Protocol Online logo
Top : Forum Archives: : Bioinformatics and Biostatistics

STANARD DEVIATION and t-value - (Jul/31/2006 )

I am not sure what to do with st. deviations, when I add up 3 mean values(from 3 sampling groups). Should I also add up ST.DEV. ?

The next thing about the function t-test in Excell (2003). What exactly does the number I get out when I compare 2 columns mean?

I would really appreciate your help, as I am really in a hurry at the moment (don't have time to browse all around).


Excel gives the t-value, you have to look in t-value tables (in statistic books) if the value (depend on degrees of freedom) exceeds the sigifiacance limits (the value in the table for a given probabilty). Statistic programs do this for you, so they are more convenient.
Means are only with SD meaningful. In your case I would look if the three means are significantly different, if not, you can add up all raw data to one group and give mean + SD. If they are different you have to handle each group separately, because something other than the treatment (I assume that it is the same in the 3 groups) has influenced the results.
Hope this helps