With all the news about vaccine efficacy and how long the effects of the vaccine will last, it is interesting to wonder how the statistical models to detect such effects are designed for such research . In the Khoury et al paper (2020), they do consider the decay of antibody titers over time in their cohort of subjects, through a linear mixed effects model with exponential decay. Their interpretations of these decaying effects from the model are somewhat unclear and are somewhat muddied by their other main results in their paper. …
Re-analyses on vaccine efficacy in COVID-19 research
Much of the news these days focuses on vaccine efficacy rates being re-updated due to various new COVID-19 variants coming out often, originating in different countries, like delta (B.1.167.2) from India and lambda (C.37) from Peru. These vaccine rates are being re-updated and re-analyzed, but not very much is discussed about how these rates are constantly analyzed and assessed. What population of data ends up being used for re-analyses? If the data is used from another country, how can the results be generalized to the United States?
The Saul et al article below…
Bayesian methods used in COVID-19 research
During the times of uncertainty in statistical methods used in COVID-19 research. Were Bayesian methods employed much in these contexts? Yes they were here and there but probably once again, just like in regular research, the methods were not used very often or were put as secondary analyses, possibly out of fear of the public not understanding the methods. They also did not seem to be used in the comparisons of vaccinated and control groups in clinical trials of the major vaccines that have been in the news and even administered.
The question is…
by Usha Govindarajulu | Jun 9, 2021 | Biostatistics, Blog, Healthcare, Professor, Usha Govindarajulu
P-values and vaccine efficacy
As the companies continue to re-evaluate vaccine efficacy against new variants, have they discussed p-values? Are they analyzing re-updated data again and again and correcting for inflation of the Type I error rate?? Given the p-value controversy in statistics and the controversy of vaccine efficacy, statisticians have to wonder if these topics have been considered together. Even if this topic is being considered, it is hardly discussed. One can only imagine it must have been very difficult to plan these trials and…
COVID-19 challenges of publishing statistically relevant studies
COVID-19 is a tricky period in which to attempt to publish new studies. Criticism came from reviewers and those reading the articles whether or not one showed negative results or positive results from the study. In fact, due to the ongoing situation with the pandemic, much criticism has been given to any potential positive results since other articles had been published with results that were not accurate. It has been a very difficult time period then for perhaps well designed studies even to get published due to the bias in the media against…
Can one control for selection bias in analyses? Unfortunately selection bias is inherent to many studies, even the gold standard clinical trial designs, but these problems can be attempted to be controlled for in analyses. In COVID-19 research especially, there are selection bias issues related to selection of patients in studies, often the less sicker of patients and also those who are willing to volunteer. All these and other issues can cause selection bias in COVID-19 research. …
Missing data
Missing data is a phenomenon that happens in almost all studies whether in observational or clinical trials. It most often occurs in studies that involve long-term follow up, where people miss different follow up visits or exit the study for various reasons. This results in problems with analyzing data, especially if there is a lot of missingness or if there is a pattern to the missingness and it did not occur randomly.
Missing data happened in COVID-19 data and continues to do so. Initially missing data happened in the beginning when it was hard to collect all measurements…
Issues in COVID-19 research and statistical analyses (Part II)
In the article previous to this, Part I, we discussed design and statistical issues related to clinical trial designs for COVID-19 research. As part of the discussion about clinical trial designs comes along interpretation of results. As clinical trials for COVID-19 vaccine trials have continued into Phase III, eventually early promising results were released about efficacy about certain vaccines. This information was released to the general public but this also brought about a lot of confusion.
The general public simply was unable to grasp the results of the efficacy or effectiveness…
Earlier we discussed the issues in COVID-19 research related to observational studies that were used as the study design for the research, especially the early time frame of COVID-19 in the U.S. like the spring of 2020. We discussed some of the overarching issues that had plagued some of these designs for this research. The other study design that was thought to be better than observational studies for interventions have been clinical trials. After the push back last spring from major journals of not accepting observational studies, more people designed randomized trials to test interventions for COVID-19. Many researchers worked…
Issues in COVID-19 research and statistical analyses
Doing research in COVID-19 presents many types of problems for having statistical analyses free from biases. In studies that were organized as observational studies to compare treatments or differences on some outcome between COVID-19 patients and either some type of control or less sick COVID-19 patients, many inherit biases came to play. In general, these studies tend to suffer from baseline differences between comparison and control groups which lead to confounding and other biases, which can also be present in these study designs. …
