Understanding applicability of PSM, roadmap-usage and effect.

Simple data envelopment analysis where comparing groups' efficiency based on "relative efficiency" score. Input and output optimal values can be seen for inefficient DMUs compared to the efficient ones.

Evaluation of the machine learning models with checking the assumptions and any violations on these assumptions and checking performance metrics. Thus step by step model evaluation over the assumption may reveal the if there can be a core improvements over models as correcting the violations.

Multiple linear regression with real life data, part 2 of the exercises.

One main and four sub cases has been researched for data set. Main research is the selection of features that can enter the clustering algorithm. Two methods has been used; stepwise and information gain. Sub researchs are; - Binary dependent variable clustering with logistic regression and KNN. - Non-binary dependent variable clustering with KNN and SVM.

RMD plot exercises by shinyapp.

Peer-graded Assignment: R Markdown Presentation & Plotly

The Impact of Weather Events on US Population Health and Economy