Work in Progress: Large-Scale Sampling and Recruitment of Engineering Doctoral Students

Daniel Briggs; Jessica Nicole Chestnut; Adam Kirn; Cheryl Cass

Download Paper | Permalink

Conference: 2017 ASEE Annual Conference & Exposition
Location: Columbus, Ohio
Publication Date: June 24, 2017
Start Date: June 24, 2017
End Date: June 28, 2017
Conference Session: Quantitative Research Methods
Tagged Division: Educational Research and Methods
Page Count: 8
DOI: 10.18260/1-2--29167
Permanent URL: https://peer.asee.org/29167
Download Count: 471

Request a correction

Paper Authors

biography

Daniel Briggs North Carolina State University

visit author page

I am a May 2017 graduate with a BS in Statistics from North Carolina State University. In August, I will begin attending Harvard TH Chan School of Public Health to pursue a MS in Biostatistics.

visit author page

author page

Jessica Nicole Chestnut North Carolina State University

biography

Adam Kirn University of Nevada, Reno orcid.org/0000-0001-6344-5072

visit author page

Adam Kirn is an Assistant Professor of Engineering Education at University of Nevada, Reno. His research focuses on the interactions between engineering cultures, student motivation, and their learning experiences. His projects involve the study of student perceptions, beliefs and attitudes towards becoming engineers, their problem solving processes, and cultural fit. His education includes a B.S. in Biomedical Engineering from Rose-Hulman Institute of Technology, a M.S. in Bioengineering and Ph.D. in Engineering and Science Education from Clemson University.

visit author page

biography

Cheryl Cass North Carolina State University

visit author page

Cheryl Cass is a teaching assistant professor in the Department of Materials Science and Engineering at North Carolina State University where she has served as the Director of Undergraduate Programs since 2011. Her research focuses on the intersection of science and engineering identity in post-secondary and graduate level programs.

visit author page

Download Paper | Permalink

Abstract

This work in progress research paper describes methodology for large-scale sampling of doctoral engineering students to analyze identity and motivation profiles, which can affect persistence. A sample size of 253 doctoral engineering programs was chosen. Doctoral engineering programs are known to have an approximately fifty-percent attrition rate, but the factors influencing attrition are obscured by limited studies in doctoral education. Small-scale and convenience sampling limit the ability to generalize results, and large-scale surveying has been implemented to capture graduate experiences but does not reflect the attitudes and experiences of students who might report hesitancy in completing a doctoral degree. As such, we will survey currently enrolled doctoral engineering students to explore the affective factors that may influence student graduation rates. To initiate discussion of engineering doctoral student attrition, we address the following research question: How do we create a sample design that allows us to capture the diverse population of engineering doctoral students and their attitudes? Engineering departments were allocated to geographic regions and received codes for academic programs based on Engineering by the Numbers to enhance diversity in the doctoral student sample by stratifying amongst geographic distribution and potential programmatic norms. Each department was coded for no more than three academic program types to account for variability within departments. Department size was imputed using the number of doctoral degrees awarded to each program as a proxy using information gathered from NSF Reported Doctorate Recipients from U.S. Universities and determined to be small, medium, or large using quantiles as determinants for allocation. Department size was stratified to minimize the influence of large, influential programs by requiring the presence of small and medium sized programs within the sample. Previous work considered region, department size, and academic program classification separately in methodology but has not utilized all three factors in a multistage cluster sampling design. The doctoral degree programs are divided into five geographic groups, then stratified by size. Finally, academic programs are sampled using probability proportional to size, where size is defined as frequency of the academic program within the smallest sampling unit. All academic programs in departments with multiple academic tracks are considered as sampling units and counted against the expected total for each program if another academic program from the same department is selected in the sample to reduce the total number of departments sampled, thus simplifying the recruitment process. Further probabilistic sampling techniques are unnecessary, as a census of students in selected academic programs will be taken. Sampling techniques described in this research facilitate recruitment of participating departments and create a generalizable protocol that permits easy replacement of non-participating programs, objective statistical analysis, and a representative sample. Further work will focus on the recruitment of doctoral degree granting engineering programs in a consistent manner based on this sampling design.

Citation
Format

Briggs, D., & Chestnut, J. N., & Kirn, A., & Cass, C. (2017, June), Work in Progress: Large-Scale Sampling and Recruitment of Engineering Doctoral Students Paper presented at 2017 ASEE Annual Conference & Exposition, Columbus, Ohio. 10.18260/1-2--29167

TY  - CPAPER
AB  - This work in progress research paper describes methodology for large-scale sampling of doctoral engineering students to analyze identity and motivation profiles, which can affect persistence. A sample size of 253 doctoral engineering programs was chosen. Doctoral engineering programs are known to have an approximately fifty-percent attrition rate, but the factors influencing attrition are obscured by limited studies in doctoral education. Small-scale and convenience sampling limit the ability to generalize results, and large-scale surveying has been implemented to capture graduate experiences but does not reflect the attitudes and experiences of students who might report hesitancy in completing a doctoral degree. As such, we will survey currently enrolled doctoral engineering students to explore the affective factors that may influence student graduation rates. To initiate discussion of engineering doctoral student attrition, we address the following research question: How do we create a sample design that allows us to capture the diverse population of engineering doctoral students and their attitudes?
 
Engineering departments were allocated to geographic regions and received codes for academic programs based on Engineering by the Numbers to enhance diversity in the doctoral student sample by stratifying amongst geographic distribution and potential programmatic norms. Each department was coded for no more than three academic program types to account for variability within departments. Department size was imputed using the number of doctoral degrees awarded to each program as a proxy using information gathered from NSF Reported Doctorate Recipients from U.S. Universities and determined to be small, medium, or large using quantiles as determinants for allocation. Department size was stratified to minimize the influence of large, influential programs by requiring the presence of small and medium sized programs within the sample.    
 
Previous work considered region, department size, and academic program classification separately in methodology but has not utilized all three factors in a multistage cluster sampling design. The doctoral degree programs are divided into five geographic groups, then stratified by size. Finally, academic programs are sampled using probability proportional to size, where size is defined as frequency of the academic program within the smallest sampling unit. All academic programs in departments with multiple academic tracks are considered as sampling units and counted against the expected total for each program if another academic program from the same department is selected in the sample to reduce the total number of departments sampled, thus simplifying the recruitment process. Further probabilistic sampling techniques are unnecessary, as a census of students in selected academic programs will be taken.          
 
Sampling techniques described in this research facilitate recruitment of participating departments and create a generalizable protocol that permits easy replacement of non-participating programs, objective statistical analysis, and a representative sample. Further work will focus on the recruitment of doctoral degree granting engineering programs in a consistent manner based on this sampling design.
AU  - Daniel Briggs
AU  - Jessica Nicole Chestnut
AU  - Adam Kirn
AU  - Cheryl Cass
CY  - Columbus, Ohio
DA  - 2017/06/24
PB  - ASEE Conferences
TI  - Work in Progress: Large-Scale Sampling and Recruitment of Engineering Doctoral Students
UR  - https://peer.asee.org/29167
DO  - 10.18260/1-2--29167
ER  -