Research Design

by Lauren Liao. When evaluating causal inference in observational studies, there often is a natural imbalance in the data. Luckily, variables are often measured alongside that can be helpful for adjustment. However, deciding which variables should be prioritized for adjustment is not trivial – since not all variables are equally important to the intervention or the outcome. I recommend using the joint variable importance plot during the observational study design phase to visualize which variables should be prioritized. This post provides a gentle guide on how to do so and why it is important.

by Leah Lee. Large-scale geographic data over time on insect diversity can be used to answer important questions in Entomology. Open-source, open-access citizen science platforms like iNaturalist generate huge amounts of data on species diversity and distribution at accelerating rates. However, unstructured citizen science data contain inherent biases and need to be used with care. One of the efforts to validate big data from iNaturalist is to cross-check with systematically collected data, such as museum specimens.

by Farnam Mohebi. As an aspiring leading researcher, I find the full-cycle research methodology crucial for transforming initial curiosities into organized studies and research products. This approach begins with thorough observation, leads to theory and hypothesis development and experimentation, and concludes with synthesizing findings into coherent narratives. It's beneficial for researchers of all backgrounds, enhancing the depth and impact of their work. By embracing this method, researchers comprehensively understand each stage and its contribution to the broader research context and can lead the process of converting an initial unspecified research idea to a streamlined research study and product. This systematic approach is particularly effective in complex studies, fostering thorough, investigative, and innovative research processes.