I research the actions of teachers. A distinction is made here between actions that focus on high-scoring, average-scoring and low-scoring students. I want to see if there is a difference between the number of times a teacher interacts with each of these groups of students. For this I have 3 columns in my dataset: number of interactions with high scoring, interactions with average scoring and interactions with low scoring. I am looking for a statistical test to see whether these three types of actions differ per teacher. I’ve already looked at a t-test and single ANOVA, but can’t figure out how to do this with three variables with no clear factor for an ANOVA.
Answer
Dear Maaike,
If I understand your explanation of the problem correctly, the 3 different scoring levels actually represent a qualitative classification of 1 single input variable.
Initially, you can analyze the influence of this on the quantitative output variable “number of interactions” with an ANOVA.
In the second instance, you can then check for which teachers there is a significant difference by including a second (non-qualitative) classification-changing “teacher” in your dataset and expanding the ANOVA.
Philippe J. Roussel
Senior Reliability Research Engineer
imec
Answered by
eng. Philippe Roussel
Microelectronics Reliability
Kapeldreef 75 3001 Leuven
http://www.imec-int.com
.