Forum Settings
       
Reply To Thread

Anyone here able to answer a stats question?Follow

#1 Feb 10 2012 at 1:40 PM Rating: Excellent
Meat Popsicle
*****
12,018 posts
I have 2 data points I want to use to form a ratio. Each data point has some uncertainty associated with it. What's the best way to express the uncertainty associated with the ratio?

For example let's say data point one is: 48.513, 50.058, 29.513

and data point 2 is 259.519, 296.952, 317.482

I'll calculate the mean and std dev for each point and get a ratio, but I'm not sure how to get an uncertainty number for the error associated with the ratio. That and our stats guy is gone for the weekend. Smiley: frown

Anyhoo, I'm google-ing away but feeling tired, just thought I'd see if I could get you people to do my homework for me. Smiley: wink

____________________________
That monster in the mirror, he just might be you. -Grover
#2 Feb 10 2012 at 1:49 PM Rating: Good
Soulless Internet Tiger
******
34,765 posts
23
____________________________
Donate. One day it could be your family.
Need a hotel at a great rate? More hotels being added weekly.

An invasion of armies can be resisted, but not an idea whose time has come. Victor Hugo

#3 Feb 10 2012 at 2:00 PM Rating: Decent
******
21,718 posts
Uglysasquatch wrote:
(23-2)(2)


____________________________
R.I.P. Jessica M. 5/3/2010
This post brought to you by Carl's Jr.
gbaji wrote:
You guys keep tossing facts out there like they mean something.


#4 Feb 10 2012 at 2:11 PM Rating: Excellent
Meat Popsicle
*****
12,018 posts
BrownDuck wrote:
Uglysasquatch wrote:
(23-2)(2)




Needs more numbers, and maybe some funky math symbols, plus pi. All good equations have pi in them somewhere.
____________________________
That monster in the mirror, he just might be you. -Grover
#5 Feb 10 2012 at 4:01 PM Rating: Good
****
5,684 posts
Quote:
Anyone here able to answer a stats question?
The odds are low.
____________________________
Almalieque wrote:
I admit that I was wrong

God bless Lili St. Cyr
#6 Feb 10 2012 at 4:03 PM Rating: Excellent
******
44,522 posts
42Smiley: pie
____________________________
George Carlin wrote:
I think it’s the duty of the comedian to find out where the line is drawn and cross it deliberately.
#7 Feb 10 2012 at 4:29 PM Rating: Excellent
Meat Popsicle
*****
12,018 posts
Bardalicious wrote:
Quote:
Anyone here able to answer a stats question?
The odds are low.


That's fine, at least we have some pie now. Would you like some?
____________________________
That monster in the mirror, he just might be you. -Grover
#8 Feb 10 2012 at 4:41 PM Rating: Excellent
Meat Popsicle
*****
12,018 posts
I kind of gave up on the problem anyway, then got distracted making scatter plots showing CVs increasing as concentration decreases.

Screenshot

You know, cutting edge science stuff and all... Smiley: nod
____________________________
That monster in the mirror, he just might be you. -Grover
#9 Feb 10 2012 at 4:52 PM Rating: Excellent
Bardalicious wrote:
Quote:
Anyone here able to answer a stats question?
The odds are low.
Actually the odds are really high. What is low are the odds that someone will actually bother to answer one.
____________________________
01001001 00100000 01001100 01001001 01001011 01000101 00100000 01000011 01000001 01001011 01000101
You'll always be stupid, you'll just be stupid with more information in your brain
Forum FAQ
#10 Feb 10 2012 at 4:59 PM Rating: Excellent
Meat Popsicle
*****
12,018 posts
Sir Xsarus wrote:
Bardalicious wrote:
Quote:
Anyone here able to answer a stats question?
The odds are low.
Actually the odds are really high. What is low are the odds that someone will actually bother to answer one.


You're holding out on me aren't you... I knew it! Smiley: bah

____________________________
That monster in the mirror, he just might be you. -Grover
#11 Feb 10 2012 at 6:26 PM Rating: Excellent
Encyclopedia
******
31,966 posts
someproteinguy wrote:
I have 2 data points I want to use to form a ratio. Each data point has some uncertainty associated with it. What's the best way to express the uncertainty associated with the ratio?

For example let's say data point one is: 48.513, 50.058, 29.513

and data point 2 is 259.519, 296.952, 317.482

I'll calculate the mean and std dev for each point and get a ratio, but I'm not sure how to get an uncertainty number for the error associated with the ratio. That and our stats guy is gone for the weekend. Smiley: frown


Um... Calculate the highest and lowest possible ratios and go from there? So lowest of one set to highest of the other, then the other way around. That gives you a single range of ratios. This assumes that the results aren't linked together directly (so one set is the variable output of one thing, the other the output of something else). If the sets are linked (each pair is the result of a interdependent test of some kind), then you'd want to treat them as three separate ratios and then go from there.


How you analyze it has to take into account how the data was generated. Otherwise, it's just garbage you used math(tm) on.
____________________________
King Nobby wrote:
More words please
#12 Feb 10 2012 at 7:50 PM Rating: Good
lolgaxe wrote:
42Smiley: pie


Smiley: nod
____________________________
Sandinmygun | |Tsukaremashi*a | Dihydrogen Monoxide (it kills)
#13 Feb 10 2012 at 8:01 PM Rating: Excellent
Meat Popsicle
*****
12,018 posts
gbaji wrote:
someproteinguy wrote:
I have 2 data points I want to use to form a ratio. Each data point has some uncertainty associated with it. What's the best way to express the uncertainty associated with the ratio?

For example let's say data point one is: 48.513, 50.058, 29.513

and data point 2 is 259.519, 296.952, 317.482

I'll calculate the mean and std dev for each point and get a ratio, but I'm not sure how to get an uncertainty number for the error associated with the ratio. That and our stats guy is gone for the weekend. Smiley: frown


Um... Calculate the highest and lowest possible ratios and go from there? So lowest of one set to highest of the other, then the other way around. That gives you a single range of ratios. This assumes that the results aren't linked together directly (so one set is the variable output of one thing, the other the output of something else). If the sets are linked (each pair is the result of a interdependent test of some kind), then you'd want to treat them as three separate ratios and then go from there.


How you analyze it has to take into account how the data was generated. Otherwise, it's just garbage you used math(tm) on.


You're looking at 6 independent measurements. In 3 of them the protein is at one concentration and in 3 it is at another level. The sampling technique is analogous to estimating the number of, say, red balls in the bin by blindly reaching in and grabbing a few. Those numbers above being the number of 'red balls' you grabbed (the decimal places come from normalization based on the variable number of successful sampling attempts).

Along the lines you were thinking though, I was considering making 6 ratios out of the points by taking the three points and comparing them to each of the other three, and using those values to address the question. The problem is that ratios don't necessarily behave the same way when you do something like average them. So that's where I got stuck.

Looks like I may be grabbing my old stats book from college and having some fun reading over it this weekend... Smiley: lol

Rate-ups for the brainstorming helps. Smiley: smile

Edited, Feb 10th 2012 6:11pm by someproteinguy
____________________________
That monster in the mirror, he just might be you. -Grover
#14 Feb 11 2012 at 9:53 AM Rating: Good
Drunken English Bastard
*****
15,264 posts
Did you take the root mean square deviation at all?

That's what we always have to do for our experiential data to find the probable uncertainty value for our results. I'm just a student though, I don't know if you'd do it different professionally.
____________________________
My Movember page
Solrain wrote:
WARs can use semi-colons however we want. I once killed a guy with a semi-colon.

LordFaramir wrote:
ODESNT MATTER CAUSE I HAVE ALCHOLOL IN MY VEINGS BETCH ;3
#15 Feb 11 2012 at 10:27 AM Rating: Good
is Happy on Friday!
*****
12,443 posts
Mashed potatoes.
____________________________
Theytak, Siren Server
LOLGAXE IS MY ETERNAL RIVAL!

Reiterpallasch wrote:
Glitterhands wrote:
Am I the only one who clicked on this thread expecting actual baby photos [of Jinte]? o.O

Except if it were baby photos, it would be like looking at before and afters of Michael Jackson. Only instead of turning into a white guy, he changes into a chick!
#16 Feb 11 2012 at 10:30 AM Rating: Excellent
Meat Popsicle
*****
12,018 posts
Nilatai wrote:
Did you take the root mean square deviation at all?

That's what we always have to do for our experiential data to find the probable uncertainty value for our results. I'm just a student though, I don't know if you'd do it different professionally.


No it's the right idea, for sure. I'm thinking what I need to do is calculate that for each of the two points and use something like this to combine the uncertainty from the two data points into a single value.

As an aside, I'd wager most students know more about these things than most "professionals" Smiley: lol
____________________________
That monster in the mirror, he just might be you. -Grover
#17 Feb 11 2012 at 10:39 AM Rating: Good
Drunken English Bastard
*****
15,264 posts
someproteinguy wrote:
Nilatai wrote:
Did you take the root mean square deviation at all?

That's what we always have to do for our experiential data to find the probable uncertainty value for our results. I'm just a student though, I don't know if you'd do it different professionally.


No it's the right idea, for sure. I'm thinking what I need to do is calculate that for each of the two points and use something like this to combine the uncertainty from the two data points into a single value.

As an aside, I'd wager most students know more about these things than most "professionals" Smiley: lol

That's the badger.

You're probably right on the students knowing more, though. Especially if you're doing labs week in week out. Tends to stick in the mind a bit. As you said, you do the experiment and you have a guy who specifically does the stats portion. It looks like you're on the right track, though!
____________________________
My Movember page
Solrain wrote:
WARs can use semi-colons however we want. I once killed a guy with a semi-colon.

LordFaramir wrote:
ODESNT MATTER CAUSE I HAVE ALCHOLOL IN MY VEINGS BETCH ;3
#18 Feb 11 2012 at 12:53 PM Rating: Good
Drunken English Bastard
*****
15,264 posts
someproteinguy wrote:
I have 2 data points I want to use to form a ratio. Each data point has some uncertainty associated with it. What's the best way to express the uncertainty associated with the ratio?

For example let's say data point one is: 48.513, 50.058, 29.513

and data point 2 is 259.519, 296.952, 317.482

I'll calculate the mean and std dev for each point and get a ratio, but I'm not sure how to get an uncertainty number for the error associated with the ratio. That and our stats guy is gone for the weekend. Smiley: frown

Anyhoo, I'm google-ing away but feeling tired, just thought I'd see if I could get you people to do my homework for me. Smiley: wink


So according to my girlfriend's SPSS Psychologist stat calculating thingy, the first data point should have a standard error of 6.605, the second should be 16.967.

Is that what sort of thing you're looking for?
____________________________
My Movember page
Solrain wrote:
WARs can use semi-colons however we want. I once killed a guy with a semi-colon.

LordFaramir wrote:
ODESNT MATTER CAUSE I HAVE ALCHOLOL IN MY VEINGS BETCH ;3
#19 Feb 11 2012 at 1:13 PM Rating: Excellent
Meat Popsicle
*****
12,018 posts
Nilatai wrote:

So according to my girlfriend's SPSS Psychologist stat calculating thingy, the first data point should have a standard error of 6.605, the second should be 16.967.

Is that what sort of thing you're looking for?


That's the part I have done. Now let's say I form want to express the difference between the two data points as a ratio (i.e. 5.2:1). How does the uncertainty from the two measurements factor into the uncertainty of the resulting ratio?
____________________________
That monster in the mirror, he just might be you. -Grover
#20 Feb 11 2012 at 1:33 PM Rating: Good
Ghost in the Machine
Avatar
******
36,218 posts
Smiley: popcorn

I have no idea what's going on, but it looks interesting.
____________________________
Please "talk up" if your comprehension white-shifts. I will use simple-happy language-words to help you understand.
#21 Feb 11 2012 at 7:15 PM Rating: Good
Something about how it all equals 42, but they are taking the long way to get there.
____________________________
Sandinmygun | |Tsukaremashi*a | Dihydrogen Monoxide (it kills)
#22 Feb 12 2012 at 8:43 AM Rating: Good
Drunken English Bastard
*****
15,264 posts
someproteinguy wrote:
Nilatai wrote:

So according to my girlfriend's SPSS Psychologist stat calculating thingy, the first data point should have a standard error of 6.605, the second should be 16.967.

Is that what sort of thing you're looking for?


That's the part I have done. Now let's say I form want to express the difference between the two data points as a ratio (i.e. 5.2:1). How does the uncertainty from the two measurements factor into the uncertainty of the resulting ratio?

I have absolutely no idea. Smiley: grin


I'll ask my girlfriend later. She's better at stats, but I kick her **** at Algebra...

Sorry, SPG!
____________________________
My Movember page
Solrain wrote:
WARs can use semi-colons however we want. I once killed a guy with a semi-colon.

LordFaramir wrote:
ODESNT MATTER CAUSE I HAVE ALCHOLOL IN MY VEINGS BETCH ;3
Reply To Thread

Colors Smileys Quote OriginalQuote Checked Help

 

Recent Visitors: 43 All times are in CST
Anonymous Guests (43)