Andy on Twitter

  • If you were looking to create a community within a site - conversations etc.. Which software would you use?,
  • As must read for any marketer. Mark Ritson: 10 lessons all marketers should take from Direct Line’s brand strategy ,
  • Great read... 21 Lessons From Jeff Bezos' Annual Letters To Shareholders - CB Insights Research ,
  • customer satisfaction survey fatigue ,
  • great post from John on how algorithms erode trust and love. ,
  • So the lounge in LA has a dining room but you can only access it if you are going to certain locations… ,
  • So Brilliant.... Banksy painting sells for $1.9 million then self-destructs ,
  • Oh... have now got maintenance on board. So, cant actually keep planes in the air either it seems. In… ,
  • Three AA flights. One cancelled. One delayed by over an hour. Another delayed - they can’t find a flight attendant.… ,
  • I wonder if brands like have any idea that it's actually the customer who is in control and that the c… ,
  • Funny... Land in LAX after messed up flight. Three emails asking for reco on best airline to fly LAX t… ,
  • WOW.... WHAT A READ!!! The Big Hack: How China Used a Tiny Chip to Infiltrate U.S. Companies - Bloomberg ,
  • Never ever Fly just shocking how bad they are. Appalling.,
  • Get through your inbox twice as fast with @SuperhumanCo.,
  • Postive news... Departure cards to be scrapped | RNZ News ,
  • Connect

Using Statistics

HBR has a nice little piece on using statitics that is very applicable to anyone undertaking measurement for communications or marketing. The central tenents are:

  1. Know what you know-and what you’re only asserting

  2. Be clear about what you want to discover

  3. Don’t take causality for granted

  4. With statistics, you can’t prove things with 100 percent certainty

  5. With statistics, you can’t prove things with 100 percent certainty

The last one is important in communicating upwards to management. Does anyone care you increased coverage 3.2%? Probably not.

Technorati :

2 Responses

  1. By Bill Paarlberg on May 23rd, 2006 at 6:07 am

    Most of what we commonly use and call statistics are meant to describe uncertainty, not certainty. They are not able or were ever supposed to “prove” anything, and definitely not “prove things with 100% certainty.”

    Most common statistical techniques are developed from the assumption that a family of data points has a certain distribution and that it is possible to calculate the probability that other data points are part of that distribution. Statistics (generally) provides a probability, and so only demonstrates that something is _not_ certain.

    From a mathematical point of view, it is the whole point of statistics that they _don’t_ prove anything. Of course, from a PR measurement point of view, the whole point of statistics is that they _do_ almost prove something.

  2. By Harry Joiner on May 26th, 2006 at 10:32 am

    Interesting post. People often forget that with statistics, there are only two outcomes in any hypothesis test:

    1. Reject
    2. FAIL to Reject

    One cannot “accept” something with statistics. The closest thing to “accepting” a hypothesis is “failing to reject” it. It’s very much the same as not finding a defendant innocent — but rather failing to find the defendant guilty in a jury trial (as in “We the jury, find the defendent ‘not guilty’ on the charge of XYZ.”).

    Make sense?

Speak Up — Add Your Thoughts

Connections

  • Connect
How did you connect?   [?]