5

I am measuring accumulation of a fluorescent-tagged protein at a particular location within a cell over time. In previous experiments that I have performed, I see a standard exponential distribution where the fluorescence intensity reaches a plateau, however in my current experiment, I see a distribution as shown below:

enter image description here

What is the best model to use for this data? Should I use two separate exponential models, one for the increase in intensity up to the peak and one for the decay phase, or is there another statistical model for this type of distribution. Thanks!

Josh
  • 53
  • 5

2 Answers2

2

I would suggest you to use spline regression. This is a relatively simple and accurate method that allows you to fit nonlinear behaviours such as that you are assessing. Splines are non parametric smoother formed by piece-wise polynomials, with pieces identified by a sequence of "knots" where pieces join smoothly. You can find here the basics of spline regression/interpolation, with some advices on how to perform an algorithm to find the interpolating "cubic" spline (most used in statistics).

Anatoly
  • 17,079
1

I my opinion you should search a model that fits your data, also you can use a model by parts because you have two behavior of your data very different.

Splines are good to fit because they can fit more or less anything but splines have a big problem, you lose the physical meaning of the model. So in my opinion search in the literature a model can be the best option.

P.S : sorry for my english.

Santiago murillo
  • 36