CATALST - Change Agents for Teaching and Learning Statistics

Joan Garfield; Robert delMas; Andrew Zieffler; Allan Rossman; Beth Chance; John Holcomb; George Cobb

CATALST - Change Agents for Teaching and Learning Statistics

By Joan Garfield¹, Robert delMas¹, Andrew Zieffler¹, Allan Rossman², Beth Chance², John Holcomb³, George Cobb⁴

1. University of Minnesota 2. California Polytechnic State University, San Luis Obispo 3. Cleveland State University 4. Mt. Holyoke

View Link (HTM)

Licensed according to this deed.

Published on

21 Jan 2015

Abstract

From the project website: "This project uses the acronym CATALST (Change Agents for Teaching and Learning Statistics) to represent the goal of accelerating change in the teaching and learning of statistics. The changes we are working towards are in both content and pedagogy. Our focus is the first, introductory, non-calculus based statistics course. This project was funded from 2008–2012 to develop curriculum materials, lesson plans, and corresponding student assessments."

"The CATALST curriculum consists of three units: (1) Chance Models and Simulation, (2) Models for Comparing Groups, and (3) Estimating Models Using Data. Activities are built on ideas of modeling and simulation, with “the core logic of inference” as the foundation (Cobb, 2007, p. 13). When applied to randomized experiments and random samples, Cobb refers to this logic as the “three Rs”: randomize, repeat, and reject. The CATALST project generalized this logic for a broader simulation-based approach to inference as follows:

Model: Specify a model that will generate data to reasonably approximate the variation in outcomes attributable to the random process—be it in sampling or assignment. The model is often created as a null model that may be rejected in order to demonstrate an effect.
Randomize & Repeat: Use the model to generate simulated data for a single trial, in order to assess whether the outcomes are reasonable. Specify the summary measure to be collected from each trial. Then, use the model to generate simulated data for many trials, each time collecting the summary measure.
Evaluate: Examine the distribution of the resulting summary measures. Use this distribution to assess particular outcomes, evaluate the model used to generate the data, compare the behavior of the model to observed data, make predictions, etc."

Cite this work

Researchers should cite this work as follows:

Garfield, J., delMas, R., & Zieffler, A. (2012) Developing statistical modelers and thinkers in an introductory, tertiary-level statistics course. ZDM—The International Journal on Mathematics Education, 44(4).