Grades Are Not Normal : Improving Exam Score Models Using the Logit-Normal Distribution / Noah Arthurs, Ben Stenhaug and Sergey Karayev.
Understanding exam score distributions has implications for item response theory (IRT), grade curving, and downstream modeling tasks such as peer grading. Historically, grades have been assumed to be normally distributed, and to this day the normal is the ubiquitous choice for modeling exam scores....
Saved in:
| Online Access: |
Full Text (via ERIC) |
|---|---|
| Main Authors: | , , , |
| Format: | eBook |
| Language: | English |
| Published: |
[Place of publication not identified] :
Distributed by ERIC Clearinghouse,
2019.
|
| Subjects: |
MARC
| LEADER | 00000nam a22000002u 4500 | ||
|---|---|---|---|
| 001 | b11019900 | ||
| 003 | CoU | ||
| 005 | 20200512140037.6 | ||
| 006 | m o d f | ||
| 007 | cr ||||||||||| | ||
| 008 | 190701s2019 xx |||| o ||| s eng d | ||
| 035 | |a (ERIC)ed599204 | ||
| 035 | |a (MvI) 8M000000578010 | ||
| 040 | |a ericd |b eng |c MvI |d MvI | ||
| 099 | |a ED599204 | ||
| 100 | 1 | |a Arthurs, Noah. | |
| 245 | 1 | 0 | |a Grades Are Not Normal : |b Improving Exam Score Models Using the Logit-Normal Distribution / |c Noah Arthurs, Ben Stenhaug and Sergey Karayev. |
| 264 | 1 | |a [Place of publication not identified] : |b Distributed by ERIC Clearinghouse, |c 2019. | |
| 300 | |a 1 online resource (6 pages) | ||
| 336 | |a text |b txt |2 rdacontent. | ||
| 337 | |a computer |b c |2 rdamedia. | ||
| 338 | |a online resource |b cr |2 rdacarrier. | ||
| 500 | |a Availability: International Educational Data Mining Society. e-mail: admin@educationaldatamining.org; Web site: http://www.educationaldatamining.org. |5 ericd. | ||
| 500 | |a Abstractor: As Provided. |5 ericd. | ||
| 500 | |a Educational level discussed: Higher Education. | ||
| 500 | |a Educational level discussed: Postsecondary Education. | ||
| 516 | |a Text (Speeches/Meeting Papers) | ||
| 516 | |a Text (Reports, Evaluative) | ||
| 520 | |a Understanding exam score distributions has implications for item response theory (IRT), grade curving, and downstream modeling tasks such as peer grading. Historically, grades have been assumed to be normally distributed, and to this day the normal is the ubiquitous choice for modeling exam scores. While this is a good assumption for tests comprised of equally-weighted dichotomous items, it breaks down on the highly polytomous domain of undergraduate-level exams. The logit-normal is a natural alternative because it is has a bounded range, can represent asymmetric distributions, and lines up with IRT models that perform logistic transformations on normally distributed abilities. To tackle this question, we analyze an anonymized dataset from Gradescope consisting of over 4000 highly polytomous undergraduate exams. We show that the logit-normal better models this data without having more parameters than the normal. In addition, we propose a new continuous polytomous IRT model that reduces the number of item-parameters by using a logit-normal assumption at the item level. [For the full proceedings, see ED599096.] | ||
| 524 | |a International Educational Data Mining Society, Paper presented at the International Conference on Educational Data Mining (EDM) (12th, Montreal, Canada, Jul 2-5, 2019). |2 ericd. | ||
| 650 | 0 | 7 | |a Grades (Scholastic) |2 ericd. |
| 650 | 0 | 7 | |a Scores. |2 ericd. |
| 650 | 0 | 7 | |a Statistical Distributions. |2 ericd. |
| 650 | 0 | 7 | |a Models. |2 ericd. |
| 650 | 0 | 7 | |a Item Response Theory. |2 ericd. |
| 650 | 0 | 7 | |a Grading. |2 ericd. |
| 650 | 0 | 7 | |a Undergraduate Students. |2 ericd. |
| 700 | 1 | |a Stenhaug, Ben, |e author. | |
| 700 | 1 | |a Karayev, Sergey, |e author. | |
| 700 | 1 | |a Piech, Chris, |e author. | |
| 856 | 4 | 0 | |u http://files.eric.ed.gov/fulltext/ED599204.pdf |z Full Text (via ERIC) |
| 907 | |a .b110199005 |b 05-21-20 |c 05-21-20 | ||
| 998 | |a web |b 05-21-20 |c f |d m |e - |f eng |g xx |h 0 |i 0 | ||
| 956 | |a ERIC | ||
| 999 | f | f | |i 05e1f940-71f5-5db6-b787-e54862570da8 |s 285b9c8e-9e3c-5fe4-bea8-ae29310cde3d |