LSAT Item Type Validity Study

User avatar
neprep
Posts: 1066
Joined: Fri Jul 26, 2013 11:16 pm

LSAT Item Type Validity Study

Postby neprep » Tue Jul 30, 2013 3:09 pm

I was reading LSAC research reports as a break from studying for the LSAT because I don't have a life*, and I found a study that most seasoned veterans would probably know about, but still would be interesting to newbies such as myself.

The study tried to estimate how different sections on the LSAT relate to first-year law school GPAs, and the tl;dr is that LR has the highest correlations, followed by RC and then Games, BUT Games still are more valuable to the predictive validity of the ENTIRE test. Paradox? See how the authors resolve it...

Here's an excerpt:

The major results of this paper indicate that each of the operational LSAT item types has a substantial correlation with FYA (first year GPA), and that each is needed to obtain the reported overall correlation because no two item types are perfectly correlated with each other. The item type with the greatest predictive validity was LR with a validity coefficient of 0.483. Even though RC with a validity coefficient of 0.430 had the next greatest value, AR with a validity coefficient of 0.340 makes the greater additional contribution to the validity coefficient of the entire test as it had a much lower correlation with LR than did RC. After adjusting for the amount of predictive validity accounted for by their correlations with LR, the remaining degree of correlation of AR with FYA was 0.124 whereas the corresponding value for RC was 0.107.

The results also verified that the interrelationships among the item types in the law school applicant pools were the same as those previously found for all test takers for a fixed LSAT form. The results verified that LR and RC remain very highly correlated (0.760), while AR is less correlated with LR or RC, but still strongly so, with correlations of 0.510 and 0.459, respectively.

The implications of this study are that all three item types have substantial correlations with FYA and should all remain as part of the LSAT to maintain the current level of overall predictive validity.


Anyone want to take a shot at a quick analysis? What would strengthen this argument? What would weaken it? What are some necessary assumptions? (just kidding)

The full study, for those well versed in Spearman-Brown analysis: http://www.lsac.org/lsacresources/research/tr/pdf/tr-98-01.pdf

*This is false, but these research reports are pretty insightful.



Return to “LSAT Prep and Discussion Forum”

Who is online

Users browsing this forum: Alexandros, cctv, SunDevil14 and 10 guests