Sorry, you need to enable JavaScript to visit this website.

Regression

  • A cartoon to be used for discussing the selection of the best explanatory variable in a regression model. The cartoon was used in the March 2017 CAUSE Cartoon Caption Contest. The winning caption was submitted by Michele Balik-Meisner, a student at North Carolina State University. The drawing was created by British cartoonist John Landers based on an idea from Dennis Pearl of Penn State University. A second winning entry, by Michael Posner of Villanova University, may be found at www.causeweb.org/cause/resources/fun/cartoons/variable-wheel-ii Three honorable mentions that rose to the top of the judging in the March competition included "No no no! You randomize AFTER you select your research topic!" by Mickey Dunlap from University of Georgia; "This isn't what I meant by random variable!" by Larry Lesser from The University of Texas at El Paso; and "We find this method of finding 'significant' predictors to be quicker than using stepwise regression and it is even slightly more reproducible." by Greg Snow from Brigham Young University.

    0
    No votes yet
  • A cartoon to be used for discussing the selection of the best explanatory variable in a regression model. The cartoon was used in the March 2017 CAUSE Cartoon Caption Contest. The winning caption was submitted by Michael Posner, from Villanova University. The drawing was created by British cartoonist John Landers based on an idea from Dennis Pearl of Penn State University. A second winning entry, by Michele Balik-Meisner, a student at North Carolina State University, may be found at www.causeweb.org/cause/resources/fun/cartoons/variable-wheel-i Three honorable mentions that rose to the top of the judging in the March competition included "No no no! You randomize AFTER you select your research topic!" by Mickey Dunlap from University of Georgia; "This isn't what I meant by random variable!" by Larry Lesser from The University of Texas at El Paso; and "We find this method of finding 'significant' predictors to be quicker than using stepwise regression and it is even slightly more reproducible." by Greg Snow from Brigham Young University.

    0
    No votes yet
  • A joke to help in recalling the purpose of Correlation and Regression. The joke was written in 2017 by Dennis Pearl from Penn State University.
    5
    Average: 5 (1 vote)
  • A video for use in teaching about the dangers of extrapolating well beyond the range of the data in linear regression. The lyrics and Powerpoint components of the video were written by Michael Posner while the vocals were done by Reena Freedman of Villanova University and won first place in the video category of the 2017 A-mu-sing contest. The lyrics parody the song "How Far I'll Go" from the Disney animated feature film Moana (sung by Alessia Cara for the movie soundtrack).
    5
    Average: 5 (1 vote)
  • A cartoon suitable for use in discussing situations where the explanatory variable has essentially no predictive power (whether the variables have a statistically significant relationship or not). The cartoon is number 1725 (August, 2016) from the webcomic series at xkcd.com created by Randall Munroe. Free to use in the classroom and on course web sites under a creative commons attribution-non-commercial 2.5 license.

    5
    Average: 5 (1 vote)
  • A cartoon to be used in discussing the interpretation of a regression equation (for example interpreting the intercept when it is well beyond the range of the data). The cartoon is #1823 in the web comic Piled Higher and Deeper by Panamanian cartoonist Jorge Cham (1976- ): see www.phdcomics.com/comics/archive.php?comicid=1823. Free for use in classrooms and course websites with acknowledgement (i.e. "Piled Higher and Deeper" by Jorge Cham, www.phdcomics.com)
    0
    No votes yet
  • A cartoon to be used in discussing the least squares property of the regression line and the lexical ambiguity in the use of the word regression. The cartoon is #1921 in the web comic Piled Higher and Deeper by Panamanian cartoonist Jorge Cham (1976- ): see www.phdcomics.com/comics/archive.php?comicid=1921. Free for use in classrooms and course websites with acknowledgement (i.e. "Piled Higher and Deeper" by Jorge Cham, www.phdcomics.com)
    0
    No votes yet
  • A cartoon to be used in discussing correlation, spurious versus causal relationships, and the meaning of residuals (humorously depicting a relationship between residual over historical enrollment levels in grad school and residual levels in the unemployment rate). The cartoon is #1078 in the web comic Piled Higher and Deeper by Panamanian cartoonist Jorge Cham (1976- ): see www.phdcomics.com/comics/archive.php?comicid=1078. Free for use in classrooms and course websites with acknowledgement (i.e. "Piled Higher and Deeper" by Jorge Cham, www.phdcomics.com)
    0
    No votes yet
  • A game to aid in the active learning of linear regression. TigerSTAT is a three dimensional on-line game where students use the game to collect data and explore models for estimating the age of a Siberian tiger. In this game, students act as researchers on a national preserve where they are expected to catch tigers, collect data, analyze their data (using simple linear regression on transformed data), and draw appropriate conclusions. Instructors also have the option of asking students to read a scientific publication discussing current methods in estimating ages of tigers. The TigetSTAT labs handouts were created by Rod Sturdivant (Ohio State University), Kevin Cummiskey (West Point) and John Jackson (West Point). Tietronix Software developed the game. This resource is part of the Stat2Labs collection.

    5
    Average: 5 (1 vote)
  • A game for use in the active learning of linear regression and sampling biases. TigerSAMPLING is almost identical to TigerSTAT. However in the TigerSAMPLING game there are additional questions that emphasize BIAS and GENERALIZABILITY. These games collect data and explore models for estimating the age of a Siberian tiger. In this game, students act as researchers on a national preserve where they are expected to catch tigers, collect data, analyze their data (using the simple linear regression on transformed data), and draw appropriate conclusions. The TigetSTAT labs handouts were created by Rod Sturdivant (Ohio State University), Kevin Cummiskey (West Point) and John Jackson (West Point). Tietronix Software developed the game. This resource is part of the Stat2Labs collection.
    0
    No votes yet

Pages

register