> library(NCStats) # Summarize, view
> library(car) # Anova
> options(contrasts=c("contr.sum","contr.poly"))
The working directory is set and the data file (i.e., box5_2.txt) is read with,
> setwd("c://aaaWork//web//fishR//bookex//AIFFD//Box5_2")
> d <- read.table("box5_2.txt", header = TRUE)
The structure of the data frame and the first six rows of the data frame are observed with,
> str(d)
'data.frame': 416 obs. of 8 variables:
$ ID : Factor w/ 63 levels "07447","200404111",..: 1 1 1 3 3 3 3 4 4 4 ...
$ sex : Factor w/ 2 levels "F","M": 2 2 2 1 1 1 1 1 1 1 ...
$ Lc : int 336 336 336 395 395 395 395 386 386 386 ...
$ date: int 2004 2004 2004 2004 2004 2004 2004 2004 2004 2004 ...
$ age : int 3 3 3 4 4 4 4 4 4 4 ...
$ Sc : num 16.3 16.3 16.3 18.4 18.4 18.4 18.4 18.6 18.6 18.6 ...
$ inc : int 1 2 3 1 2 3 4 1 2 3 ...
$ Si : num 5 12.9 16.3 4.8 9.9 16.5 18.4 4.9 8.5 13.6 ...
> head(d)
ID sex Lc date age Sc inc Si
1 07447 M 336 2004 3 16.3 1 5.0
2 07447 M 336 2004 3 16.3 2 12.9
3 07447 M 336 2004 3 16.3 3 16.3
4 35334 F 395 2004 4 18.4 1 4.8
5 35334 F 395 2004 4 18.4 2 9.9
6 35334 F 395 2004 4 18.4 3 16.5
It is very important to note that this data file is already in what is called one-radii-per-line format. This is noted by the fact that the first three lines of the data file all pertain to fish number 07447. Note that all information in those three rows is the same except in the column labelled Si which is the scale radius at age i. It is common for the data to be collected in what is called one-fish-per-line format where all information for one fish is found in one row of the data file. The data must be in one-radii-per-line format to efficiently back-calculate length-at-age. Methods of converting from one format to the other format are described here.
|
The data must be in one-radii-per-line format for back-calculation methods. |
Finally, for some back-calculation methods (e.g., Dahl-Lea) it is not important that the measurements made on the fish and those made on the scales are in the same units. However, a common set of units is required for other methods (e.g., Fraser-Lee). The scale and fish measurements should be converted to common units to guard against forgetting to do this later. The authors note that the fish measurements in this example are mm whereas the scale measurements are in cm at a magnificant of 24X. Thus, the scale measurements are converted to actual mm (and stored in a new veriable) with,
> d$Si2 <- d$Si*10/24 # convert radial measurements
> d$Sc2 <- d$Sc*10/24 # convert total scale radius
> head(d)
ID sex Lc date age Sc inc Si Si2 Sc2
1 07447 M 336 2004 3 16.3 1 5.0 2.083333 6.791667
2 07447 M 336 2004 3 16.3 2 12.9 5.375000 6.791667
3 07447 M 336 2004 3 16.3 3 16.3 6.791667 6.791667
4 35334 F 395 2004 4 18.4 1 4.8 2.000000 7.666667
5 35334 F 395 2004 4 18.4 2 9.9 4.125000 7.666667
6 35334 F 395 2004 4 18.4 3 16.5 6.875000 7.666667
|
|
In general, the scale and length measurements should be in the same units (i.e., the same scale). |
