Comments on: Bioassay Analysis with the Five Parameter Logistic (5-PL) Non-Linear Regression Curve-Fitting Model

By: aliu

aliu — Wed, 01 Jun 2011 20:26:45 +0000

Hi Carla,

I am not aware of any logistic 5 parameter functions that are linear. May I ask why you require linear? If so, you can can try a simple linear equation such as: f(x) = ax + b

Have you tried a nonlinear 5PL fit yet? If not, I would recommend you try that first in our free online curve fitting application. You will also have the option of trying the linear fit as well.

I hope this information helps.

Allen

By: CARLA

CARLA — Mon, 30 May 2011 14:22:16 +0000

How can I get linear regression of the 5PL function, I am performing leptin quantification but I cannot do it.

By: aliu

aliu — Tue, 05 Apr 2011 15:58:54 +0000

Hi Fica,

Can you please be more specific on what you mean by “5PL-er”?

Thanks,

Allen

By: Fica

Fica — Tue, 05 Apr 2011 05:07:33 +0000

It is difficult to find a proper definition of a 5PL-er. I was wondering if anybody in this group could give me the definition?

By: aliu

aliu — Mon, 21 Jun 2010 22:02:35 +0000

Hi J,

You are absolutely right! I should know my PEMDAS much better than that. It has been corrected. Thanks for the heads up.

Allen

By: J

Mon, 21 Jun 2010 21:36:17 +0000

the formula for calculating the EC50/IC50 from the 5PL doesn’t look right to me. shouldn’t it look like
x = C*((2^(1/E) – 1))^(1/B))???

By: aliu

aliu — Mon, 15 Mar 2010 22:06:37 +0000

Thanks for the reference! I read through the paper discussing the reparameterized 5PL and it seems to me that the main advantage this new function is the ease of interpretation of the parameters such as the C* (ED50) which is no longer a function of E or the asymmetry factor. Are there references to this relatively new reparameterized 5PL function in other published articles?

By: Anonymous

Anonymous — Fri, 12 Mar 2010 15:31:14 +0000

This 5PL form has a lot of drawbacks. Please see the paper by Liao, et al. (2009), “Re-parameterization of Five-parameter Logistic Dose Response Curve”, J. of Chemometrics, 23, 248 – 253.

By: Anshuman

Anshuman — Thu, 13 Aug 2009 11:30:08 +0000

Thank you very much for the assistance, as I have to answer to my project incharge about the
calculations associated with the 4PL equation, as I am presently dealing with the ELISA techniques.

By: aliu

aliu — Tue, 11 Aug 2009 18:05:34 +0000

@anshuman: I apologize but I think I initially misread your question. Actually calculating the values for A and D is definitely beyond the scope of this post and is a really complicated process. Essentially, one begins with a “guess” of the parameters and depending on the fit of those parameters the algorithm will try to improve of the initial values and so on and so on. I apologize that this is not really straightforward but that is the reason why we have algorithms and software that do it for us.

By: Anshuman

Anshuman — Tue, 11 Aug 2009 11:23:15 +0000

Thanks for the reply, but then how do one find the values of A and D for the 4PL equation,besides thee values for B and C can be calculated from the graph I suppose. Kindly sight one example and explain.

By: Anonymous

Anonymous — Tue, 11 Aug 2009 11:21:02 +0000

Thanks for the reply, but then how do one find the values of A and D for the 4PL equation,besides thee values values for B and C can be calculated from the graph. Kindly sight one example and explain.

By: aliu

aliu — Mon, 10 Aug 2009 15:54:04 +0000

@anshuman: The concentrations cannot be calculated at A and D because those are the limits of the function. Basically, anything less than or equal to A or greater than or equal to D will be out of limits of the function.

By: anshuman

anshuman — Sat, 08 Aug 2009 12:32:35 +0000

If it is dangerous to extrapolate the grapt then what will the values of A and D in the 4 parameter equation .