4. 1.
Being mindful of underlying
uncertainties behind any statistic
avoids overvaluing the figure
5. For instance the probability of a Clinton win in
the recently concluded US elections was
reported till double decimal places
6. With a population of 230 million and such
diversity, it is nearly impossible to cover a
sample that is a true representative of the
population, let alone predict the number till 2
decimals
7. These overstated statistics do even more
damage when reported using suave visuals as
they morph the idea of any fallacy
8. The concept of ‘average’ numbers should be
perceived with even more caution since they
tend to over generalize metrics
9. 2.
An added knowledge of the data
source used to calculated a
statistic brings in more realism to
its value
10. For instance, one poll found that 41 percent of
Muslims in the US support jihad, which is
obviously pretty scary
11. But, it turns out only 16 percent defined it as,
"violent holy war against unbelievers.“. It is
also possible that no one in the survey who
defined it as violent holy war also said they
support it.
12. And finally, only 600 respondents took part in
that poll. There are roughly three million
Muslims in this country, according to Pew
Research Center. That means the poll spoke to
roughly one in every 5,000 Muslims in this
country which in no way is an accurate sample
13. While collaborating with Analysts, Managers
need to be aware of these caveats as a false
statistic can drastically change the course of
any analysis and its reporting