The Mixture Index of Fit and Quick Shiny

NOTE: This will be an English-speaking meetup. The 'Tiszta kódolás R-ben' event has been postponed to 29th April.

We will have two presentations on this Wednesday - a deeper and a lighter.

Juraj Medzihorsky (CEU): pistar, an R package for the Pi* mixture index of fit.

Juraj will speak about his R package and its applications. The Pi* mixture index of fit is a new measure of model fit. It is easy to interpret, applies to many different models, and unlike conventional measures of fit it rests on assumptions that are always true. The index measures model fit by the smallest fraction of the population that cannot be described perfectly by a distribution belonging to the model, and facilitates new substantive findings through the analysis of the residual component. The pistar (https://github.com/jmedzihorsky/pistar) package currently allows to estimate Pi* for univariate distributions, multivariate normal distribution, and all models which input and predict values representable as contingency tables.

Imre Kocsis (Quanopt): Tales from the Trenches: Applying Shiny Quick and Dirty

We would like to introduce a series beginning with the one below, to spotlight the community's favorite R recipes, quick and dirty hacks, tricks and tips. This pilot episode operates with the shiny package and shows a quick way to overview our data.