# Comparison Cohorts Schools can be grouped into two important types of groups: "peers" and "neighbors." * **Nationwide schools like me** groups are made by looking at schools that are similar in certain ways, like the type of school, the number of students, the grades they offer, and the income of the nearby area. Schools that are alike in these ways get grouped together into a certain number of peer groups. We use machine learning and k-means cluster algorithms to group like schools together. * **Local neighbor groups** are made up of schools that are close to each other and offer similar grades. Each school has its own group of nearby neighbors. When we want to compare schools, we look at different statistics or numbers (like enrollment, tuition, or financial aid). These statistics can be calculated for individual schools or for the whole group of schools in a peer or neighbor group. A **comparison** is when we take one of these statistics and look at how it changes over time for a school and its peer and neighbor groups. For example, we might compare how a school’s enrollment has changed over the past few years with its peers and neighbors. The comparison also comes with a title and a short summary that explains what we’re looking at. Sometimes, the data for a school or group might be missing. This can happen if the school didn’t provide the needed information, or if there aren’t enough similar schools to create a good comparison. Schools, groups, and their comparisons all depend on data that gets updated regularly. When new data is added or old data is changed, the statistics and comparisons are recalculated to keep everything up to date. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.nais.org/nais/comparisons/comparison-cohorts.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.