Quite recently, I began posting my formulas on another site. These are the “magical” formulas I used to develop the maps that I had for national disease patterns, evaluating population pyramids at the one year age range level for statistically significant differences, using plain old SAS, not even SAS-GIS, to produce 3D images of your research areas, and designing health and disease monitoring and prediction models at the managed care level.
One of the funniest things about human behavior is how much age influences what you’ll do in your field. Older participants in the field tend to have that stereotyping thrown at them claiming they get behind in the technology and fall behind in learning about anything new. Not sure if that’s an accurate statement or not.
What I do see however is that the best followers of novelty and innovation are people of the college student age, probably in college. This means that if and when they learn the new technology I throw at them in terms of statistical formulas, that these formulas cannot be validated or approved by their overseers and upper level managers. Such “old timers” are not in tune with the new ideas, new measures, new ways of reviewing numbers. More importantly, as time passes once you’ve completed your training in numbers related work, you lose sense of the philosophy, knowledge and understanding that are needed to know why I argue that one theory from one set of processes is easily transferable to another due to underlying parallels in the logic, methodology and equations used to produce the final numbers, p-values or not.
The statistics world is undergoing hybridization of sorts. Qualitative methods have tended to evolve from quantitative ideologies. Fro the T-test came the U-test for example, and from the ANOVAs came the non-parametric equivalents such as Kruskal-Wallis and Friedman. The 2×2 and 2×3 Chi square work best for numbers between 50 and 2500, or did we forget that, and try to apply it to big data, with numbers amounting to tens of thousands on up?
Manager, leaders who forget the theory, and abide by the book, and what they learned eons ago, limit progress for their companies. This is why students are always smarter in the long run than managers for the most part. And why managers refuse to accept the fact that they don’t really know a lot usually, unless they themselves just graduates of invented something completely new to work with.
There is this idea that developing innovation is important to the new corporate setting. But how varied the definitions of innovations can be, makes many of them just as ridiculous to claim as all the “miracles” we hear about occurring daily. Is that a daily miracle, just experienced by somebody new, or a true miracle that cannot be predicted or explained. Is that method you developed as a statistician a “new” method that is unheard of, in the literature, or in the field, or by you closest colleagues or international knowledge base equivalent?
Innovations are 90% all on paper–like the ones professed to by nearly all insurance companies out there trying to analyze health. I have yet to speak with a company with a formula I haven’t yet cracked the code for. Some of these discoveries are fourth generation, new to Company D, because it stole it from Company C and modified, not knowing that Company C had pulled it years before from Company B, which is a split off of Company A, the original developer of this “black box” routinely used to estimate people’s health risk scores. Yes, companies like insurance companies numbers 2, 3 and 4, “Optimum health” claimers, PBMs, corporate financial overseers, insurance company #1, have all made such claims of “discovering” the same algorithm. A claim seen in each of their advertisements for work positions, on screen, in writing, and on the video about the company. These “innovations” are innovations because the produce believes them to be, thereby revealing the limited knowledge base these developers, producers and managers are already working with.
Some formulas get recognition for their success. Those that no one knew about, neither have the experience or the past of relying upon them. And that’s where the most resistance comes from. That is a good sign your formulas is clean and knew. If it makes them uncomfortable, and unwilling to learn or listen, your innovation is taking the right path.
Therefore, a formula’s secret to success is developing it undercover, without support or feedback from too many peers, in a way that puts it a generation or two ahead of their work. This way, when you share that first level with them, and the bickering begins, you already know you are right, because you are two more generations of use and productivity ahead of what their trying to understand. The worse the management, the more behind companies can be. This is why.