Many branches of the industry are joining the hype around using deep neural networks or complex machine learning approaches, eg gradient boosting machines, random forests. However, I am sceptical that these “black box” algorithms will make major contributions to drug development, since the problems in clinical trials seems conceptually different from, eg image or speech…
In randomized controlled clinical trials, the confounding of the treatment with other factors (sex, age, other patient characteristics) at baseline is of crucial importance as well as maintaining the integrity of the treatment during the trial. However, an important uncontrolled factor violating the integrity of the treatment is patient behaviour, especially in response to his…
Immuno-oncology drugs stimulate the immune-system of the patient to fight cancer cells. These effects might be enhanced by using Pawlowing conditioning of external stimuli to the drug. For example, Pawlow demonstrated that by exposing dogs (cf patients) to the ringing of a bell (eg white coat of clinician) during feeding time, the unconditioned reaction of…
The following paper is a breakthrough in facial feature recognition and numeric representation of facial features and may be helpful to understand the genomic basis of facial features (once the relevant dimensions of the phenome are identified), but also to help to recognize the emotional expression in human faces [1,2]. [1] http://www.cell.com/cell/fulltext/S0092-8674(17)30538-X [2] http://www.bbc.co.uk/news/science-environment-4013124
KAGGLE’s newest predictive analytics competition on improving the Zillow’s Home Value Prediction with an overall prize money of $1,200,000 is currently the talk of the town and has attracted 716 teams ·(7 months to go, 4 months to go until merger deadline) [1]. Are you interested in joining my team? [1] https://www.kaggle.com/c/zillow-prize-1/data
David Spiegelhalter gave inspiring and entertaining talk on “Engaging without manipulating: the balanced communication of statistics” at PSI 2017 conference in London. Obviously, scientific results are often miscommunicated by mass media to boost the novelity and relevance of scientific results. After David’s talk I raised the question whether addressing the questions who owns the results…
Rstudio has recently released (2017-01) their Rstudio connect platform for deployment of software and reports, which I am currently evaluating: Quote: RStudio Connect is a new publishing platform for the work your teams create in R. Share Shiny applications, R Markdown reports, dashboards, plots, and more in one convenient place. Use push-button publishing from the…
I recently got my hands on Bayesian Belief Networks to model multi-dimensional decision problems, which include objective and subjective data (“beliefs”) with varying degrees of under uncertainty. To choose a (non)trivial example one can look at the question “Does she/he like me?” after you met this attractive person, randomly picking the same book on machine…
Considering the success in of Gradient boosting machines in machine learning, one might think of the application of the same principle to elections. The rationale behind it being that voters may have changed their vote conditioned on the knowledge of the current power distribution is. Unconditional voting may lead to power distributions which may be…
If you want to find out, that you share quite a lot of confusion regarding the estimand concept with the RSS/PSI experts, I recommend listening to the audio recording of the RSS/PSI journal club on estimands from 2016-07-06 on YouTube [1]. Personally, I think that much of the confusion around the estimand concept (except not…