Oops .. max = square root (cross products of the _reliabilities_ of the two variables) .,. just wasted by daily quota with a typo!
========================== John W. Kulig, Ph.D. Professor of Psychology Coordinator, Psychology Honors Plymouth State University Plymouth NH 03264 ========================== ----- Original Message ----- From: "John Kulig" <ku...@mail.plymouth.edu> To: "Teaching in the Psychological Sciences (TIPS)" <tips@fsulist.frostburg.edu> Sent: Wednesday, February 19, 2014 8:46:32 AM Subject: Re: [tips] SAT and High School grade study Well, grades are not perfect measurement devices, but what is in psychology? Interestingly, less than perfect reliability of any otwo variables limits the extent the two variables can correlate. Measurement texts give the upper limit, or maximum, of validity coefficients (as, say, SAT predicting college grades) as square root (cross products of the two variables). So if HS grades have reliability of .9 and college grades have a reliability of .6, max correlation between the two variables = sqrt(.54) = .73. That's _maximum_. So raw validity coefficients usually underestimate validity of the predictor variable ... same is true when we try to predict college grades from HS grades. This makes the correlations in Stuart's reference even more impressive. ========================== John W. Kulig, Ph.D. Professor of Psychology Coordinator, Psychology Honors Plymouth State University Plymouth NH 03264 ========================== ----- Original Message ----- From: "Christopher Green" <chri...@yorku.ca> To: "Teaching in the Psychological Sciences (TIPS)" <tips@fsulist.frostburg.edu> Sent: Wednesday, February 19, 2014 8:22:53 AM Subject: Re: [tips] SAT and High School grade study Grades aren't designed to predict how well one will do at the next level. They are designed to summarize (impossibly) in a single character (or two) how one performed at the last level. The determinants of high school and college performance are not exactly the same, so, not surprisingly, high school grades don't predict college performance very exactly. But why are we expecting *anything* to predict more than, say, half of the variance in college performance? We have very little in the rest of psychology that predicts more than half of any cognitively and behaviorally complex performance. Chris ....... Christopher D Green Department of Psychology York University Toronto, ON M6C 1G4 chri...@yorku.ca http://www.yorku.ca/christo > On Feb 19, 2014, at 2:09 AM, Mike Wiliams <jmicha5...@aol.com> wrote: > > These studies of SAT and grades as predictors or criterion just highlight how > grades are poorly designed as a measurement device. What is their reliability > and validity as measures of performance. Somehow the college board and SAT > makers get the scrutiny that we don't apply to ourselves as grade makers. The > error goes both ways. > > Mike Williams > >> On 2/19/14 12:00 AM, Teaching in the Psychological Sciences (TIPS) digest >> wrote: >> Re: SAT and High School grade study > > > --- > You are currently subscribed to tips as: chri...@yorku.ca. > To unsubscribe click here: > http://fsulist.frostburg.edu/u?id=430248.781165b5ef80a3cd2b14721caf62bd92&n=T&l=tips&o=34371 > > or send a blank email to > leave-34371-430248.781165b5ef80a3cd2b14721caf62b...@fsulist.frostburg.edu --- You are currently subscribed to tips as: ku...@mail.plymouth.edu. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13338.f659d005276678c0696b7f6beda66454&n=T&l=tips&o=34377 or send a blank email to leave-34377-13338.f659d005276678c0696b7f6beda66...@fsulist.frostburg.edu --- You are currently subscribed to tips as: ku...@mail.plymouth.edu . To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13338.f659d005276678c0696b7f6beda66454&n=T&l=tips&o=34380 (It may be necessary to cut and paste the above URL if the line is broken) or send a blank email to leave-34380-13338.f659d005276678c0696b7f6beda66...@fsulist.frostburg.edu --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=34381 or send a blank email to leave-34381-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
