Despite some initial startup time to learn R, it is gaining popularity in use due to being an open-source program with no direct costs, wide access around the world, the capability to be used on Windows, MacOS, and other platforms, the ability to import data from different kinds of files (e.g., Excel, SPSS, SAS, etc.), the availability of more than 2,000 statistical packages, and easy access to information, tutorials, and other input on R through online resources. The current talk presents a confirmatory factor analysis application (CFA) using the open-source R program, lavaan. In the talk, I’ll feature a number of steps in the application, including: (1) a theoretical model drawn from Risman (2004) who emphasizes that individual, interactional and institutional factors are needed to understand the nature of structures or constructs such as Career Satisfaction; (2) preliminary data analyses to check the data and internal consistency of the constructs; (3) analyzing three CFA models of four Work-Environment constructs (i.e., Career Influence, Work Climate, Work Respect, and Career Satisfaction); and (4) interpreting the results and briefly suggesting possible next steps. Work-environment data from 265 faculty at a New England University will be made available, as will a copy of the R code and output for any who would like to gain practice analyzing this CFA application with lavaan. If interested, download the latest version of R from the R Project (https://www.r-project.org/), as well as a user-friendly graphical interface called R Studio (https://rstudio.com/products/rstudio/download/). They both should be loaded onto your computer if you would like to use R or R studio to conduct analyses such as CFA with R. If you are like me, you may find that R is initially challenging but with ongoing practice and use, it becomes rather beckoning and captivating, and definitely worth using.
Risman, B. J. (2004). Gender as a social structure: Theory wrestling with activism. Gender & Society, 18(4), 429-450.
*Thanks for data from a $3,500,000 NSF Grant Award (#0245039): Advancing Women in the Sciences (PI: B. Silver).
Using the R package, lavaan, a CFA model assesses the structure of Career Influence, Work Climate, Work Respect, and Career Satisfaction. Three CFA versions are tested: a correlated model, an orthogonal model, and an “all-one” model (i.e., fixing correlations among factors at 1.0 that tests a single general factor).