RobertNiles.com
About Robert
Reporting Help
Finding Data on the Internet
Questions for Candidates
Stats Lessons
Mean
Median
Percent
Per capita
Standard Deviation
Margin of Error
Data Analysis
Sample Sizes
Stats Tests
Help Board
Bookstore


The Cartoon Guide to Statistics

This isn't some dumb-downed whitewash. It's a must-read for a beginner taking his or her first steps toward understanding stats.
More information
-->

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

Rounding
Message posted by Jen on November 4, 1999 at 12:00 AM (ET)

We've been having a discussion on rounding rules & seem to have 2 differing opinions. Assume we are rounding to 1 decimal place.

The first method says that if the second decimal is 0-4, the second digit stays the same; if the second digit is 5-9, round up.

The second method is basically the same except if the second digit is 5. In this case, you would round the last digit to the closest even number. "Thus the number would 3.55 would round to 3.6 & 3.45 would round to 3.4".

The first method appears be fair - round up 50% of the time & round down 50% of the time. However, some contend that 0 doesn't count, &, therefore, the first method is bias. Others contend that 0 is a valid number (particularly when rounding a number like 2.104 - where the 0 takes on a definite value) &, therefore, makes the second method bias.

What do you think?


READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: Rounding
Message posted by JG on November 4, 1999 at 12:00 AM (ET)

The first method is usually used. Zero is just a number.

However, you have another problem, while 0.9 can be rounded to 1, 0.2 can not be rounded to 0 . Maybe that is what they mean by zero is special.


Re: Rounding
Message posted by JG on November 5, 1999 at 12:00 AM (ET)

Zero does not count because you do not have a rounding problem if you end with zero . If you are rounding one significant figure such as changin 1.x to an interger then if x = 0 there is no problem, if x is 1,2,3,4 round down , if xis 6,7,8,9 round up and if x is 5 toss a fair coin and round up for heads ,down for tail , etc.

If x = many digits then the problem evaporates, since 0000000000 and 5000000000 will not occur very often.


Re: Rounding
Message posted by j-bamdad on November 5, 1999 at 12:00 AM (ET)

hi i,m wait



Your $5 contribution helps cover part the $500 annual cost of keeping this site online.

Niles Online Sites:RobertNiles.comTheme Park InsiderViolinist.com

RobertNiles.com™, the site, content and services 咀opyright 1996-2002, Robert Niles.
All rights reserved. Questions? Comments? Read my Privacy Policy, or E-mail me!