We're putting together information to help you move to virtual advising, deploy nudging, get answers on data science questions, and use your solutions during COVID-19. ACCESS RESOURCES HERE. 

Support is Moving! You can submit a new ticket at support@civitaslearning.com

Open navigation

What are Powerful Predictors?

Each Powerful Predictor is a predictive factor or behavior for the filtered student group. These variables are unique to your institution based on the most predictive indicators of persistence for your unique student population.

The data points listed to the right of each Power Predictor include:

Multi-modal overlap measure (MOM) represents the shaded area beneath the two distributions that illustrate persisting and non-persisting students in a Powerful Predictor Chart. Distributions that are close together show that students persist and do not persist at similar rates at each value. Distributions that are further apart suggest that at a certain point, there are significant differences in persistence. These differences are one indicator that the Powerful Predictor may be predictive of persistence.

MOM (ALL) is calculated using all historical samples of students related to the currently selected Powerful Predictor, including students without a known value.
DATA %DATA % represents the percentage of available historical student data for the Powerful Predictor given the current filter criteria. DATA % is not included in the rank of Powerful Predictors.

Powerful Predictors are ranked by their historical influence on persistence.

By default, the full list of Powerful Predictors is sorted by rank or MOM (ALL). You can change the order of Powerful Predictors to be alphabetical by predictor name or sorted by Category or DATA %. Click the gray text above any column to sort the list. In this example, the list of Powerful Predictors is sorted by Category.

The number of Powerful Predictors available is unique for each Civitas Learning partner institution depending on the data provided to Civitas Learning. The number of Powerful Predictors will change when filters are applied because different data are available for different groups of students. For example, student in their first term may not have a GPA, and therefore Powerful Predictors that use GPA data will not appear when applying the 0 Terms Completed filter.

Find the total number of Powerful Predictors available for a filtered group of students above the list of Powerful Predictors.

Search for any Powerful Predictor by typing a variable of interest into the Search box above the list. If you are interested in exploring GPA variables, type GPA into the Search box. This will surface all of the Powerful Predictors with GPA in the name or the description.

The list of Powerful Predictors is not the list of model variables used in institution-specific predictive models that generate individual persistence predictions for students. Powerful Predictors are curated to be interpretable, insightful, and actionable. Model variables can be difficult to interpret and may not provide actionable information.

Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.