were returned. Of the 987 completed MESRTs, 288 (29%) indicated that there had been an ME. Registered nurses reported preventing 49 (5%) MEs. Overall, eight (2.8%) MEs had patient consequences. The high response rate suggests that this new method may be a very effective approach to detect, report, and describe ME in hospitals.

Model Evaluation Based on the Distribution of Estimated Absolute Prediction Error

The construction of a reliable, practically useful prediction rule for future response is heavily dependent on the "adequacy" of the fitted regression model. In this article, we consider the absolute prediction error, the expected value of the absolute difference between the future and predicted responses, as the model evaluation criterion. This prediction error is easier to interpret than the average squared error and is equivalent to the mis-classification error for the binary outcome. We show that the distributions of the apparent error and its cross-validation counterparts are approximately normal even under a misspecified fitted model. When the prediction rule is "unsmooth", the variance of the above normal distribution can be estimated well via a perturbation-resampling method. We also show how to approximate the distribution of the difference of the estimated prediction errors from two competing models. With two real examples, we demonstrate that the resulting interval estimates for prediction errors provide much more information about model adequacy than the point estimates alone.

Implementation status of error disclosure standards reported by Swiss hospitals

QUESTION UNDER STUDY To establish at what stage Swiss hospitals are in implementing an internal standard concerning communication with patients and families after an error that resulted in harm. METHODS Hospitals were identified via the Swiss Hospital Association's website. An anonymous questionnaire was sent during September and October 2011 to 379 hospitals in German, French or Italian. Hospitals were asked to specify their hospital type and the implementation status of an internal hospital standard that decrees that patients or their relatives are to be promptly informed about medical errors that result in harm. RESULTS Responses from a total of 205 hospitals were received, a response rate of 54%. Most responding hospitals (62%) had an error disclosure standard or planned to implement one within 12 months. The majority of responding university and acute care (75%) hospitals had introduced a disclosure standard or were planning to do so. In contrast, the majority of responding psychiatric, rehabilitation and specialty (53%) clinics had not introduced a standard. CONCLUSION It appears that Swiss hospitals are in a promising state in providing institutional support for practitioners disclosing medical errors to patients. This has been shown internationally to be one important factor in encouraging the disclosure of medical errors. However, many hospitals, in particular psychiatric, rehabilitation and specialty clinics, have not implemented an error disclosure policy. Further research is needed to explore the underlying reasons.

A BAYESIAN APPROACH TO DOSE-RESPONSE ASSESSMENT AND DRUG-DRUG INTERACTION ANALYSIS: APPLICATION TO IN VITRO STUDIES

The considerable search for synergistic agents in cancer research is motivated by the therapeutic benefits achieved by combining anti-cancer agents. Synergistic agents make it possible to reduce dosage while maintaining or enhancing a desired effect. Other favorable outcomes of synergistic agents include reduction in toxicity and minimizing or delaying drug resistance. Dose-response assessment and drug-drug interaction analysis play an important part in the drug discovery process, however analysis are often poorly done. This dissertation is an effort to notably improve dose-response assessment and drug-drug interaction analysis. The most commonly used method in published analysis is the Median-Effect Principle/Combination Index method (Chou and Talalay, 1984). The Median-Effect Principle/Combination Index method leads to inefficiency by ignoring important sources of variation inherent in dose-response data and discarding data points that do not fit the Median-Effect Principle. Previous work has shown that the conventional method yields a high rate of false positives (Boik, Boik, Newman, 2008; Hennessey, Rosner, Bast, Chen, 2010) and, in some cases, low power to detect synergy. There is a great need for improving the current methodology. We developed a Bayesian framework for dose-response modeling and drug-drug interaction analysis. First, we developed a hierarchical meta-regression dose-response model that accounts for various sources of variation and uncertainty and allows one to incorporate knowledge from prior studies into the current analysis, thus offering a more efficient and reliable inference. Second, in the case that parametric dose-response models do not fit the data, we developed a practical and flexible nonparametric regression method for meta-analysis of independently repeated dose-response experiments. Third, and lastly, we developed a method, based on Loewe additivity that allows one to quantitatively assess interaction between two agents combined at a fixed dose ratio. The proposed method makes a comprehensive and honest account of uncertainty within drug interaction assessment. Extensive simulation studies show that the novel methodology improves the screening process of effective/synergistic agents and reduces the incidence of type I error. We consider an ovarian cancer cell line study that investigates the combined effect of DNA methylation inhibitors and histone deacetylation inhibitors in human ovarian cancer cell lines. The hypothesis is that the combination of DNA methylation inhibitors and histone deacetylation inhibitors will enhance antiproliferative activity in human ovarian cancer cell lines compared to treatment with each inhibitor alone. By applying the proposed Bayesian methodology, in vitro synergy was declared for DNA methylation inhibitor, 5-AZA-2'-deoxycytidine combined with one histone deacetylation inhibitor, suberoylanilide hydroxamic acid or trichostatin A in the cell lines HEY and SKOV3. This suggests potential new epigenetic therapies in cell growth inhibition of ovarian cancer cells.

Evaluating a medical error taxonomy

Healthcare has been slow in using human factors principles to reduce medical errors. The Center for Devices and Radiological Health (CDRH) recognizes that a lack of attention to human factors during product development may lead to errors that have the potential for patient injury, or even death. In response to the need for reducing medication errors, the National Coordinating Council for Medication Errors Reporting and Prevention (NCC MERP) released the NCC MERP taxonomy that provides a standard language for reporting medication errors. This project maps the NCC MERP taxonomy of medication error to MedWatch medical errors involving infusion pumps. Of particular interest are human factors associated with medical device errors. The NCC MERP taxonomy of medication errors is limited in mapping information from MEDWATCH because of the focus on the medical device and the format of reporting.

Design and analysis for three level hierarchical structures with count response

In numerous intervention studies and education field trials, random assignment to treatment occurs in clusters rather than at the level of observation. This departure of random assignment of units may be due to logistics, political feasibility, or ecological validity. Data within the same cluster or grouping are often correlated. Application of traditional regression techniques, which assume independence between observations, to clustered data produce consistent parameter estimates. However such estimators are often inefficient as compared to methods which incorporate the clustered nature of the data into the estimation procedure (Neuhaus 1993).1 Multilevel models, also known as random effects or random components models, can be used to account for the clustering of data by estimating higher level, or group, as well as lower level, or individual variation. Designing a study, in which the unit of observation is nested within higher level groupings, requires the determination of sample sizes at each level. This study investigates the design and analysis of various sampling strategies for a 3-level repeated measures design on the parameter estimates when the outcome variable of interest follows a Poisson distribution. ^ Results study suggest that second order PQL estimation produces the least biased estimates in the 3-level multilevel Poisson model followed by first order PQL and then second and first order MQL. The MQL estimates of both fixed and random parameters are generally satisfactory when the level 2 and level 3 variation is less than 0.10. However, as the higher level error variance increases, the MQL estimates become increasingly biased. If convergence of the estimation algorithm is not obtained by PQL procedure and higher level error variance is large, the estimates may be significantly biased. In this case bias correction techniques such as bootstrapping should be considered as an alternative procedure. For larger sample sizes, those structures with 20 or more units sampled at levels with normally distributed random errors produced more stable estimates with less sampling variance than structures with an increased number of level 1 units. For small sample sizes, sampling fewer units at the level with Poisson variation produces less sampling variation, however this criterion is no longer important when sample sizes are large. ^ 1Neuhaus J (1993). “Estimation efficiency and Tests of Covariate Effects with Clustered Binary Data”. Biometrics , 49, 989–996^

In the aftermath of medical error : Caring for patients, family, and the healthcare workers involved

Medical errors, in particular those resulting in harm, pose a serious situation for patients ("first victims") and the healthcare workers involved ("second victims") and can have long-lasting and distressing consequences. To prevent a second traumatization, appropriate and empathic interaction with all persons involved is essential besides error analysis. Patients share a nearly universal, broad preference for a complete disclosure of incidents, regardless of age, gender, or education. This includes the personal, timely and unambiguous disclosure of the adverse event, information relating to the event, its causes and consequences, and an apology and sincere expression of regret. While the majority of healthcare professionals generally support and honest and open disclosure of adverse events, they also face various barriers which impede the disclosure (e.g., fear of legal consequences). Despite its essential importance, disclosure of adverse events in practice occurs in ways that are rarely acceptable to patients and their families. The staff involved often experiences acute distress and an intense emotional response to the event, which may become chronic and increase the risk of depression, burnout and post-traumatic stress disorders. Communication with peers is vital for people to be able to cope constructively and protectively with harmful errors. Survey studies among healthcare workers show, however, that they often do not receive sufficient individual and institutional support. Healthcare organizations should prepare for medical errors and harmful events and implement a communication plan and a support system that covers the requirements and different needs of patients and the staff involved.

Functional error modeling for uncertainty quantification in hydrogeology

Approximate models (proxies) can be employed to reduce the computational costs of estimating uncertainty. The price to pay is that the approximations introduced by the proxy model can lead to a biased estimation. To avoid this problem and ensure a reliable uncertainty quantification, we propose to combine functional data analysis and machine learning to build error models that allow us to obtain an accurate prediction of the exact response without solving the exact model for all realizations. We build the relationship between proxy and exact model on a learning set of geostatistical realizations for which both exact and approximate solvers are run. Functional principal components analysis (FPCA) is used to investigate the variability in the two sets of curves and reduce the dimensionality of the problem while maximizing the retained information. Once obtained, the error model can be used to predict the exact response of any realization on the basis of the sole proxy response. This methodology is purpose-oriented as the error model is constructed directly for the quantity of interest, rather than for the state of the system. Also, the dimensionality reduction performed by FPCA allows a diagnostic of the quality of the error model to assess the informativeness of the learning set and the fidelity of the proxy to the exact model. The possibility of obtaining a prediction of the exact response for any newly generated realization suggests that the methodology can be effectively used beyond the context of uncertainty quantification, in particular for Bayesian inference and optimization.

Developing an alternative response format for the script concordance test

Introduction: Clinical reasoning is essential for the practice of medicine. In theory of development of medical expertise it is stated, that clinical reasoning starts from analytical processes namely the storage of isolated facts and the logical application of the ‘rules’ of diagnosis. Then the learners successively develop so called semantic networks and illness-scripts which finally are used in an intuitive non-analytic fashion [1], [2]. The script concordance test (SCT) is an example for assessing clinical reasoning [3]. However the aggregate scoring [3] of the SCT is recognized as problematic [4]. The SCT`s scoring leads to logical inconsistencies and is likely to reflect construct-irrelevant differences in examinees’ response styles [4]. Also the expert panel judgments might lead to an unintended error of measurement [4]. In this PhD project the following research questions will be addressed: 1. How does a format look like to assess clinical reasoning (similar to the SCT but) with multiple true-false questions or other formats with unambiguous correct answers, and by this address the above mentioned pitfalls in traditional scoring of the SCT? 2. How well does this format fulfill the Ottawa criteria for good assessment, with special regards to educational and catalytic effects [5]? Methods: 1. In a first study it shall be assessed whether designing a new format using multiple true-false items to assess clinical reasoning similar to the SCT-format is arguable in a theoretically and practically sound fashion. For this study focus groups or interviews with assessment experts and students will be undertaken. 2. In an study using focus groups and psychometric data Norcini`s and colleagues Criteria for Good Assessment [5] shall be determined for the new format in a real assessment. Furthermore the scoring method for this new format shall be optimized using real and simulated data.

Apply response adaptive randomization to group sequential with early stopping

Group sequential methods and response adaptive randomization (RAR) procedures have been applied in clinical trials due to economical and ethical considerations. Group sequential methods are able to reduce the average sample size by inducing early stopping, but patients are equally allocated with half of chance to inferior arm. RAR procedures incline to allocate more patients to better arm; however it requires more sample size to obtain a certain power. This study intended to combine these two procedures. We applied the Bayesian decision theory approach to define our group sequential stopping rules and evaluated the operating characteristics under RAR setting. The results showed that Bayesian decision theory method was able to preserve the type I error rate as well as achieve a favorable power; further by comparing with the error spending function method, we concluded that Bayesian decision theory approach was more effective on reducing average sample size.^

Nurse likelihood to report a pediatric medication error: Examination of the "pre-reporting" period

Each year, hospitalized patients experience 1.5 million preventable injuries from medication errors and hospitals incur an additional $3.5 billion in cost (Aspden, Wolcott, Bootman, & Cronenwatt; (2007). It is believed that error reporting is one way to learn about factors contributing to medication errors. And yet, an estimated 50% of medication errors go unreported. This period of medication error pre-reporting, with few exceptions, is underexplored. The literature focuses on error prevention and management, but lacks a description of the period of introspection and inner struggle over whether to report an error and resulting likelihood to report. Reporting makes a nurse vulnerable to reprimand, legal liability, and even threat to licensure. For some nurses this state may invoke a disparity between a person‘s belief about him or herself as a healer and the undeniable fact of the error.^ This study explored the medication error reporting experience. Its purpose was to inform nurses, educators, organizational leaders, and policy-makers about the medication error pre-reporting period, and to contribute to a framework for further investigation. From a better understanding of factors that contribute to or detract from the likelihood of an individual to report an error, interventions can be identified to help the nurse come to a psychologically healthy resolution and help increase reporting of error in order to learn from error and reduce the possibility of future similar error.^ The research question was: "What factors contribute to a nurse's likelihood to report an error?" The specific aims of the study were to: (1) describe participant nurses' perceptions of medication error reporting; (2) describe participant explanations of the emotional, cognitive, and physical reactions to making a medication error; (3) identify pre-reporting conditions that make it less likely for a nurse to report a medication error; and (4) identify pre-reporting conditions that make it more likely for a nurse to report a medication error.^ A qualitative research study was conducted to explore the medication error experience and in particular the pre-reporting period from the perspective of the nurse. A total of 54 registered nurses from a large private free-standing not-for-profit children's hospital in the southwestern United States participated in group interviews. The results describe the experience of the nurse as well as the physical, emotional, and cognitive responses to the realization of the commission of a medication error. The results also reveal factors that make it more and less likely to report a medication error.^ It is clear from this study that upon realization that he or she has made a medication error, a nurse's foremost concern is for the safety of the patient. Fear was also described by each group of nurses. The nurses described a fear of several things including physician reaction, manager reaction, peer reaction, as well as family reaction and possible lack of trust as a result. Another universal response was the description of a struggle with guilt, shame, imperfection, blaming oneself, and questioning one's competence.^

Bayesian estimation of multilevel item response model with missing data

This study proposed a novel statistical method that modeled the multiple outcomes and missing data process jointly using item response theory. This method follows the "intent-to-treat" principle in clinical trials and accounts for the correlation between outcomes and missing data process. This method may provide a good solution to chronic mental disorder study. ^ The simulation study demonstrated that if the true model is the proposed model with moderate or strong correlation, ignoring the within correlation may lead to overestimate of the treatment effect and result in more type I error than specified level. Even if the within correlation is small, the performance of proposed model is as good as naïve response model. Thus, the proposed model is robust for different correlation settings if the data is generated by the proposed model.^

Diurnal fluctuations in seawater pH influence the response of a calcifying macroalga to ocean acidification

Coastal ecosystems that are characterized by kelp forests encounter daily pH fluctuations, driven by photosynthesis and respiration, which are larger than pH changes owing to ocean acidification (OA) projected for surface ocean waters by 2100. We investigated whether mimicry of biologically mediated diurnal shifts in pH-based for the first time on pH time-series measurements within a kelp forest-would offset or amplify the negative effects of OA on calcifiers. In a 40-day laboratory experiment, the calcifying coralline macroalga, Arthrocardia corymbosa, was exposed to two mean pH treatments (8.05 or 7.65). For each mean, two experimental pH manipulations were applied. In one treatment, pH was held constant. In the second treatment, pH was manipulated around the mean (as a step-function), 0.4 pH units higher during daylight and 0.4 units lower during darkness to approximate diurnal fluctuations in a kelp forest. In all cases, growth rates were lower at a reduced mean pH, and fluctuations in pH acted additively to further reduce growth. Photosynthesis, recruitment and elemental composition did not change with pH, but ?(13)C increased at lower mean pH. Including environmental heterogeneity in experimental design will assist with a more accurate assessment of the responses of calcifiers to OA.