Influence of Expectations and Belonging on Science Identity: Estimation Thinking with HSLS:09 Data

• In Event: Advancing Estimation Thinking in Educational Leadership Research: Methodological Innovations and Practical Implications

Abstract

Objectives or Purposes:
This paper uses multiple-group latent growth curve modeling to examine how principals’ and teachers’ expectations and students’ sense of belonging influence high school students’ science identity growth. The objective is to demonstrate the application of estimation thinking to analyze longitudinal data from the High School Longitudinal Study of 2009 (HSLS:09).

Theoretical Framework:
The study is framed within the context of estimation thinking, which emphasizes the use of effect sizes, confidence intervals, and latent growth curve modeling to capture the dynamic nature of student development over time. This approach contrasts with dichotomous thinking, which relies on NHST and p-values to determine significance.

Methods:
The study employs multiple-group latent growth curve modeling to analyze HSLS:09 data. This method allows for the examination of individual growth trajectories and the identification of factors influencing science identity development. The analysis includes the use of effect sizes, confidence intervals, and model fit indices to provide a comprehensive understanding of the data.

Data Sources:
Data from the HSLS:09 were used, which includes information on students’ science identity, sense of belonging, and perceptions of school leadership. The longitudinal nature of the data allows for a detailed analysis of student development over time.

Results and/or Conclusions:
The findings highlight the importance of estimation thinking in analyzing longitudinal data. The study demonstrates that principals’ and teachers’ expectations significantly influence students’ science identity growth, with variations observed among different racial and ethnic groups. The use of effect sizes and confidence intervals provides a nuanced understanding of these relationships, emphasizing the need for estimation thinking in educational research.

Scientific or Scholarly Significance:
This research underscores the value of estimation thinking in analyzing complex longitudinal data. By using latent growth curve modeling and emphasizing effect sizes and confidence intervals, the study provides a more accurate and meaningful interpretation of the data. The findings highlight the need for methodological rigor in educational research, promoting the use of advanced statistical techniques to capture the dynamic nature of student development.
The study provides practical guidelines for researchers, including the importance of using estimation thinking to analyze longitudinal data, the need for transparency in reporting, and the value of effect sizes and confidence intervals in understanding complex relationships. This research contributes to the ongoing dialogue on methodological innovation in educational research, advocating for a shift towards estimation thinking to enhance the validity and reliability of research findings.

Author

• Joonkil Ahn, University of Arizona