Evidence for a normal distribution of normalized gains
Recently Burkholder et al. argued that class normalized gains over the entire population of courses is approximated by a Cauchy distribution, not by a normal distribution, and therefore should not be used to compare different classes because means and standard deviations cannot be calculated. They a...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
American Physical Society
2023-02-01
|
Series: | Physical Review Physics Education Research |
Online Access: | http://doi.org/10.1103/PhysRevPhysEducRes.19.010111 |
_version_ | 1797900948893335552 |
---|---|
author | Vincent P. Coletta |
author_facet | Vincent P. Coletta |
author_sort | Vincent P. Coletta |
collection | DOAJ |
description | Recently Burkholder et al. argued that class normalized gains over the entire population of courses is approximated by a Cauchy distribution, not by a normal distribution, and therefore should not be used to compare different classes because means and standard deviations cannot be calculated. They argued that multiple linear regression should be used instead. Burkholder et al. provided very little data in support of their belief, but instead provided a theoretical argument with certain assumptions. We shall show that these assumptions are unreasonable. We also show explicitly how normalized gains from 114 clases taught by six different instructors are indeed normally distributed and how two other even larger samples are roughly normally distributed and are not remotely like a Cauchy distribution. The continued use of normalized gains by physics instructors is therefore justified. |
first_indexed | 2024-04-10T08:54:10Z |
format | Article |
id | doaj.art-1ad6641b007743e9a333f723782bb10d |
institution | Directory Open Access Journal |
issn | 2469-9896 |
language | English |
last_indexed | 2024-04-10T08:54:10Z |
publishDate | 2023-02-01 |
publisher | American Physical Society |
record_format | Article |
series | Physical Review Physics Education Research |
spelling | doaj.art-1ad6641b007743e9a333f723782bb10d2023-02-21T19:06:57ZengAmerican Physical SocietyPhysical Review Physics Education Research2469-98962023-02-0119101011110.1103/PhysRevPhysEducRes.19.010111Evidence for a normal distribution of normalized gainsVincent P. ColettaRecently Burkholder et al. argued that class normalized gains over the entire population of courses is approximated by a Cauchy distribution, not by a normal distribution, and therefore should not be used to compare different classes because means and standard deviations cannot be calculated. They argued that multiple linear regression should be used instead. Burkholder et al. provided very little data in support of their belief, but instead provided a theoretical argument with certain assumptions. We shall show that these assumptions are unreasonable. We also show explicitly how normalized gains from 114 clases taught by six different instructors are indeed normally distributed and how two other even larger samples are roughly normally distributed and are not remotely like a Cauchy distribution. The continued use of normalized gains by physics instructors is therefore justified.http://doi.org/10.1103/PhysRevPhysEducRes.19.010111 |
spellingShingle | Vincent P. Coletta Evidence for a normal distribution of normalized gains Physical Review Physics Education Research |
title | Evidence for a normal distribution of normalized gains |
title_full | Evidence for a normal distribution of normalized gains |
title_fullStr | Evidence for a normal distribution of normalized gains |
title_full_unstemmed | Evidence for a normal distribution of normalized gains |
title_short | Evidence for a normal distribution of normalized gains |
title_sort | evidence for a normal distribution of normalized gains |
url | http://doi.org/10.1103/PhysRevPhysEducRes.19.010111 |
work_keys_str_mv | AT vincentpcoletta evidenceforanormaldistributionofnormalizedgains |