I am looking for a statistics model to compare one dose(inhibition) response curve to the log space of that same curve. The trick is, in order to analyze the data, we have to take the observed concentrations and RFU's and log transform them. We then have to log transform them again. So, we are taking the log log of the concentrations and observed RFUs. So, we are essentially looking to compare the log space of one curve to the log log space of another curve.

It gets a little bit more complicated. The spreadsheet I am using is able to fit a curve the log log data, but is unable to fit a curve to the log data. So, I have the 4PL parameters of the log log data, but only the A, D & C parameters of the log data. Which is why we're looking for a way to compare these two curves. We want to know if it is okay to take the log of the log data in order to fit the curve. I don't know how to embed my pictures of the two charts. But, I uploaded the two charts. One is labeled "Log of Log" and the other is "Log not Fitted".

I've read the "Statistics - Comparing Dose Response Curves" thread, and it doesn't answer my question. I've also looked at the following links:

http://www.graphpad.com/guides/prism/6/statistics/index.htm?stat_qa_multiple_comparisons_after_.htm

http://www.acoustics.asn.au/conference_proceedings/ICSVS-1997/pdf/scan/sv970356.pdf

http://cdn.intechopen.com/pdfs-wm/10675.pdf

The last one is a bit long, and I'm still trying to digest it.