Support
Open navigation

How are data calculated in reports?

The graphs and tables show the percentage of participants who reported positive experiences with a particular condition. In some cases, they also show the percentage point change in the share of participants who rated the condition positively. 

For an experience to be considered positive, participants have to:

  • “Agree” or “Strongly Agree” with a positive statement. For example, they must agree or strongly agree with the statement: “I feel accepted in this class.”

  • “Disagree” or “Strongly Disagree” with a negative statement. For example, they must disagree or strongly disagree with the statement: “People here would be surprised if I, or someone like me, did well in this class.”

All questions are asked on 6-points scales with the options: Strongly Disagree, Disagree, Somewhat Disagree, Somewhat Agree, Agree, and Strongly Agree.

Composite scores for each condition are weighted means of the individual item scores. For example, if scores on three items were 20%, 30%, and 40%, then the composite score of those three items would be 30%, assuming the same number of participants answered each item. If twice as many participants answered item 1 (20%), then that question would be weighted more heavily and the composite score would be 28%.

When data are missing because a participant did not complete the survey or chose not to answer a particular question, their previous responses are carried forward (or “imputed”) to ensure that changes are only shown when participants’ responses actually changed—not just because of who happened to respond to a particular survey. See What do we do with missing data (when participants skip a survey)?

In networks and communities that have Classes/Groups of different sizes, every participant's response is equally weighted.

Did you find it helpful? Yes No

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