I love learning, trying new ways (to me) of analysing data. Most of my learning is self-taught (autodidact would be the two-dollar word); that is, I hit my head against a problem for a few times, read blogs, articles, more head-hitting and get things working. In some ways the process is highly inefficient: it would be a lot easier to take a course (if available). However, the inefficiency is somewhat compensated by the actual learning that occurs, as learning by doing is easier to retain.
Many researchers run a lot of ideas, some of them end up as published articles, but many (most in my case) are never formally published. Formal publication needs a lot of work and—confession time—I often find the formal writing part really-super-extremely boring. Writing fiction is fun, following a recipe for an article not so much for me. I really envy people for whom scientific writing comes easily.
Anyhow, I was reading this article announcement in LinkedIn and then I thought “I was mucking around with something related in 2019!”. Using Bayes B approaches with extractive contents in wood, but in my case it didn’t work out so well, so I shoved it in my incomplete project drawer. I don’t mean a literal, physical drawer in my desk, but in a computer folder. This got me thinking about all the other things that were learning experiments, just sitting there. And this took me to thinking of other researchers and their own drawers: there must be a huge number of ideas, experiments, analyses that never went anywhere, not even as a blog post.
On the plus side, I get the pleasure of reading and learning about NIRS from a cool paper on blueberry breeding (yum!).
