| View previous topic :: View next topic |
| Author |
Message |
Degenar
Newbie
Joined: 26 Nov 2005
Posts: 1
|
 Posted: Sat Nov 26, 2005 5:28 pm Post subject: Standard deviation in diagrams |
 |
|
Hello,
1. Question: I want to know how you insert the standard deviation into a diagram.
Description of the case: the mean of 5 results of a measured velocity shall be written on the ordinate (y-axis), while a given concentration shall be written on the abscissa (x-axis).
there are five concentrations and five corresponding means. Each mean is based upon 5 different measurements, so there is a standard deviation for each mean.
Question: How is it possible to insert the standard deviation corresponding to each mean into the diagram?
In Microsoft Word it is possible to put the same standard deviation on all resluts in the diagram. In contrast, I wish to see the individual standard deviations of the results.
2. Question: How do I fit a regression curve into the diagram described above? How do I fit this regression curve in a way that it takes into account the standard deviation?
In this case I know that the regression curve approaches an asymptote on the y-axis. The curve is a saturation curve (in german "Sättigungskurve").
The Asymptote is the maximal value of the velocity that can be achieved with any concentration.
The function of the curve has to be v = s / (k+s).
v, s and k being variables of the Michaelis-menten kinetics.
An example of such a curve (beginning of text) is here: http://en.wikipedia.org/wiki/Michaelis-Menten_kinetics
Do not get confused, in this example the curve does not show any standard deviation.
In Microsoft Excel it is possible to choose linear, potential, exponential, logarithmic and polynomic regression curves. I need another one, but I would also be happy to know that Openoffice is capable of doing what Excel does.
If the details of the case make the question unclear, here are the questions in general:
1. How do I put the standard deviation into a diagram?
2. How do I fit any regression curve into a diagram?
If there is anything unclear, please post your questions, i would be happy if you could help me for this basic application.
Please, tell me the exact path on which I get to the solution of the problem. Even using the help function of Openoffice I could neither dicover the solution for introducing the standard deviation nor a regression curve into a diagram.
Thank you very much
Sincerely
Degenar
_________________
Hoping that software becomes more helpful. |
|
| Back to top |
|
 |
joerg04
OOo Advocate
Joined: 14 May 2004
Posts: 326
Location: Germany
|
| Posted: Mon Nov 28, 2005 1:18 am Post subject: Re: Standard deviation in diagrams |
|
|
| Degenar wrote: | Hello,
1. Question: I want to know how you insert the standard deviation into a diagram.
Description of the case: the mean of 5 results of a measured velocity shall be written on the ordinate (y-axis), while a given concentration shall be written on the abscissa (x-axis).
there are five concentrations and five corresponding means. Each mean is based upon 5 different measurements, so there is a standard deviation for each mean.
Question: How is it possible to insert the standard deviation corresponding to each mean into the diagram?
In Microsoft Word it is possible to put the same standard deviation on all resluts in the diagram. In contrast, I wish to see the individual standard deviations of the results.
2. Question: How do I fit a regression curve into the diagram described above? How do I fit this regression curve in a way that it takes into account the standard deviation?
In this case I know that the regression curve approaches an asymptote on the y-axis. The curve is a saturation curve (in german "Sättigungskurve").
The Asymptote is the maximal value of the velocity that can be achieved with any concentration.
The function of the curve has to be v = s / (k+s).
v, s and k being variables of the Michaelis-menten kinetics.
An example of such a curve (beginning of text) is here: http://en.wikipedia.org/wiki/Michaelis-Menten_kinetics
Do not get confused, in this example the curve does not show any standard deviation.
In Microsoft Excel it is possible to choose linear, potential, exponential, logarithmic and polynomic regression curves. I need another one, but I would also be happy to know that Openoffice is capable of doing what Excel does.
If the details of the case make the question unclear, here are the questions in general:
1. How do I put the standard deviation into a diagram?
2. How do I fit any regression curve into a diagram?
If there is anything unclear, please post your questions, i would be happy if you could help me for this basic application.
Please, tell me the exact path on which I get to the solution of the problem. Even using the help function of Openoffice I could neither dicover the solution for introducing the standard deviation nor a regression curve into a diagram.
Thank you very much
Sincerely
Degenar |
What you want is not possible with OOo. After all you need dedicated software. You can try this
http://www.oooforum.org/forum/viewtopic.phtml?t=19890&highlight=
Additionally search in the forum for help with the search function. One autor of this forum "David" also gave good advises for comercial packages. So specify your search aslo for him.
In short your solution/workaround might be:
freee/freeware:
gnumeric (Win/Linux) http://www.gnome.org/projects/gnumeric/
R (Win/Linux/Mac) http://www.r-project.org/
gnuplot (Win/Linux) http://www.gnuplot.info/
LabPlot (Linux) http://labplot.sourceforge.net/
QtiPlot (Linux) http://soft.proindependent.com/qtiplot.html
Comercial:
Origin(Windows) http://www.originlab.com/
Accept R all should do plots with standard deviation.
About the regression issue. An other way is to caculate the coefficents and to draw the function in any spreadsheet application you want. Giving the Range and some steps should be sufficient. In any case the coefficients must be caculated e.g. with R (http://cran.r-project.org/search.html -> search for Micahaelis-Menten and you will see there is a lot to find). Doing this be hand should be basicly the same as for linear functions but I can't recommend this way. Too much work  .
_________________
joerg04
RKWard: http://rkward.sourceforge.net/
sidux: http://sidux.com/index.html
Musix: http://musix.org.ar/en/index.html |
|
| Back to top |
|
|
|
|
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
|
Powered by phpBB © 2001, 2005 phpBB Group
|
