0

# A statistically insignificant number can be significant

Fri 21 Aug, 2009 10:32 pm
Divide 25 by 300 million

25/300,000,000 = 0.000000008333333 = 0.0000008333%

25 is the number given by the TIME magazine of people who caused the financial meltdown. A scion of a wealthy political family of ex-presidents, a former president who during his term of office signed into law allowing business mergers in the financial sector, a former professor of economics and senator who represented an international bank and a slew of bank and mortgage company managers would be numerically a statistically insignificant quantity.

A thirty-year-old man dies from a car accident in 5 seconds. 30x365x24x3600 = 946080000 seconds

5/946080000 = 0.00000000284965331 or 000000284965331% it is so small that it is insignificant.

For 30 years this person was alive but within 5 seconds he was dead from an accident.

Statistics can be deceptive when the numbers have equal value. As can be seen above the 5 seconds and the 25 people are insignificant. But putting a value to the 5 seconds equal to the driver's life and 25 people means the financial meltdown then it is significant in both cases.
• Topic Stats
• Top Replies
Type: Discussion • Score: 0 • Views: 1,863 • Replies: 5
No top replies

fresco

1
Sat 22 Aug, 2009 07:42 am
@talk72000,
"Significance levels" are always arbitrary in statistics. The standard practice of using (less than).05 or .o1 significance levels in statistical results is purely conventional. And besides, even if such a level is accepted as "significant" it only constitutes a criterion for rejecting a null hypothesis rather than the acceptance of a particular hypothesis with respect to the data.
talk72000

1
Sat 22 Aug, 2009 08:18 am
@fresco,
Statistically both examples are insignificant but real life issues shows that the 5 seconds means the driver's life and the 25 people activities mean the recession and the disappearance of many seniors' life savings and destruction of pensions. Statistics can be used to lie or hide dangerous events as well reveal them as Florence Nightingale did about cleanliness in hospitals during the Crimean War.
fresco

1
Sat 22 Aug, 2009 08:38 am
@talk72000,
Yes, "signifance" always involves "for whom".
0 Replies

spendius

1
Sat 22 Aug, 2009 12:55 pm
@talk72000,
Quote:
Statistics can be used to lie or hide dangerous events as well reveal them as Florence Nightingale did about cleanliness in hospitals during the Crimean War.

The latest historical research claims that Florence was a confounded nuisance and death rates fell as soon as she was shifted out.

Not that I know either way.
talk72000

1
Sun 23 Aug, 2009 11:09 am
@spendius,
She was a nurse after all not a doctor so she was resented by the doctor besides those in the hospital resented her too because of the extra work. It worked out well in the end anyway they now keep hospitals clean as a result of her statistical studies same with cigarette smoking and cancer.
0 Replies

### Related Topics

Where is the US economy headed? - Discussion by au1929
Shopping Around For Loans - Question by Brandon9000
What is greed? - Discussion by Robert Gentel
bonds series h - Question by allen russell
Naked Short Selling - Question by optimus cubed
HOW TO GET WEALTHY - Discussion by farmerman

1. Forums
2. » A statistically insignificant number can be significant