BREAKING: Target Test Prep releases Brand New 2026 On Demand GMAT prep course

Redeem

Standard Deviation

This topic has expert replies
Post new topic Post Reply
Previous Topic Next Topic
Source: — Data Sufficiency |
User avatar
Community Manager
Posts: 1060
Joined: Fri May 13, 2011 6:46 am
Location: Utrecht, The Netherlands
Thanked: 318 times
Followed by:52 members

by neelgandham » Fri Oct 28, 2011 11:27 am
No not necessary !

let the numbers be 4,4,4,4, Mean = 4 and SD =0
If all the numbers in a set are changed by a certain percentage, say 100%, then the numbers are 8,8,8,8, Mean = 8 but SD =0
Anil Gandham
Welcome to BEATtheGMAT | Photography | Getting Started | BTG Community rules | MBA Watch
Check out GMAT Prep Now's online course at https://www.gmatprepnow.com/
Top
User avatar
GMAT Instructor
Posts: 349
Joined: Wed Sep 28, 2011 3:38 pm
Location: Austin, TX
Thanked: 236 times
Followed by:54 members
GMAT Score:770

by GmatMathPro » Fri Oct 28, 2011 12:49 pm
neelgandham wrote:No not necessary !

let the numbers be 4,4,4,4, Mean = 4 and SD =0
If all the numbers in a set are changed by a certain percentage, say 100%, then the numbers are 8,8,8,8, Mean = 8 but SD =0
But zero increased by 100% IS zero.
Pete Ackley
GMAT Math Pro
Free Online Tutoring Trial
Top
Senior | Next Rank: 100 Posts
Posts: 40
Joined: Fri Jul 15, 2011 5:37 am
Thanked: 3 times

by studentps2011 » Fri Oct 28, 2011 12:58 pm
I think it increases by the same percentage. Please have a look at the below link.

https://www.beatthegmat.com/gmat-prep-t9874.html[/url]
Top
User avatar
GMAT Instructor
Posts: 349
Joined: Wed Sep 28, 2011 3:38 pm
Location: Austin, TX
Thanked: 236 times
Followed by:54 members
GMAT Score:770

by GmatMathPro » Fri Oct 28, 2011 1:18 pm
Yeah, it should increase by the same percentage. Informally, if you think of standard deviation as a measure of how spread out the data is, if you double the values, or whatever, they should become twice as spread out.

If each data point is multiplied by a positive constant, C, then the mean is multiplied by that same constant, C. Then when we compute the standard deviation by subtracting each data point from the mean and squaring it, we will be able to factor out a C^2: (Cx1-Cu)^2=(C(x1-u))^2=C^2(x1-u). This C^2 could then be factored out of all of the differences, and then when you take the square root at the end, sqrt(C^2)=C, so it would just be C times the original standard deviation.

Increasing something by a percentage is the same as multiplying by a constant, so it will work the same way.
Pete Ackley
GMAT Math Pro
Free Online Tutoring Trial
Top
Post new topic Post Reply
• Page 1 of 1