The most important thing for me professionally is: My ability to clearly justify and communicate my modeling decisions.
Not just running analyses—I already do that—but explaining why my approach is the most appropriate given messy, real-world data and competing alternatives.
I often work in situations where:
The data are non-ideal (ordinal, skewed, hierarchical, unbalanced)
The models are complex (GLMMs, CFA/ESEM, IRT, longitudinal designs)
There are multiple defensible approaches
And I need to respond to reviewers, clients, or collaborators who challenge my choices
At that level, the challenge isn’t technical ability—it’s this:
Turning “this works statistically” into “this is the most appropriate, defensible, and interpretable choice.”
Question assumptions instead of taking methods at face value
Compare alternative frameworks
Focus on interpretation, not just statistical significance
I benefit most from improving how I:
1. Frame trade-offs
Instead of just noting limitations, I clearly explain why one approach is preferable given the data and constraints.
2. Pre-empt criticism
I anticipate concerns—especially in areas like model choice, measurement modeling, and power—and address them upfront.
3. Translate across audiences
I bridge the gap between statistical rigor and applied interpretation so that different stakeholders understand and trust my decisions.
If your data are complex and the “right” analytical approach isn’t obvious, I help you choose and defend methods that stand up to scrutiny. I don’t just run models—I ensure your results are technically sound, clearly justified, and ready for reviewers, stakeholders, or publication. Let’s turn uncertainty into decisions you can confidently stand behind.