CAUSE WebinarGAISEing into the Future of Statistics Education

Chris FranklinUniversity of Georgia

Jessica UttsUniversity of California, Davis

November 14, 2006

GAISE• Guidelines for Assessment and Instruction in

Statistics Educationhttp://www.amstat.org/education/gaise/

• Strategic initiative of ASA. The GAISE documents were endorsed by ASA in 2005.

• Provides a Framework for Teaching Statistics – Within the PreK-12 Mathematics Curriculum and – For the College Introductory Course

Guidelines for Teaching and Learning Statistics within the PreK-12 Mathematics

Curriculum -- The Pre K-12 GAISE Framework

Christine FranklinUniversity of Georgia

Department of Statisticschris@stat.uga.edu

PreK-12 Writers and AdvisorsWriters: Advisors:• Christine Franklin Peter Holmes• Gary Kader Brad Hartlaub• Denise Mewborn Landy Godbold• Jerry Moreno Cliff Konold• Roxy Peck Susan Friel• Mike Perry• Richard Scheaffer

What’s Happening in Statistics Education, PreK-12

• Everyone – students, teachers, parents, employers – interested in data

• Data analysis has become a key component of modern PreK-12 mathematics curriculum

• NCTM, NAEP, State guidelines -- GA has become a model state with the integration of data in the new GA Performance Standards for mathematics

Current efforts

• Curriculum Standards (PSSM) of the National Council of Teachers of Mathematics (NCTM)Data Analysis and Probability (one of the 5 strands) runs throughout the curriculum

Advanced Placement Statistics• First exam in 1997 – 7500 exams• In 2006 – 90,000 exams

What’s Needed for the Future• Statistics is a relatively new science that is still

developing

• Many teachers have not had any opportunity to develop sound knowledge of the principles and practices of data analysis they are now called upon to teach

• “Fleshing out” of the NCTM “Standards” is more essential for the statistics strand than for others

GAISE• The goals of the Pre K-12 document are to provide a basic

framework for informed Pre K-12 stakeholders that describes what is meant by a statistically literate high school graduate and to provide steps to achieve this goal.

• This framework provides a conceptual structure for statistics education which gives a coherent picture of the overall curriculum. This framework supports and complements the objectives of the NCTM PSSM.

• A goal in the professional growth of our mathematics teachers should be to give a big picture of statistics and allow implementation of the NCTM Standards in an informed way.

Levels in PreK-12 GAISE• The main content of the Pre K-12 Framework is

divided into three levels, A, B, and C that roughly parallel the PreK-5, 6-8, and 9-12 grade bands of the NCTM Standards.

• The framework levels are based on experience not age.

Check out the ASA/NCTM Committee Statistics Teacher Network Newsletter, Issue 68 (current issue)

• http://www.amstat.org/education/stn/

FRAMEWORK FOR STATISTICS EDUCATION

Statistical analysis is an investigatory process that turns often loosely formed ideas into scientific studies by:

• refining a problem into one or more questions that can be addressed with data

• designing a plan to collect appropriate data • analyzing the collected data by graphical and

numerical methods,• interpreting the analysis so as to reflect light on the

original question.An understanding of variability is crucial for the practice

of this process

A Curriculum Framework for Pre K-12 Statistics Education

Basic principles around which this Framework revolves can be summarized as:

• Both conceptual understanding and procedural skill should be developed deliberately, but conceptual understanding should not be sacrificed for procedural proficiency.

• Active learning is key to the development of conceptual understanding.

• Real world data must be used wherever possible in statistics education.

• Appropriate technology is essential in order to emphasize concepts over calculations

These principles continue as the foundation of the College GAISE recommendations.

GAISE College Group

Joan Garfield Univ. of Minnesota (Chair)Martha Aliaga ASA George Cobb Mt. Holyoke CollegeCarolyn Cuff Westminster CollegeRob Gould UCLARobin Lock St. Lawrence UniversityTom Moore Grinnell CollegeAllan Rossman Cal Poly San Luis ObispoBob Stephenson Iowa StateJessica Utts UC DavisPaul Velleman Cornell UniversityJeff Witmer Oberlin College

The Goal

Produce a set of recommendations and guidelines for instruction and

assessment in introductory statistics courses at the undergraduate level.

Four Part Report

• Introduction and History• Goals for Students in an Introductory

Course: What it Means to be Statistically Educated

• Six Recommendations for helping teachers achieve those goals

• Appendix of Examples and Suggestions

Six Recommendations

1. Emphasize statistical literacy and develop statistical thinking

2. Use real data3. Stress conceptual understanding rather than

mere knowledge of procedures4. Foster active learning in the classroom5. Use technology for developing conceptual

understanding and analyzing data6. Integrate assessments that are aligned with

course goals to improve as well as evaluate student learning.

Expanding on Recommendations 1 and 2

Emphasize statistical literacy and develop statistical thinking and Use real data

– Use scenarios that are familiar to students as well as data of interest to them

– Don’t use data out of context of the problem to be solved

– Start with a question and model the whole process to arrive at the answer, even if it’s throughout the course and not all in the same day

Using Familiar Scenarios:Wason Selection Task

Modified somewhat from this source: http://coglab.wadsworth.com/experiments/WasonSelection.shtml

Cards have a letter on one side and a number on the other.Consider the rule:

If a card has a B on one side, it has a 21 on the other side. Question: Which card(s) do you need to turn over to verify

that the rule holds for all cards?

B 16

C 21

Using Familiar Scenarios:Wason Selection Task

Cards have a letter on one side and a number on the other.Consider the rule:

If a card has a B on one side, it has a 21 on the other side. Question: Which card(s) do you need to turn over to verify

that the rule holds for all cards?

Answer: B and 16

B 16

C 21

New Example Source: The Tipping Point; orig. Professor Leda Cosmides, UCSB

The Rule: No one under 21 is allowed to drink alcohol in a bar.

There are 4 people drinking in a bar:• One is drinking beer.• One is 16 years old.• One is drinking coke.• One is 21 years old.

Question: For which person(s) do we need more information to verify that the law is being upheld?

New Example Source: The Tipping Point; orig. Professor Leda Cosmides, UCSB

The Rule: No one under 21 is allowed to drink alcohol in a bar.

There are 4 people drinking in a bar:• One is drinking beer.• One is 16 years old.• One is drinking coke.• One is 21 years old.

Question: For which person(s) do we need more information to verify that the law is being upheld?

The person drinking beer and the 16-year old .

The two tasks are the same, but one is a familiar scenario! That makes it easier to understand.

Cards have a letter on one side and a number on the other.Consider the rule:

If a card has a B on one side, it has a 21 on the other side. Question: Which card(s) do you need to turn over to verify that

the rule holds for all cards?

Answer: B and 16

Beer

Age 16 Coke

Age 21

Model statistical thinking for students by presenting examples as questions that need an answer, and showing the statistical process for finding the answer.

Work examples from the beginning (the question) to the end (the conclusion).

Question of interest: Do men lose more weight by dieting or by exercising regularly? Study done at Stanford, used overweight male volunteers, randomlyassigned to one year of diet or exercise. Lost more weight with diet.

Useful for illustrating these concepts and processes:• Types of studies (randomized experiment versus observational study)• Design of randomized experiments• When cause and effect can be concluded (or not); it can for this experiment• How to do hypothesis tests, from start to finish• How to construct and interpret a confidence interval

Example of Modeling Statistical Thinking

GAISE Recommendations: Making It Happen

Start with small steps, for example:• Add an activity to your course• Have your students do a small project• Integrate an applet into a lecture• Demonstrate the use of software to your students• Increase the use of real data sets• Add a case study (newspaper story <-> journal article)• Choose one topic to delete from the list you currently try to

cover and using the time saved to focus more on understanding concepts.

QUESTIONS??

http://www.amstat.org/education/gaise

chris@stat.uga.edujmutts@ucdavis.edu