Addressing confirmation bias in middle school data science education

Sarai Hedges; Kim Given

doi:10.3934/fods.2021035

Article Contents

2023, Volume 5, Issue 2: 223-243. Doi: 10.3934/fods.2021035

This issue Previous Article Facilitating API lookup for novices learning data wrangling using thumbnail graphics Next Article Facilitating team-based data science: Lessons learned from the DSC-WAV project

Addressing confirmation bias in middle school data science education

Sarai Hedges^1, and
Kim Given^2,

1.
Associate Professor, Department of Mathematical Sciences, College of Arts & Sciences, University of Cincinnati, USA
2.
Gifted Intervention Specialist, Indian Hill Middle School, Indian Hill Ohio, USA

Received: July 2021

Revised: October 2021

Early access: January 2022

Published: June 2023

Abstract / Introduction Full Text(HTML) Figure(0) / Table(3) Related Papers Cited by

Abstract

More research is needed involving middle school students' engagement in the statistical problem-solving process, particularly the beginning process steps: formulate a question and make a plan to collect data/consider the data. Further, the increased availability of large-scale electronically accessible data sets is an untapped area of study. This interpretive study examined middle school students' understanding of statistical concepts involved in making a plan to collect data to answer a statistical question within a social issue context using data available on the internet. Student artifacts, researcher notes, and audio and video recordings from nine groups of 20 seventh-grade students in two gifted education pull-out classes at a suburban middle school were used to answer the study research questions. Data were analyzed using a priori codes from previously developed frameworks and by using an inductive approach to find themes.

Three themes that emerged from data related to confirmation bias. Some middle school students held preconceptions about the social issues they chose to study that biased their statistical questions. This in turn influenced the sources of data students used to answer their questions. Confirmation bias is a serious issue that is exacerbated due to endless sources of data electronically available. We argue that this type of bias should be addressed early in students' educational experiences. Based on the findings from this study, we offer recommendations for future research and implications for statistics and data science education.

Keywords:

Mathematics Subject Classification: Primary: 62R07; Secondary: 97K80, 97C30.

Citation:

Full Text(HTML)

Table 1. Groups' Question and Study Design Development

Group (Size)	Question Versions	Initial Question Final Question	Study Design for Final Question
1 (2)	3	How does overpopulation affect quality of life? How does overpopulation affect mortality rate?	Most and least populated country in each continent in 2016 from World Bank, Statistics Times, and Worldometers
2 (2)	10	What affects poverty? [Do] race and ethnicity of people affect the average yearly income they make?	Race/ethnicity and highest and lowest income categories in 2016 from U.S. Census
3 (2)	8	How many people are living in poverty? Is the rate of children being born into poverty decreasing in the United States of America?	Child poverty in U.S. in 2000 – 2016 from KidsCount
4 (2)	4	How many people are eating based on MyPlate regulations in the United States of America per day? What percentage of students get a free or reduced lunches [sic] per county (in Ohio)?	Six largest counties in Ohio in 2017 from CDC website
5 (3)	3	How many cats and dogs are abused each year in the USA? What percent of the animal abuse cases in New York City are neglected?	Animal abuse cases reported in 2017-2108 from NYC Open Data
6 (2)	6	What are the ages of people in poverty? What percent of people in the U.S. are in poverty per state?	Poverty per state in 2016 from KidsCount
7 (2)	11	How are animals affected by climate change? How has average precipitation within the U.S.A. changed over the course of 17 years? (2000-2017)?	Average precipitation in 2000–2017 from National Centers for Environmental Information (NCEI)
8 (3)	6	What is the current poverty rate in the United States? What is the income to poverty ratio for people of different age groups?	Income to poverty ratios by age group in 2016 from U.S. Census
9 (2)	4	What was the most dangerous modern war? What is the total number of civilian deaths in Afghanistan that were [sic] killed by ISAF from 2010 to 2013?	Subset of CIVCAS database provided in Science Magazine

| Show Table

DownLoad: CSV

Table 2. Pertinent Data Codes and Themes

Type	Code/Theme
In vivo	"reliable data"
Emergent	Sampling from the extremes Preconceptions

| Show Table

DownLoad: CSV

Table 3. Students' Meanings of the Term Reliable Data Source

Reliable data come from...	Count (Groups)
Government organization or from the teacher	4 (1, 6, 7, 9)
Varied/multiple sources	4 (2, 3, 7, 9)
No explanation given	1 (8)
Note: Groups 7 and 9 gave different definitions at different times.

| Show Table

DownLoad: CSV

Related Papers

Cited by

References

[1]	A. Agresti, C. Franklin and B. Klingenberg, Statistics: The Art and Science of Learning from Data, 4th edition, Pearson, Boston, 2017.
[2]	J. Ainley and D. Pratt, Computational modelling and children's expressions of signal and noise, Statistics Education Research Journal, 16 (2017), 15-37. doi: 10.52041/serj.v16i2.183.
[3]	The Annie E. Casey Foundation Kids Count Data Center, About Kids Count Data Center, (n.d.)., Available from https://datacenter.kidscount.org/about.
[4]	K. Aridor and D. Ben-Zvi, Statistical modeling to promote students' aggregate reasoning with sample and sampling, ZDM, 50 (2018), 1165-1181. doi: 10.1007/s11858-018-0994-5.
[5]	P. M. Arnold, Statistical Investigative Questions: An Enquiry into Posing and Answering Investigative Questions from Existing Data, Ph.D thesis, 2013. Available from http://researchspace.auckland.ac.nz.
[6]	A. Bargagliotti, C. Franklin, P. Arnold, R. Gould, S. Johnson, L. Perez and D. A. Spangler, Guidelines for Assessment and Instruction in Statistics Education II (GAISE II): A Framework for Statistics and Data Science Education, American Statistical Association, Alexandria, 2020. Available from https://www.amstat.org/asa/education/Guidelines-for-Assessment-and-Instruction-in-Statistics-Education-Reports.aspx.
[7]	L. Bershidsky, No, big data didn't win the U.S. election, in Bloomberg View, (2016, December 8). Available from https://www.bloomberg.com/view/articles/2016-12-08/no-big-data-didn-t-win-the-u-s-election.
[8]	C. Büscher and S. Schnell, Students' emergent modelling of statistical measures – a case study, Statistics Education Research Journal, 16 (2017), 144-162.
[9]	S. B. Bush, K. S. Karp, J. Albanese and F. Dillon, The oldest person you've known, Mathematics Teaching in the Middle School, 20 (2015), 278-285. doi: 10.5951/mathteacmiddscho.20.5.0278.
[10]	B. J. Casad, Confirmation bias, in Encyclopedia Britannica, 2009. Available from https://www.britannica.com/science/confirmation-bias.
[11]	J. W. Creswell, Qualitative Inquiry and Research Design: Choosing Among Five Approaches, 3rd edition, Sage, Thousand Oaks, 2013.
[12]	The Concord Consortium, Common Online Data Analysis Platform (CODAP), 2018. Available from https://codap.concord.org/.
[13]	M. Dawkins, B. Gentile-Henning, K. Given, M. Burgess, E. Leppert and M. Stewart, Information for Parents and Educators Working With Gifted Students, 2017. Available from https://www.indianhillschools.org/Downloads/Indian%20Hill%20Gifted%20Handbook%20November%202019.pdf.
[14]	C. Duhigg, How companies learn your secrets, in The New York Times Magazine, (2012, February 16). Available from http://www.nytimes.com/2012/02/19/magazine/shopping-habits.html?_r=1&pagewanted=all. doi: 10.7312/star16075-025.
[15]	T. G. Edwards, A. Özgün-Koca and J. Barr, Interpretations of boxplots: Helping middle school students to think outside the box, Journal of Statistics Education, 25 (2017), 21-28. doi: 10.1080/10691898.2017.1288556.
[16]	Facing the Future, Facing the Future, 2018. Available from https://www.facingthefuture.org/.
[17]	C. Franklin, G. Kader, A. Bargagliotti, D. Mewborn, J. Moreno, R. Peck, M. Perry and R. Scheaffer, Guidelines for Assessment and Instruction in Statistics Education (GAISE) Report: A PreK-12 Curriculum Framework, American Statistical Association, Alexandria, 2007. Available from http://www.amstat.org/ASA/Education/Guidelines-for-Assessment-and-Instruction-in-Statistics-Education-Reports.aspx.
[18]	R. Gould, Statistics and the modern student, International Statistical Review, 78 (2010), 297-315. doi: 10.1111/j.1751-5823.2010.00117.x.
[19]	R. Gould, A. Bargagliotti and T. Johnson, An analysis of secondary teachers' reasoning with participatory sensing data, Statistics Education Research Journal, 16 (2017), 305–334. Available from http://iase-web.org/Publications.php?p=SERJ doi: 10.52041/serj.v16i2.194.
[20]	R. E. Groth, M. Jones and M. Knaub, Working with noise in bivariate data, Mathematics Teaching in the Middle School, 23 (2017), 82-89. doi: 10.5951/mathteacmiddscho.23.2.0082.
[21]	I. Hernandez and J. L. Preston, Disfluency disrupts the confirmation bias, Journal of Experimental Social Psychology, 49 (2013), 178-182.
[22]	R. Hurworth, Interpretivism, in Encyclopedia of Evaluation (ed. S. Mathison), (2005), 209–210.
[23]	S. Kazak, D. Pratt and R. Gökce, Sixth grade students' emerging practices of data modelling, ZDM - Mathematics Education, 50 (2018), 1151-1163. doi: 10.1007/s11858-018-0988-3.
[24]	N. C. Lavigne and S. P. Lajoie, Statistical reasoning of middle school children engaging in survey inquiry, Contemporary Educational Psychology, 32 (2007), 630-666.
[25]	M. Lenker, Motivated reasoning, political information, and information literacy education, Portal: Libraries and the Academy, 16 (2016), 511-528. doi: 10.1353/pla.2016.0030.
[26]	Y. S. Lincoln and E. G. Guba, Naturalistic Inquiry, Sage, Newbury Park, 1985.
[27]	Magnified Giving, Magnified Giving, (n.d.). Available from http://www.magnifiedgiving.org/.
[28]	J. H. Michalski, The sociological determinants of scientific bias, Journal of Moral Education, (2020). doi: 10.1080/03057240.2020.1787962.
[29]	M. B. Miles, A. M. Huberman and J. Saldaña, Qualitative Data Analysis: A Methods Sourcebook, 3rd edition, Sage, Thousand Oaks, 2014.
[30]	W. L. Neuman, Social Research Methods: Qualitative and Quantitative Approaches, 7th edition, Pearson Education, Boston, 2011.
[31]	C. Nolan and S. Herbert, Introducing linear functions: An alternative statistical approach, Mathematics Education Research Journal, 27 (2015), 401-421. doi: 10.1007/s13394-015-0147-x.
[32]	Ohio Department of Education, Gifted Screening and Identification, 2018. Available from https://education.ohio.gov/Topics/Other-Resources/Gifted-Education/Gifted-Screening-and-Identification.
[33]	C. O'Neil, Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy, Crown, New York, 2016.
[34]	A. Patel and M. Pfannkuch, Developing a statistical modeling framework to characterize year 7 students' reasoning, ZDM, 50 (2018), 1197-1212. doi: 10.1007/s11858-018-0960-2.
[35]	Public School Review., 2018. Available from https://www.publicschoolreview.com/indian-hill-middle-school-profile.
[36]	J. Reid and C. Carmichael, A taste of Asia with statistics and technology, Australian Primary Mathematics Classroom, 20 (2015), 10-14.
[37]	Represent, in Merriam-Webster.com, (n.d.). Available from https://www.merriam-webster.com/dictionary/represent.
[38]	J. Ridgway, Implications of the data revolution for statistics education, International Statistical Review, 84 (2016), 528-549. doi: 10.1111/insr.12110.
[39]	M. B. Roscoe, A vehicle for bivariate data analysis, Mathematics Teaching in the Middle School, 21 (2016), 348-356. doi: 10.5951/mathteacmiddscho.21.6.0348.
[40]	A. Savard and D. Manuel, Teaching statistics: Creating an intersection for intra and interdisciplinarity, Statistics Education Research Journal, 15 (2016), 239-256. doi: 10.52041/serj.v15i2.250.
[41]	P. Stapleton, Cognitive biases: Promoting good decision making in research methods courses, Teaching in Higher Education, 24 (2019), 578-586. doi: 10.1080/13562517.2018.1557137.
[42]	D. E. Varberg, The development of modern statistics, The Mathematics Teacher, 56 (1963), 252-257.
[43]	J. Watson, K. Beswick, N. Brown, R. Callingham, T. Muir and S. Wright, Digging into Australian Data with TinkerPlots, Objective Learning Materials, Melbourne, 2011.
[44]	J. M. Watson and J. B. Moritz, Development of sampling for statistical literacy, Journal of Mathematical Behavior, 19 (2000), 109-136.
[45]	H. G. Wells, Mankind in the Making, Chapman and Hall, London, 1903. Available from http://www.gutenberg.org/ebooks/7058.
[46]	C. H. Wild and M. Pfannkuch, Statistical thinking in empirical enquiry, International Statistical Review, (1999), 223–248. Available from http://www.jstor.org/stable/1403699.
[47]	M. H. Wilkerson and V. Laina, Middle school students' reasoning about data and context through storytelling with repurposed local data, ZDM - Mathematics Education, 50 (2018). doi: 10.1007/s11858-018-0974-9.
[48]	L. Zapata-Cardona, Students' construction and use of statistical models: A socio-critical perspective, ZDM - Mathematics Education, 50 (2018), 1213-1222. doi: 10.1007/s11858-018-0967-8.