# Latest Posts

Relating the binomial and Poisson distributions The binomial and Poisson distributions are equivalent under a limit. This is a helpful interpretation. Recall, precision, specificity, and sensitivity Illustration of recall, precision, specificity, and sensitivity Periodic functions as art Mathematics in an art museum. Noria, a wheely Xe-selective solid We found porous organic cage solid Noria to be selective for xenon over krypton. Computationally-inspired material discovery We used computer simulations to sift through thousands of materials; we predicted that SBMOF-1 would selectively adsorb xenon over krypton. Experiments affirm that it does. So you think you can count? Permutations and combinations Nested loops via recursion An example of recursion On funding curiosity-driven research Lessons from CRISPR Computing the heat of adsorption in a grand canonical Monte Carlo simulation Where does the fluctuation formula come from? Matplotlib markers Visualization of markers in Matplotlib Bravais lattice and its reciprocal lattice Bravais lattice An argument for basic research Funding basic research is imperative for scientific and societal progress Water is the wrong focus for water conservation As consumers, most should focus on food instead. Accelerating Materials Discovery with CUDA Running molecular simulations on GPUs with the CUDA programming language has accelerated our research progress. Honey Bees and Materials Science A connection between honey bees and a nanoporous material Computer-aided search for materials to store natural gas for vehicles Computer simulations can help discover sponge-like materials to store natural gas onboard vehicles How a parameter affects a function in the IJulia Notebook Using Interact.jl and Gadfly.jl to visualize how changing a parameter affects a function. We eat most of the water that we consume We cannot see most of the water that we consume. Using standard atom colors in Matplotlib Color your plots consistently with structure visualization tools How big is the tip of the iceberg? We can use a back-of-the-envelope calculation to estimate the fraction of an iceberg that is submerged in water. Job control in Bash Running jobs in parallel using the Bash shell Generating uniformly distributed numbers on a sphere Generating uniformly distributed numbers on a sphere Proof by beads 1+2+...+(n-1)+n+(n-1)+...+2+1=n ^{2}has a nice geometric proofDoes having a PhD hurt your dating prospects? Dating app Coffee Meets Bagel releases data on percentage of times a person is liked given his or her level of education. Feature importance in random forests when features are correlated Correlations between features affect feature importance measures in random forests. Parallel Monte Carlo in Julia A tutorial on parallel computing capabilities of Julia. Computing pi with a Monte Carlo simulation. Musings on correlation and causality Correlation does not imply causation. The memoryless Poisson process and volcano insurance The Poisson process is a memoryless point process, where the history has no impact on future outcomes. ROC curves to evaluate binary classification algorithms A receiver operator characteristic (ROC) curve depicts the performance of a binary classification algorithm as the classification threshold is varied. The Mathematics Behind the Ebola Epidemic A discussion of the ordinary differential equations used to model the progression of the epola epidemic and forecast cases. A metric for inequality: the Gini coefficient We can measure income inequality by statements such as `the top 10% of the population earns 50.4% of the pre-tax income`. The Gini coefficient is a single number that encapsulates many such statements. Save water, shower together We cannot see most of our water consumption. Berkson's Paradox: Are handsome men really jerks? The stereotype that handsome men tend to be jerks could be a result of selection bias. The intuition is that we may tolerate rudeness if looks make up for it! XKCD: Frequentist vs. Bayesian Statistics XKCD comic about frequentist vs. Bayesian statistics explained. Voronoi cookies and the post office problem The cookies that I baked formed a Voronoi diagram. The Voronoi diagram is a useful mathematical tool. Your lovers probably had more lovers than you (this is math) While it seems paradoxical, your sexual partners have probably had more sexual partners than you have. Think about it: you are more likely to sleep with someone who sleeps with a lot of people. Trees come from air People look at a tree and think it comes out of the ground, but, trees come from air. -Richard Feynman By how many flights should an airline overbook? Airlines sell more tickets than the capacity of the flight and hope that just enough customers show up to get a full flight. By how much should the airline oversell to maximize profits? The Principle of Maximum Entropy The principle of maximum entropy is that we should model our process with the probability distribution that contains the most amount of unpredictability. This is under the constraints of the distribution satisfying the information that we do know about our process, of course. Why Cocaine Users Should Learn Bayes' Theorem Even when a diagnostic test for a disease or drug has a high accuracy, the false positives can outnumber the true positives when the incidence of the disease or drug use is low. Simpson's Paradox In 1973, UC Berkeley was sued for discrimination against women in graduate school admissions. If we take a closer look at the admissions data, we find that this is a case of Simpson's Paradox.