|
Activity Number:
|
284
- Assessment Tools in Statistics and Data Science Education
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 9, 2022 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistics and Data Science Education
|
|
Abstract #322962
|
|
|
Title:
|
Tensions in Student Thinking About Statistical Design
|
|
Author(s):
|
Kelly Findley* and Brein Mosely
|
|
Companies:
|
University of Illinois at Urbana-Champaign and University of Illinois at Urbana-Champaign
|
|
Keywords:
|
Statistics Education;
Design;
Causal Inference;
Sampling
|
|
Abstract:
|
Reform efforts in statistics education emphasize the need for students to develop statistical thinking. Critical to this goal is a solid understanding of design in the process of collecting data, evaluating evidence, and drawing conclusions. We surveyed 760 students taking introductory statistics courses. These participants were asked them to evaluate different designs and discuss which option provided stronger evidence for a statistical claim. We also interviewed 6 students who were asked to design a study to best answer a general research question. Student views diverged over the value of intervention. Some students viewed intervention as a weakness that disrupts natural habits, while others viewed intervention as critical for identifying a clear cause and effect relationship. Students also took different views on whether a sample should be more homogeneous or heterogeneous. Both of these divergences highlight a tension in design between strengthening causality or generalizability. Our long-term interests in this project are to inspire curricular efforts in the area of design that prompt students to see design as a balancing of different priorities.
|
Authors who are presenting talks have a * after their name.
