Statistical Analysis & Forecasting

Descriptive and predictive analytics in R: PCA, clustering, ARIMA and ETS forecasting and multivariate modeling, all reported through RMarkdown.

Source on GitHub

A random walk with drift forecast of the gold price: the intervals widen the further ahead it looks.Open full size: A random walk with drift forecast

A coursework-driven project that exercises the full descriptive-to-predictive analytics workflow in R. Includes dimensionality reduction via PCA, k-means clustering, ARIMA and ETS forecasting on real time series, and multivariate modeling, all packaged as reproducible RMarkdown reports.

Figures

Gold price over five decades: flat for twenty years, then a climb past 1,500.Open full size: Gold price over five decades: flat

RMSE by forecast horizon for five models: ARIMA stays lowest, while ETS error grows fastest, to nearly 2,000 at the longest horizon.Open full size: RMSE by forecast horizon for five

PCA of European countries, colored by k-means cluster.Open full size: PCA of European countries, colored by

Correspondence

Research, data science work or a question about a project. Email, LinkedIn or the contact form all reach me.

mawangot2000@gmail.com LinkedIn

There is also a contact form, and aresume (PDF).