Higher credence for the masses: From a Ted talk?

May 16, 2017

(This article was originally published at Statistical Modeling, Causal Inference, and Social Science, and syndicated at StatsBlogs.)

The Four Most Dangerous Words? A New Study Shows | Laura Arnold | TEDxPennsylvaniaAvenue

I brought this link forward in some comments but wanted to promote it to a post as I think its important and I know many folks just do not read comments.

As I once heard claimed in a talk on risk communication – “No one has as much credibility as a mother voicing concerns about her children – No one!” Now, academics have been voicing concerns about the quality of published studies and claims for a long time, me in 1989, others inspired by Fisher in 1959 and CS Peirce in 1879. Recently there has been an exponential explosion in the voicing of concerns about  the quality of published studies – but it does not seem to be reaching the masses. Academics must not have much credibility with the masses?

Now, in this TEDx talk we have someone that most folks will likely believe has the money to be a willing philanthropist and who does want that money to do some good, if not the maximum amount of good. They voice an inability to do that simply because they perceive the evidence in published studies is no where near adequate quality. In fact, that is where they now believe they need to spend their money (nuisance funding – what they wish they did not need to do) in order to have some hope in the future to fund ways to make the world better (interest funding – what they want to do). They cite some examples that have been discussed on this blog and even parody a TED talk on one of them.

Will it have high credence with the masses? So far less than 25,000 views – does not seem like the masses are there – yet.

p.s. Revised: In the original post I had put “washed up Wonder Woman” as the subtitle [which the editor replaced with “a Ted talk”] as it appeared as  a rude comment about the presenter’s appearance and I thought it would be a good example of why many people just don’t read comments. Originally writing here  – so I understand why many do not want to read comments – in 2017 we would hope a woman can give a talk and not have her appearance disparagingly commented on.  On this blog though many of the comments are worth reading and one way to slowly wade in is to start reading comments from some commenters and just keep with the ones that seem worthwhile.

p.s.2 Around 2005 I had a conversation with the president of a large disease based charity about how naivety in terms of running clinical trails (e.g. implementing/managing randomisation schedules, tracking trial progress, data entry quality control, engaging statistical consulting, reproducible analyses, etc.) of the clinicians they were funding was wasting a lot of their funds. I argued that this could be fixed rather inexpensively by funding some common resources for them to draw on.  They agreed this made a lot of sense but was sure it would not look very good to their donors as they would expect the money would only be directly spent on disease X. They did say they would see if other disease based charities might consider jointly pooling some resources.

Never heard back, but I think I started to understand why funding improvements in research quality was seen as unattractive.  (Only a very small percentage of grant submissions on reproducible research were being funded back then and I was perplexed about that. ) But just the appearance of high quality (if  credible enough to the masses) was more than adequate to make the funding system run smoothly (e.g. charities, funding agencies, research institutes, universities and governments). That is, poor research was likely to get as much positive publicity if not more than more expensive to fund higher quality research.

Its the really needing to depend on using the research that makes the real quality matter enough to be willing to risk investing in it in a world where research quality is poorly understood.

The post Higher credence for the masses: From a Ted talk? appeared first on Statistical Modeling, Causal Inference, and Social Science.

Please comment on the article here: Statistical Modeling, Causal Inference, and Social Science

Tags: ,