The Origin Forum
File Exchange
Try Origin for Free
The Origin Forum
Home | Profile | Register | Active Topics | Members | Search | FAQ | Send File to Tech support
Username:
Password:
Save Password
Forgot your Password? | Admin Options

 All Forums
 Origin Forum
 Origin Forum
 Query regarding use of statistical analysis
 New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

metaltemujin

India
4 Posts

Posted - 01/07/2014 :  07:03:48 AM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
Hi,

I wanted to know if there was a way to apply any of the statistical methods (Such as t-test/ANOVA/etc) using Mean followed by SEM or SD by giving 'n' of the experiment.

Currently I have tried inputing individual values of each sample, but incases where Mean & SEM/SD is already calculated and/or applying statistics to fold-change data rt-pcr,etc.

Origin Ver. and Service Release (Select Help-->About Origin): 9
Operating System: Win 8

Echo_Chu

China
Posts

Posted - 01/10/2014 :  12:55:20 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi, metaltemujin

It looks you are looking for the Power and Size tools, which enable you to calculate the probabilities to reject a false null hypothesis by given N and test parameters.

Please try our Power and Sample Size tools by selecting Statistics: Power and Sample Size from Origin menu.

You can also learn how to use these tools from our tutorial

http://www.originlab.com/doc/Tutorials/Power-SampleSize

Echo
OriginLab Corp.
Go to Top of Page

metaltemujin

India
4 Posts

Posted - 01/10/2014 :  12:30:52 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
I checked what you had given. That's not what I am looking for. I'll give u an example.

Assume I am testing weight response to a drug. I have a Control and 2 treatments, and each group has 10 obeservations ('n', aka biological replicates).

I have with me only the "Mean" and "Standard Deviation" of each of those groups.

How will I calculate using t-test or ANOVA if the variation in the groups are statistically signifiant on Origin?

(I need to know this in cases where individual responses are complex - as mentioned in 1st post).
Go to Top of Page

Echo_Chu

China
Posts

Posted - 01/13/2014 :  12:32:46 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Thank you for the example. I know what you need now. I am afraid that Origin does not have such feature yet. But you can get used to our set column value tool and save the worksheet as analysis template for future use.

Let me take two sample t-test as an example.

Assumed that we have a worksheet where mean 1 is in the first column, sd1 is in the 2nd column, n1 in the 3rd column, mean2 is in the 4th column ,sd2 is in the 5th column and n2 in the 6th column, then you can

1. Hightlight the 7th column, right click and select Set Column Value from the context menu
2. In the Set Column values dialog, copy/paste the script blow in the Before Formula Script box of the dialog

range x1 = wcol(1);
range sd1 = wcol(2);
range n1 = wcol(3);
range x2 = wcol(4);
range sd2 = wcol(5);
range n2 = wcol(6);

double sp = sqrt(((n1-1)*sd1^2 + (n2  - 1)*sd2^2)/(n1+n2-2));

tvalue = (x1 - x2)/(sp*sqrt(1/n1+1/n2));


Enter "tvalue" in the upper panel of the dialog as the image blow



You can enter other mean, sd and n of two groups in the other rows of column 1 ~ column 6 then corresponding t value will be calculated automatically in the 7th column.


But if for anova, the algorithm requires you to calculate the sum of squares from the sample so you can not simply get the result from the known mean and sd of the samples.
Go to Top of Page
  Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic
 New Topic  Reply to Topic
 Printer Friendly
Jump To:
The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000