Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Using the structure of the residuals to evaluate the goodness of fit : a pedagogical case study with Newton’s law of cooling

Dunnett, K. LU ; Le, Kim Cuong LU orcid and Holmqvist, T. LU (2025) In European Journal of Physics 46(5).
Abstract

Introductions to data analysis in university physics often focus on fitting (typically to linearised functions) and uncertainty propagation, but residuals are less commonly introduced. Structured residuals indicate that the function (theoretical description) used to fit data does not capture all the relevant elements (i.e. the theoretical description is incomplete), and can be present even when the fit line is within the error bars of all data points. Residuals are therefore resilient to strategies such as forcing numerical agreement between data and theory (fit) through increasing uncertainty estimates. In this paper, we argue that introducing residuals alongside fitting could be an effective strategy for encouraging critical... (More)

Introductions to data analysis in university physics often focus on fitting (typically to linearised functions) and uncertainty propagation, but residuals are less commonly introduced. Structured residuals indicate that the function (theoretical description) used to fit data does not capture all the relevant elements (i.e. the theoretical description is incomplete), and can be present even when the fit line is within the error bars of all data points. Residuals are therefore resilient to strategies such as forcing numerical agreement between data and theory (fit) through increasing uncertainty estimates. In this paper, we argue that introducing residuals alongside fitting could be an effective strategy for encouraging critical scientific thinking, particularly about trusting and understanding one’s data, and a useful tool for identifying—and realising—laboratory tasks that students can develop into genuine investigations. We illustrate this with a simple experiment of cooling water where the structured residuals of the fitted temperature data clearly indicate that the theoretical description (Newton’s Law of Cooling) is insufficient. This demonstrates the overlooked potential for residuals to be introduced as one of the earliest elements of data analysis.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
data analysis, Newton’s law of cooling, residuals
in
European Journal of Physics
volume
46
issue
5
article number
055104
publisher
IOP Publishing
external identifiers
  • scopus:105016999565
ISSN
0143-0807
DOI
10.1088/1361-6404/ae0201
language
English
LU publication?
yes
id
1ac7c3b9-0380-401f-944c-b5f494140ada
date added to LUP
2025-11-26 13:14:57
date last changed
2025-11-26 13:16:04
@article{1ac7c3b9-0380-401f-944c-b5f494140ada,
  abstract     = {{<p>Introductions to data analysis in university physics often focus on fitting (typically to linearised functions) and uncertainty propagation, but residuals are less commonly introduced. Structured residuals indicate that the function (theoretical description) used to fit data does not capture all the relevant elements (i.e. the theoretical description is incomplete), and can be present even when the fit line is within the error bars of all data points. Residuals are therefore resilient to strategies such as forcing numerical agreement between data and theory (fit) through increasing uncertainty estimates. In this paper, we argue that introducing residuals alongside fitting could be an effective strategy for encouraging critical scientific thinking, particularly about trusting and understanding one’s data, and a useful tool for identifying—and realising—laboratory tasks that students can develop into genuine investigations. We illustrate this with a simple experiment of cooling water where the structured residuals of the fitted temperature data clearly indicate that the theoretical description (Newton’s Law of Cooling) is insufficient. This demonstrates the overlooked potential for residuals to be introduced as one of the earliest elements of data analysis.</p>}},
  author       = {{Dunnett, K. and Le, Kim Cuong and Holmqvist, T.}},
  issn         = {{0143-0807}},
  keywords     = {{data analysis; Newton’s law of cooling; residuals}},
  language     = {{eng}},
  number       = {{5}},
  publisher    = {{IOP Publishing}},
  series       = {{European Journal of Physics}},
  title        = {{Using the structure of the residuals to evaluate the goodness of fit : a pedagogical case study with Newton’s law of cooling}},
  url          = {{http://dx.doi.org/10.1088/1361-6404/ae0201}},
  doi          = {{10.1088/1361-6404/ae0201}},
  volume       = {{46}},
  year         = {{2025}},
}