growth.curve {agce} | R Documentation |
This function is particular a case of the manova.growth, the manova reduces to an ANOVA when the a particular growth curve is linear.
growth.curve(data, C=NULL, U=NULL, normal=TRUE, B=1000, time=NULL)
data |
The data matrix or data frame, where the first column correspond to the group ids, the second to the animal ids, the remaining columns are the measurements at each time. |
C |
The left contrast matrix. Default to test same rate of growth in each group. |
U |
The right contrast matrix. Default to test same rate of growth in each group. |
normal |
A logical value, if normal is true the standard
deviations of the rates are computed based on normal assumption of
the measurements, otherwise computed by bootstraping. Default to TRUE. |
B |
A numeric value, the number of bootstraps. Only used if
normal is FALSE. |
time |
A vector of numeric values corresponding to the time
points at which the measurements were effectued. Time is absolutely required. |
In this function, we assume that the mean is of the form A+B*t. Where A, B are estimated . Therefore the mean is just a function (matrix multiplication ) of the rates.
Ftest |
The value of the F-test used to test the hypothesis based on C and U. |
df1 |
The numerator degrees of freedom for the F-test |
df2 |
The denominator degrees of freedom for the F-test |
p |
The p-value associated to the F-test |
mean |
The estimate of the mean |
std.mean |
The standard deviation associated to the mean |
rate |
The rate of growth. Set to NULL if rate is FALSE |
std.rate |
The standard deviation of the rates. Set to NULL if rate is FALSE |
Raphael Gottardo
Daniel F. Heitjan, Andrea Manni and Richard J. Santen Statistical Analysis of in Vivo Tumor Growth Experiments Cancer Research 53:6042-6050, 1993.
data(Bt20) growth.curve(Bt20, C=NULL, U=NULL, normal=TRUE, time=c(0,3,7,10,14,16))