<p> plot(data,char,size,clr) </p>

3e996bef-6d58-4955-a372-fa70da4c4348 42 4 5 decimal

&[DATE] &[TIME] - &[FILENAME]

data char size clr plot k 1 data rows range r3 k el char : r4 k el size : r5 k el clr : 31 line for data r3 r4 r5 augment 21 line :

1. Lab data/information

data Dose Positive Total Response 0.009 070 0.09 070 0.9 17 0.143 9811 0.727 9089 0.889 90078 0.875 900057 0.714 9000033194 mat :

data data 29 range 14 range el : 0.009 070 0.09 070 0.9 17 0.143 9811 0.727 9089 0.889 90078 0.875 900057 0.714 9000033184 mat

2. The X scale transform

i 18 range : u data i 2 el : v data i 3 el : response u v / vectorize : 41 line

The X scale transform, 
typical for "X datum 0" λ data i 1 el : X 10009 / λ * log10 vectorize : 21 sys

3. Prepare the project

data 0.009 070 0.09 070 0.9 17 0.143 9811 0.727 9089 0.889 90078 0.875 900057 0.714 9000033184 mat :

Y data 4 col : XY X Y augment : Y data 2 col data 3 col / ≡ (response ≡ plot XY o 5 black plot : 41 line

XY 00102 0.143 3 0.727 4 0.889 5 0.875 6 0.714 7182 mat

β 7 2.5 21 mat :

4. fit/solve the model

Transmute Sigmoid

Parameters β will depend upon the scaling of 'X'

U 2.5218 :

x β f β 1 el 1 x / (β 2 el^* - exp :

User U U β f + 20 blue 15 mat :

About the project . . .

I don't have the science to explain Rotavirus.

Steven F. has proposed another approach that is not

immediate for Smath and that does NOT respect the

two 1rst Y response 0 ... just a pass through.

The sigmoid is a better model, fitted by hand.

Steven propsed MLE Bata Poisson.

]]> plot x β f User 3 1 sys

U β f 0.5

x β f 0.5 - 0 ≡ x 23 solve 2.5218

MLE ... Maximum Likelihood Estimation... In statistics, maximum likelihood estimation (MLE) is a method of estimating the parameters of a statistical model, given observations. MLE attempts to find the parameter values that maximize the likelihood function, given the observations.

ε 105 -^:

XY ε 0102 0.143 3 0.727 4 0.889 5 0.875 6 0.714 7182 mat :

x β Deriv x 0 - (β 2 el^(2^x 0 - ln x 0 - (2 β 2 el *^* β 1 el * - (β 1 el x 0 - (β 2 el^/ - exp * x 0 - (β 2 el^(2^x 0 - (β 2 el^* / :

X XY 1 col : Y XY 2 col : n XY rows : 31 line

x β f x diff x β Deriv 2 1 sys

n 8

SSD = "Sum Square Differences" SSD Y i el X i el β f - (2^(i 1 n sum : 0.0836

data 10020103^34 0.75 104^1113 0.85 105^78 0.88 106^2123 0.91 108^22164 mat :

D data 1 col : P data 2 col : T data 3 col : R data 4 col : 14 mat

ε 1012 -^: k data rows : 21 line

α.1 β.1 21 mat 1121 mat :

x α.1 β.1 f 11 x β.1 / + (α.1 -^- :

α.1 β.1 MLE P i el D i el α.1 β.1 f ln * T i el P i el - (1 ε + D 1 el α.1 β.1 f - ln * + i 1 k sum :

oops ! does not sanity ? α.1 β.1 MLE 19.1874 -