MyMedR

Displaying all 4 publications

Abstract:

Sort:

Zero-inflated Conway-Maxwell Poisson Distribution to Analyze Discrete Data

Sim SZ, Gupta RC, Ong SH

Int J Biostat, 2018 Jan 09;14(1).
PMID: 29306919 DOI: 10.1515/ijb-2016-0070

In this paper, we study the zero-inflated Conway-Maxwell Poisson (ZICMP) distribution and develop a regression model. Score and likelihood ratio tests are also implemented for testing the inflation/deflation parameter. Simulation studies are carried out to examine the performance of these tests. A data example is presented to illustrate the concepts. In this example, the proposed model is compared to the well-known zero-inflated Poisson (ZIP) and the zero- inflated generalized Poisson (ZIGP) regression models. It is shown that the fit by ZICMP is comparable or better than these models.

Matched MeSH terms: Biostatistics/methods*
Fulltext Teaching Epidemiology and Biostatistics: a peer-led teaching module for postgraduate psychiatry student

Pang,Nicholas Tze Ping, Koh,Eugene Boon Yau, Sandi James, Mohd Amiruddin Mohd Kassim

Borneo Epidemiology Journal, 2020;1(2):157-162.
MyJurnal

Background and Objective: Biostatistics and epidemiology have been integral subjects in any postgraduate courses, including medical specialties Master programs. Both are widely accepted as among the difficult and confusing subjects, which worsen by lack of adequate exposure and often, time constraints. Hence, peer-led learning approach was proposed as a viable option to the traditional lecturer-driven learning style
Method: The peer-led approach intends to promote targeted learning and conceptual understanding, instead of widely sweeping learning, which is rather directionless and could cause information overload
Discussion: Students were divided into two groups, namely humanities-inclined group and science inclined group. Different pedagogical methods to address the different groups were discussed.
Conclusion: This approach helps to make the learning more palatable, boosting knowledge retention and fostering camaraderie spirit among colleagues

Matched MeSH terms: Biostatistics
Evaluation of model-based methods in estimating respiratory mechanics in the presence of variable patient effort

Redmond DP, Chiew YS, Major V, Chase JG

Comput Methods Programs Biomed, 2019 Apr;171:67-79.
PMID: 27697371 DOI: 10.1016/j.cmpb.2016.09.011

Monitoring of respiratory mechanics is required for guiding patient-specific mechanical ventilation settings in critical care. Many models of respiratory mechanics perform poorly in the presence of variable patient effort. Typical modelling approaches either attempt to mitigate the effect of the patient effort on the airway pressure waveforms, or attempt to capture the size and shape of the patient effort. This work analyses a range of methods to identify respiratory mechanics in volume controlled ventilation modes when there is patient effort. The models are compared using 4 Datasets, each with a sample of 30 breaths before, and 2-3 minutes after sedation has been administered. The sedation will reduce patient efforts, but the underlying pulmonary mechanical properties are unlikely to change during this short time. Model identified parameters from breathing cycles with patient effort are compared to breathing cycles that do not have patient effort. All models have advantages and disadvantages, so model selection may be specific to the respiratory mechanics application. However, in general, the combined method of iterative interpolative pressure reconstruction, and stacking multiple consecutive breaths together has the best performance over the Dataset. The variability of identified elastance when there is patient effort is the lowest with this method, and there is little systematic offset in identified mechanics when sedation is administered.

Matched MeSH terms: Biostatistics*
Fulltext Assessing the perceptions of a biostatistics and epidemiology module: views of Year 2 medical students from a Malaysian university. A cross-sectional survey

Daher AM, Amin F

BMC Med Educ, 2010 May 13;10:34.
PMID: 20462464 DOI: 10.1186/1472-6920-10-34

BACKGROUND: In the era of evidence based medicine, biostatistics and epidemiology are considered as the main elements aiding the health professional to design a research study, understand the literature, and make decisions about patient care. The aim of the study is to explore students' perception about this subject because it plays an important role in determining educational outcome.
METHODS: Data were collected from a self-administered questionnaire distributed among 164 Year 2 medical students. The 5-point Likert scale anchored by Strongly disagree = 1 and Strongly agree = 5 included 36 questions in four domains designed to assess the perception of a biostatistics and epidemiology module amongst students.
RESULTS: 138 students with ages ranging from 20 to 24 years (Mean = 20.7; SD = 0.62) returned their responses to the questionnaire. This was a response rate of 84.14%. Of the 138 students, 80.7% realized the relevance of the subject to real health issues at the end of the module, while 89.8% believed the module focused on interpretation more than calculation.More than three quarters (78.1%) agreed that lack of practicing exercises was the cause for declining interest in the subject, while only 26.1% believed that lectures were not interesting. Another three quarters (75.4%) believed that there were too many lectures for one day of teaching activities, while 84.6% recommended practical sessions for designing research and data collection.
CONCLUSIONS: This study found that students perceived the relevance of biostatistics and epidemiology to real health issues. The major cause of poor interest in the subject was attributed to the short duration of the course, lack of practicing exercises, and the need for practical data collection sessions. Emphasis should be given to early introduction of projects for data collection and analysis.

Matched MeSH terms: Biostatistics*