Recently, I’ve run into posts, articles, and discussions concerning findings that employee morale doesn’t equate to productivity. They are an excellent example of how easily we can mislead ourselves with data.
ADVERTISEMENT |
By way of background, apparently some of the research groups and “better management” consulting firms assembled analyses refuting the assumption that higher employee morale will drive higher employee productivity. Hearing such a statement, some of us immediately acknowledge that the findings merely state the obvious. Some of us argue that the analyses couldn’t have drawn an accurate conclusion. Some of us demand to see the data and the analyses, suspicious that something so obviously complex couldn’t possibly be summed up so simply.
…
Comments
Title change?
Alan - you raise some very important points. The veracity of a study is related more to the structure of the 'experiment' and how, exactly, the data were analyzed than anything else. This is why we get a study one day that says 'don't drink coffee' and the next day 'coffee will save your life'.
I might recommend that the title would be more accurate if it were "trusting too much in reprted findings that don't disclose the analytical structure and the data itself" (usually a well designed graph of the data - not summary statistics - is sufficient.
My rules at work is that stories aren't allowed unless accompanied by the structure and graphical analysis...
Reply, "Title Change"
BDANIELS,
Thanks for reading and for your constructive comment. I'm glad to hear that there is at least one more person out there too wise to be misled by stories about data. I concede to your suggestion that a different title might better match the message; where was your advice when I wrote the post? Perhaps I should have titled it, "Trusting Too Much in Tales of Data."
Thanks,
Alan
Add new comment