Women in Statistics Conference 2014

May 14th, 2014

Tatsiana Maskalevich, Data Scientist and Rachel Poulsen, Data Scientist will be presenting at the inaugural Women In Statistics conference being held in Cary, North Carolina from May 15-17, 2014 (https://women-instats.org/).

Tatsiana will be presenting Gerrymandering and Political Gridlock in the US.  In recent decades gerrymandering has become an effective tactic to guarantee the outcomes of general elections. This poster explains how we analyzed gerrymandering. By combining district compactness — the ratio of the shape’s area to its perimeter — with Partisan Voting Index data we compared Congressional Districts based on the voting patterns of their constituents.  We concluded that the swing districts are less gerrymandered than the party-aligned ones.

Rachel will be presenting Application of Statistical Learning: Segmentation and Classification. Statistical learning algorithms are found in many applications. One type of statistical learning uses a combination of the multivariate statistical techniques of segmentation and classification. This poster will review the segmentation techniques of hierarchical and K-means clustering using R, discuss their benefits and challenges, and build a classification model for future assignment of new observations.