Three styles

Three different audiences in one.

  1. Students, seeing data-centric lessons
  2. Instructors, learning some new tools and styles
  3. Budding data scientists, learning tools for doing data science

Results from the survey

  1. I am willing to take this survey. 94% (sampling bias)
  2. Institution type: two thirds from two-year colleges. One from high school. Remaining from 4-year institutions.
  3. Everyone responding has taught introductory statistics.

Results from the survey

  1. What coursework did we take in graduate school?

Results from the survey

  1. Almost half have taken applied stats coursework.
  2. Almost half "conduct statistical analyses of data outside of teaching (e.g., for your own research, consulting, etc.)"

Results from the survey

  1. Computing used

Results from the survey

  1. We lack
    • Access to real data: 50%
    • Personal experience handling large data sets: 55%
    • Technology infrastructure for large data sets: 45%
    • Graphing ability: 60% [ci at 95%: 40-80%]
  2. Obstacles to making changes
    • Not enough personal time: 70%
    • Student characteristics: 55%
    • Technology constraints: 60% [ci at 95%: 40-80%]
    • Department or institutional constraints: 30%

"Too many students can't take the intro stats course, and hence graduate, because of the burden of "intermediate algebra" prerequisite."

Results from the survey

Areas of consensus

  • Students learn statistics more effectively by learning fewer topics in greater depth than learning more topics in less depth. 95% agree or strongly agree
  • The many methods covered in introductory statistics can be reduced to a small set of common principles. 85% agree
  • Rules of probability should be included in an introductory statistics course. 85% agree.
  • Students learn statistics more effectively from a good lecture than from a good activity. 80% disagree or strongly disaggree

Results from the survey

More areas of concesus

  • Algebraic formulas are the best method to learn statistics. 100% disagree
  • Students learn statistics better by understanding how to express concepts with algebra. 85% disagree
  • Computing offers a framework for understanding statistical theory that is as legitimate as the theory based on probability rules and algebra. 80% agree
  • Students should learn how to read statistical tables of theoretical distributions (e.g., t-table, F-table). 80% disagree

About tables …

GAISE College report (p. 24)

Drills with z-, t-, χ2, and F-tables. These skills are no longer necessary and do not reflect modern statistical practice. Since statistical software produces a p-value as part of performing a hypothesis test, a shift from finding p-values to interpreting p-values in context is appropriate.

p value quiz

ASA statement:

Underpinning many published scientific conclusions is the concept of “statistical significance,” typically assessed with an index called the p-value. While the p-value can be a useful statistical measure, it is commonly misused and misinterpreted.

Quiz: Agree or disagree?

  1. P-values can indicate how incompatible the data are with a specified statistical model.

  2. P-values do not measure the probability that the studied hypothesis is true, or the probability that the data were produced by random chance alone.

  3. A p-value, or statistical significance, does not measure the size of an effect or the importance of a result.

  4. By itself, a p-value does not provide a good measure of evidence regarding a model or hypothesis.

Answers here

Theory or practice?

Is statistics …

  • an area of theory (like group theory or number theory or graph theory)?
  • a practical tool?




Insofar as statistics is a practical tool, the stat education community some catching up to do.

1880s Galton and Benz

  • 1885 Karl Benz designs 4-stroke engine for use in his automobile
  • 1888 Francis Galton introduces the "co-relation" coefficient

1908 Gossett and Ford

  • First Model T off Henry Ford's production line
  • William Gossett's t statistic

1920s

  • 1925 ANOVA appears in Fisher's Statistical Methods for Research Workers
  • 1927 Ford Model A enters production

Orientation to the workshop agenda