Fit kNN and tree based methods using the caret package to predict if a patient will have heart disease or not.

Fit and predict with multiple linear regression models and, similarly, with logistic regression models.

Implement one-sample t-test and execute a Monte Carlo study to compare sequential and parallel computing performance.

Summarize the horseshoe crab data numerically and graphically. Perform exploratory data analysis (EDA) to identify general patterns in the data.

A new algorithm has been developed by Prof. Hayes in order to estimate variances of a model parameter based on perturbation of the best fitted parameter. This algorithm has been claimed to give a good assessment of the standard error of the model parameter. The obtained results have been published in several research articles. This work is to reproduce the algorithm and compare it with the other common statistics methods including nonlinear regression models, bootstrap confidence intervals and the delta normality method.

Contact a restful API to query and parse movie info from the open movie database. Perform data transformation and summarization.

Create a Monte Carlo simulation study in R to investigate properties of estimators and confidence intervals (CIs).

Create and implement a Markov chain Monte Carlo (MCMC) sampler in R for a logistic regression model.

Use Likelihood Ratio Test (LRT) to conduct a chi-square test for homogeneity and compare it with a Monte Carlo simulation.