PAGES:  [BACK to PROTEUS home page]    Back to CKHS100 MAIN PAGE     Outline     Research protocol

SPECIAL TOPICS:   Histograms/Central tendency    Sensitivity/Specificity   Rates   Critical review 

               Evaluation Research   Definitions    Designs  Sample size  Sample methods  Confounding 

The following is a series of "second-looks" at claims, conclusions, advertisements, and results that should not have been believed in the first place.

 MISSING INFORMATION!

MISLEADING PEOPLE THROUGH RELYING ON ONLY TWO DATA POINTS.

 Must ask- what was happening before??.......

This is an example of a well-known (but still fascinating)

illusion.  Do the math yourself !...........

......GUILTY OF REPEATED-COUNTING OF SOME BUT NOT OTHER PARTICIPANTS.

The next example comes from the Ontario Government Lottery Corporation several weeks after the "39" lottery began.  This pamphlet was designed to encourage people to purchase tickets and gamble on the odds.  Read the text carefully...

This is what the public saw on the pamphlet...

This is how the data should have appeared if the chart were drawn properly

This was ANOTHER EXAMPLE OF THE MISSING DENOMINATOR!!!!

The rule is, whenever you use a frequency (count) add a percentage.

(Whenever you use a percentage, provide the original frequency as well)

This is also an excellent example of a confounder