[DataWorker]

The scientific process as it stands at present is greatly overestimated in its ability to reach firm conclusions. It comes down to trust. Do you trust the studies that say fat and salt and alcohol have no deleterious effects? Do you trust meta-analysis because “more must better”? These issues are coming to a head and I think we’re in a transition right now but I don’t know what’s next. Some want to abandon significance testing, some think frequentist approaches should be discarded in favor of Bayesian. Meanwhile people cling to the dogma of scientific rigor because without that, what do we have. Whether the flaws in our current efforts are endemic or the result of economic factors is unclear. Publication bias is clearly an economic problem, but the problems I worry most about are things like measurement error and clerical mistakes like this https://www.bloomberg.com/news/articles/2013-04-18/faq-reinh...