Engineering Research, starting to look at statistics

#1
Hey everyone,

This will be my first post on this forum. I'm an engineering grad student and I have a little experience with statistics,but not enough to be able to do a sound analysis.

I've completed my system design and will start looking at data collection. My primary aim is looking at energy variations in a system. There are a lot of factors that come into play that can effect this and I'd like to get a good amount of data to be able to say with confidence that there is a variation of say 3 or 5% in the energy output.

At this point I've hit the wall where I need to ask myself, how much data(sample size) do I really need. After looking around a bit, it seems like this is usually approached with a statistical power analysis?

Would this be a good way to approach this? I'm not sure if there is another method that may be more fitting.

Thank you in advance for any help!
 
#3
Yes, power analysis is the general term for what you're looking for. There are many different formulas though, depending on what type of test you're using. To say anything more specific, we would need to know more about your data.