[BigJohn043]

I wasn't really going to respond because this isn't going anywhere.  But I will make one more post because you specifically asked me to.

First, let me repeat the points from the study:

• The STTF found that standardized test scores aid in predicting important aspects of student success.
  
• For students within any given (HSGPA) band, higher standardized test scores correlate with a higher freshman UGPA, a higher graduation UGPA, and higher likelihood of graduating within either four years (for transfers) or seven years (for freshmen). 
  
• Further, the amount of variance in student outcomes explained by test scores has increased since 2007, while variance explained by high school grades has decreased, although altogether does not exceed 26%. 
  
• Test scores are predictive for all demographic groups and disciplines, even after controlling for HSGPA. 
  
• In fact, test scores are better predictors of success for students who are Underrepresented Minority students (URMs), who are first-generation, or whose families are low-income.
  

The study very clearly says that test scores aid the basic job of admissions in finding students who can succeed.  They are predictive even after controlling for GPA and demographic groups.  I am not sure why you can't understand this basic finding from a bunch of academics who don't like the answer but at least are willing to engage with the facts.

It is true that in any study like this the R2 is going to be lowish given the amount of variability.  This give you the chance to say that the data is underwhelming.  But that is just true of the data set.  For example, if you are looking to predict NFL player success the first thing you would do is look at where a player was drafted.  You would find that it is clearly a statistically significant driver but explains only a small part of the overall variance.  In this kind of data set, you are never going to get a high R2 for literally any metric.

My guess is that you can't admit the basic facts because:

• SJWs hate standardized tests and IQ tests that are highly correlated with standardized tests.  The science behind these tests is very strong but as we all know there are differences in results for different demographic groups.  This is just unacceptable to your social justice worldview, even if the science is very strong and the predictive value is clear.  It is a "sacred" value for SJW types.  People of all political viewpoints will throw science out the window when it conflicts with their sacred values.
  
• You don't really care about the core mission of the admissions office to admit the students with the best chance of success.  You think their mission should really be about social justice and forget the real life consequences.
  

This is it for me.  I don't think this conversation is going anywhere.  When faced with very clear evidence written by a set of liberal academics you can't face reality.  At some point, further discussion is pointless.

[BigJohn043]

I wasn't really going to respond because this isn't going anywhere.  But I will make one more post because you specifically asked me to.

First, let me repeat the points from the study:

• The STTF found that standardized test scores aid in predicting important aspects of student success.
  
• For students within any given (HSGPA) band, higher standardized test scores correlate with a higher freshman UGPA, a higher graduation UGPA, and higher likelihood of graduating within either four years (for transfers) or seven years (for freshmen). 
  
• Further, the amount of variance in student outcomes explained by test scores has increased since 2007, while variance explained by high school grades has decreased, although altogether does not exceed 26%. 
  
• Test scores are predictive for all demographic groups and disciplines, even after controlling for HSGPA. 
  
• In fact, test scores are better predictors of success for students who are Underrepresented Minority students (URMs), who are first-generation, or whose families are low-income.
  

The study very clearly says that test scores aid the basic job of admissions in finding students who can succeed.  They are predictive even after controlling for GPA and demographic groups.  I am not sure why you can't understand this basic finding from a bunch of academics who don't like the answer but at least are willing to engage with the facts.

It is true that in any study like this the R2 is going to be lowish given the amount of variability.  This give you the chance to say that the data is underwhelming.  But that is just true of the data set.  For example, if you are looking to predict NFL player success the first thing you would do is look at where a player was drafted.  You would find that it is clearly a statistically significant driver but explains only a small part of the overall variance.  In this kind of data set, you are never going to get a high R2 for literally any metric.

My guess is that you can't admit the basic facts because:

• SJWs hate standardized tests and IQ tests that are highly correlated with standardized tests.  The science behind these tests is very strong but as we all know there are differences in results for different demographic groups.  This is just unacceptable to your social justice worldview, even if the science is very strong and the predictive value is clear.  It is a "sacred" value for SJW types.  People of all political viewpoints will throw science out the window when it conflicts with their sacred values.
  
• You don't really care about the core mission of the admissions office to admit the students with the best chance of success.  You think their mission should really be about social justice and forget the real life consequences.
  

This is it for me.  I don't think this conversation is going anywhere.  When faced with very clear evidence written by a set of liberal academics you can't face reality.  At some point, further discussion is pointless.