Chronology |
Current Month |
Current Thread |
Current Date |

[Year List] [Month List (current year)] | [Date Index] [Thread Index] | [Thread Prev] [Thread Next] | [Date Prev] [Date Next] |

*From*: John Denker <jsd@av8n.com>*Date*: Fri, 24 Aug 2012 15:37:58 -0700

On 08/24/2012 03:11 PM, Paul Nord wrote:

don't we generally use the standard deviation and not the HWHM?

Standard deviation is slightly smaller.

What do you mean by "we", Kemosabe?

-- Sometimes there are excellent reasons for using the HWHM.

-- Sometimes there are excellent reasons for using the standard deviation.

-- Sometimes there are excellent reasons for using both ... or neither.

The only rule here is: Say what you mean, and mean what you say.

Is the standard deviation still defined for any set of measurements

even it they are widely scattered?

Yes. There is an utterly straightforward mathematical definition

of standard deviation.

Can I call .... the standard deviation even though a normal

distribution clearly will not fit the data?

Yes. Non-normal distributions have perfectly well defined

standard deviations.

Whether the standard deviation of some wacky distribution tells

you anything /interesting/ is another question. Sometimes it

does ... sometimes it doesn't.

**References**:**[Phys-L] Statistics question***From:*Paul Nord <paul.nord@valpo.edu>

**Re: [Phys-L] Statistics question***From:*John Denker <jsd@av8n.com>

**Re: [Phys-L] Statistics question***From:*Paul Nord <paul.nord@valpo.edu>

- Prev by Date:
**Re: [Phys-L] rounding** - Next by Date:
**Re: [Phys-L] rounding** - Previous by thread:
**Re: [Phys-L] Statistics question** - Next by thread:
**Re: [Phys-L] Statistics question** - Index(es):