9 H

9.1 H0

The null hypothesis: that an observed difference between groups or from a specific value is due to chance alone.

See also null hypothesis, H1, alternate hypothesis, and NHST.

9.2 H1

The alternate hypothesis: that an observed difference between groups or from a specific value is NOT due to chance alone.

See also alternate hypothesis, H0, null hypothesis, and NHST.

9.3 hierarchical model

A type of regression model that involves estimating both fixed effects and random effects.

See linear mixed effects model.

9.4 HTML

Hyper-Text Markup Language: A system for semantically tagging structure and information on web pages.

R Markdown scripts are often knit to HTML. Therefore, you can also include HTML and CSS (a way to control visual style) in your scripts.

Here is an example of some simple HTML.

<h1>My Title</h1>

<p>A paragraph of stuff...</p>

<ul>
  <li>List item</li>
  <li>Another list item</li>
</ul>

<img src="images/darwin.jpg" title="The cutest ferret">

9.5 hypothesis

A proposed explanation made on the basis of limited evidence as a starting point for further investigation.

In science, hypotheses are based on published literature and theories. In quantitative sciences, hypotheses can then be evaluated using statistical methods (e.g., "NHST")). Hypotheses are usually not considered in isolation, but in relation to other hypotheses. For instance, if a researcher wants to investigate the relationship between depression and insomnia, they could contrast the following two hypotheses:

A hypothesis describing the researchers' assumption, usually that there is a non-chance difference between groups or a difference from a specified value (alternate hypothesis): "People with depression report sleep problems more often than healthy controls."

A hypothesis that refutes the researchers' assumption, usually that any differences are due to chance (null hypothesis): "People with depression report sleep problems as often as healthy controls".