skewing the data

15 03 2007

in my efforts to push the envelop on improving our professional image, I’ve been calling out gross instances of the type of work that makes us look bad to our peers and superiors thus harming our reputations and calling into question our professionalism. 

this example is from the report on training administration and operations just published by expertus and trainingoutsourcing.com.  you can get a free copy of the report if you are a member of trainingoutsourcing.com.  membership is free.

take a look at this graphic and think about how you would write or talk about the data set that it represents.
Outsourcing_fudge_3

now you might say something like a majority of programs estimate that their percentage spend on administration and operations is under 20%.   or 8% have cost control problems.  right?  Here’s what the survey’s report says about this data:

Survey Highlights

  • Results show that administrative expenses are high in most organizations:  7.6% of respondents said their companies spent more than 50% of their training budgets on administration and operations; 10.2% spent between 36 and 50%; and 29.3% spent 20 to 35%.

what!!!!!  what about the other 53% of the respondents.  47% does not constitute "most" of the respondents.  what’s the break down of the 53% of organizations who are below 20%.  for all we know, cost could be running under 10% for half the respondents.  but then again, that wouldn’t be good for an organization who is in existence to promote the efficiencies that outsourcing can bring to an organization.

this ladies and gentlemen, boys and girls, is a particularly mangled attempt to skew the presentation of the data to make it look more favorable to one’s own position, no matter what the data actually says.  usually skewing the data will be seen by your audience and will undercut your credibility on this and future topics. 

if you do research in hopes of supporting your position, but end up with data that harms your position you might be able to pretend that there was no research was done or that some how the study was compromised.  but the best thing to do in the long run is to study what you have found and change your position accordingly.   you might lose the current battle, but you will earn a level of respect that will pay dividends well into the future.


Actions

Information

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s




%d bloggers like this: