# CPAT and the Rényi-Type Statistic; End-of-Sample Change Point Detection in R

This article is also available in PDF form.

# Introduction

I started my first research project as a graduate student when I was only in the MSTAT program at the University of Utah, at the very end of 2015 (or very beginning of 2016; not sure exactly when) with my current advisor, Lajos Horváth. While I am disappointed it took this long, I am glad to say that the project is finished and I am finally published.

# The Distribution of Time Between Recessions: Revisited (with MCHT)

## Introduction

These past few weeks I’ve been writing about a new package I created, MCHT. Those blog posts were basically tutorials demonstrating how to use the package. (Read the first in the series here.) I’m done for now explaining the technical details of the package. Now I’m going to use the package for purpose I initially had: exploring the distribution of time separating U.S. economic recessions.

# Time Series and MCHT

## Introduction

Over the past few weeks I’ve published articles about my new package, MCHT, starting with an introduction, a further technical discussion, demonstrating maximized Monte Carlo (MMC) hypothesis testing, bootstrap hypothesis testing, and last week I showed how to handle multi-sample and multivariate data. This is the final article where I explain the capabilities of the package. I show how MCHT can handle time series data.

# Beyond Univariate, Single-Sample Data with MCHT

## Introduction

I’ve spent the past few weeks writing about MCHT, my new package for Monte Carlo and bootstrap hypothesis testing. After discussing how to use MCHT safely, I discussed how to use it for maximized Monte Carlo (MMC) testing, then bootstrap testing. One may think I’ve said all I want to say about the package, but in truth, I’ve only barely passed the halfway point!

# Bootstrap Testing with MCHT

## Introduction

Now that we’ve seen MCHT basics, how to make `MCHTest()` objects self-contained, and maximized Monte Carlo (MMC) testing with MCHT, let’s now talk about bootstrap testing. Not much is different when we’re doing bootstrap testing; the main difference is that the replicates used to generate test statistics depend on the data we feed to the test, and thus are not completely independent of it. You can read more about bootstrap testing in [1].

# Maximized Monte Carlo Testing with MCHT

## Introduction

I introduced MCHT two weeks ago and presented it as a package for Monte Carlo and boostrap hypothesis testing. Last week, I delved into important technical details and showed how to make self-contained `MCHTest` objects that don’t suffer side effects from changes in the global namespace. In this article I show how to perform maximized Monte Carlo hypothesis testing using MCHT, as described in [1].

# MCHT, Closures, and R Environments: Making MCHTest Objects Self-Contained

## Introduction

Last week I announced the first release of MCHT, an R package that facilitates bootstrap and Monte Carlo hypothesis testing. In this article, I will elaborate on some important technical details about making `MCHTest` objects, explaining in the process how closures and R environments work.