license

Creative Commons License
Where the stuff on this blog is something i created it is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License so there are no requirements to attribute - but if you want to mention me as the source that would be nice :¬)

Saturday, 21 May 2016

10 tips on how to react to a presentation on research / #statistics about an area you care about … #NSMNSS - comments?

Having recently attended a conference presenting research and statistics on an area I care about ... 

... and observing/chatting about my reactions to the presentations (logical / emotional & otherwise) ...

... I had the following thoughts on what advice I'd give myself next time before such a conference - they are particularly focused on how to react to a presentation on research/statistics about an area you care about


... any comments?



1) If findings don’t support your views  - on the day hold fire on criticizing the methodology

2) Assume the findings are correct - consider what you’d need to change if they were

3) Even if the findings aren’t correct - think thru how you'd monitor the issues they raise

4) Clarify with presenters when a correlation is being identified or causation claimed

5) Observe whether graph axis values help reinforce the argument being put forward

6) Check whether graphic proportions in infographics represent the claimed scale of impact

7) Be wary of statistical validity conclusions based on only one value (e.g. a p-value)

8) Consider how the sample methods might introduce bias

9) Identify when management last changed direction based on research/statistics

10) Ask stats professionals their conclusions & compare them with those of management


No comments:

Post a Comment