2022
DOI: 10.1615/jwomenminorscieneng.2022036220
|View full text |Cite
|
Sign up to set email alerts
|

How Statistical Model Development Can Obscure Inequities in Stem Student Outcomes

Abstract: Researchers often frame quantitative research as objective, but every step in data collection and analysis can bias findings in often unexamined ways. In this investigation, we examined how the process of selecting variables to include in regression models (model specification) can bias findings about inequities in science and math student outcomes. We identified the four most used methods for model specification in discipline-based education research about equity: a priori, statistical significance, variance … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 41 publications
0
5
0
Order By: Relevance
“…Indeed, we are aware of how studies examining racial group differences using inferential methods often perpetuate racism and stereotypes, including anti-Black racism and the model minority myth stereotype (Garcia & Mayorga, 2018; Gillborn et al, 2018; Kim et al, 2022). Researchers often use regression models to draw conclusions about students of color that do not take into consideration the effects of structural racism and differences in social experiences and that promote deficit views of students of color (Ross et al, 2020; Van Dusen & Nissen, 2022). The broad categorization of racial and ethnic groups such as we are using in this study (i.e., White, Black, Asian, Hispanic), often masks subgroup differences within each racial group (Ross et al, 2020).…”
Section: Purpose and Significance Of The Studymentioning
confidence: 99%
“…Indeed, we are aware of how studies examining racial group differences using inferential methods often perpetuate racism and stereotypes, including anti-Black racism and the model minority myth stereotype (Garcia & Mayorga, 2018; Gillborn et al, 2018; Kim et al, 2022). Researchers often use regression models to draw conclusions about students of color that do not take into consideration the effects of structural racism and differences in social experiences and that promote deficit views of students of color (Ross et al, 2020; Van Dusen & Nissen, 2022). The broad categorization of racial and ethnic groups such as we are using in this study (i.e., White, Black, Asian, Hispanic), often masks subgroup differences within each racial group (Ross et al, 2020).…”
Section: Purpose and Significance Of The Studymentioning
confidence: 99%
“…Nesting by year was not performed for these models, as student performance in ALEKS was measured before students began their General Chemistry course. To determine the best fit model, four proposed models were compared based on their Akaike Information Criterion Corrected (AICc) values using the AICcmodavg package in R, as recommended by Van Dusen and Nissen for models with intersectionality. , The four proposed models to examine initial knowledge in each content area were: Model 2: Social identities alone Model 3: Social identities, and interaction terms between race/ethnicity and gender Model 4: Social identities, and interaction terms between race/ethnicity and first-generation status Model 5: Social identities, and all interaction terms between race/ethnicity, gender, and first-generation status. Note, this model excluded the race term Asian due the small sample sizes (<16) of the interaction term with Hispanic and Black …”
Section: Methodsmentioning
confidence: 99%
“…This harm includes drawing conclusions about Black students that ignore the effects of structural racism and oppression on Black youth, that compare them to White students as the norm, and that homogenize them across ethnicity and gender as if all Black youth are similarly affected by their social experiences and oppressive systems (Bryan, Williams, et al., 2022; Washington et al., 2023). Therefore, we are seeking to continually examine and challenge the ways in which quantitative research, regression methods, and secondary data analysis perpetuate anti‐Black racism and stereotypes and to understand how to conduct such research through an antiracist lens (Garcia & Mayorga, 2018; Gillborn et al., 2018; Ross et al., 2020; Van Dusen & Nissen, 2022). We understand that one way to better represent the experiences of Black youth is to examine the intersection of race and gender (Ross et al., 2020; Van Dusen & Nissen, 2022; Volpe et al., 2022).…”
Section: Introductionmentioning
confidence: 99%
“…Therefore, we are seeking to continually examine and challenge the ways in which quantitative research, regression methods, and secondary data analysis perpetuate anti‐Black racism and stereotypes and to understand how to conduct such research through an antiracist lens (Garcia & Mayorga, 2018; Gillborn et al., 2018; Ross et al., 2020; Van Dusen & Nissen, 2022). We understand that one way to better represent the experiences of Black youth is to examine the intersection of race and gender (Ross et al., 2020; Van Dusen & Nissen, 2022; Volpe et al., 2022). Therefore, in this study we attempt to explore how schools and school counseling programs affect Black students differentially to better understand the specific needs of Black male and female students and how school counselors may better meet those needs.…”
Section: Introductionmentioning
confidence: 99%