Quantitative study design, significance testing, and different classes of statistical tests.
I got here to jot down this text through what was a predictable yet still unexpected set of events. I recently finished a course on statistical testing and reporting, and I set out to jot down a series of articles explaining the main points of probably the most useful statistical tests I learned. I needed to do that each to cement my very own knowledge in addition to help other data scientists learn a subject I discovered immensely helpful.
The primary of those articles was going to be on the t-test, a standard statistical test used to find out if two means (averages) from different sets of information are statistically different. I started to jot down this text, but I spotted I needed to first explain that there are two different sorts of t-tests. Then, I spotted that to clarify that, I needed to clarify a separate but related underlying concept. The cycle continued as I planned out the article.
Moreover, I spotted that I would wish to do that with each recent article I wrote, as every statistical test required the identical underlying knowledge base. Quite than repeat this information in each article, it could be significantly better to reference one standing source of knowledge.
And thus, this text was born. Within the words that follow, I’ll attempt to offer a concise but effective primer on the fundamental concepts try to be acquainted with to be able to conduct and report statistical tests. To your convenience, I even have broken down the concepts within the order you’ll encounter them running a study from start to complete. So without further ado, let’s get into it.
Quantitative Study Design
When designing a study, there are several essential details one needs to think about. This text is just not about study design, and I won’t be going into the main points of best practices and the reasoning behind them. That said, the design of a study strongly influence the eventual statistical test needed, and so it is crucial to have a basic understanding of the next concepts:
- Aspects and measures
- Levels and coverings