Distractions and amusements, with a sandwich and coffee.
I collaborated with Scientific American to create a data graphic for the September 2014 issue. The graphic compared the genomes of the Denisovan, bonobo, chimp and gorilla, showing how our own genomes are almost identical to the Denisovan and closer to that of the bonobo and chimp than the gorilla.
Here you'll find Hilbert curve art, a introduction to Hilbertonians, the creatures that live on the curve, an explanation of the Scientific American graphic and downloadable SVG/EPS Hilbert curve files.
Hilbertonians are creatures that live in the depths of the Hilbert curve. They live across three adjacent orders of the curve (e.g. 2, 3, 4). The come in many different personalities and many classes exist.
They are social—they always appear in multiples of 4. This is a consequence of how they are defined. A single Hilbertonian has never been seen.
Their genomes are 20 bases long. They only have 2 different types of bases. Out of a possible 220 = 1,048,576 genomes, only 104,976 (almost exactly 10%) produce living and breathing Hilbertonians, defined as those whose bodies form a contiguous shape. The other 943,600 are unfortunately unviable. The genomes of every Hilbertonian can be downloaded.
We demand rigidly defined areas of doubt and uncertainty! —D. Adams
A popular notion about experiments is that it's good to keep variability in subjects low to limit the influence of confounding factors. This is called standardization.
Unfortunately, although standardization increases power, it can induce unrealistically low variability and lead to results that do not generalize to the population of interest. And, in fact, may be irreproducible.
Not paying attention to these details and thinking (or hoping) that standardization is always good is the "standardization fallacy". In this column, we look at how standardization can be balanced with heterogenization to avoid this thorny issue.
Voelkl, B., Würbel, H., Krzywinski, M. & Altman, N. (2021) Points of significance: Standardization fallacy. Nature Methods 18:5–6.
Clear, concise, legible and compelling.
Making a scientific graphical abstract? Refer to my practical design guidelines and redesign examples to improve organization, design and clarity of your graphical abstracts.
An in-depth look at my process of reacting to a bad figure — how I design a poster and tell data stories.
Building on the method I used to analyze the 2008, 2012 and 2016 U.S. Presidential and Vice Presidential debates, I explore word usagein the 2020 Debates between Donald Trump and Joe Biden.
We are celebrating the publication of our 50th column!
To all our coauthors — thank you and see you in the next column!
When modelling epidemics, some uncertainties matter more than others.
Public health policy is always hampered by uncertainty. During a novel outbreak, nearly everything will be uncertain: the mode of transmission, the duration and population variability of latency, infection and protective immunity and, critically, whether the outbreak will fade out or turn into a major epidemic.
The uncertainty may be structural (which model?), parametric (what is `R_0`?), and/or operational (how well do masks work?).
This month, we continue our exploration of epidemiological models and look at how uncertainty affects forecasts of disease dynamics and optimization of intervention strategies.
We show how the impact of the uncertainty on any choice in strategy can be expressed using the Expected Value of Perfect Information (EVPI), which is the potential improvement in outcomes that could be obtained if the uncertainty is resolved before making a decision on the intervention strategy. In other words, by how much could we potentially increase effectiveness of our choice (e.g. lowering total disease burden) if we knew which model best reflects reality?
This column has an interactive supplemental component (download code) that allows you to explore the impact of uncertainty in `R_0` and immunity duration on timing and size of epidemic waves and the total burden of the outbreak and calculate EVPI for various outbreak models and scenarios.
Bjørnstad, O.N., Shea, K., Krzywinski, M. & Altman, N. (2020) Points of significance: Uncertainty and the management of epidemics. Nature Methods 17.
Bjørnstad, O.N., Shea, K., Krzywinski, M. & Altman, N. (2020) Points of significance: Modeling infectious epidemics. Nature Methods 17:455–456.
Bjørnstad, O.N., Shea, K., Krzywinski, M. & Altman, N. (2020) Points of significance: The SEIRS model for infectious disease dynamics. Nature Methods 17:557–558.