| age.comp {FSA} | R Documentation |
Computes overall measures of precision and bias for paired age assignments. The paired age assignments can consist of age measurements recorded for two structures (e.g., otoliths and scales), for two readers of the same structure, or for one reader at two times.
age.comp(col.data,row.data,col.lab="First",row.lab="Second")
## S3 method for class 'AgeComp':
summary(object,what=c("precision","agreement","differences","prec.stats",
"symmetry","detail"),...)
## S3 method for class 'AgeComp':
plot(x,what=c("bias","sunflower"),conf.level=0.95,show.n=TRUE,xlab=x$col.lab,
ylab=x$row.lab,...)
col.data |
A numeric vector containing the recorded age assignments that will form the columns in the table or the x-axis on the plots. |
row.data |
A numeric vector containing the recorded age assignments that will form the columns in the table or the y-axis on the plots. |
col.lab |
A character string containing an optional label for the column age assignments. |
row.lab |
A character string containing an optional label for the row age assignments. |
x |
An object saved from the age.comp call (i.e., of class AgeComp). |
object |
An object saved from the age.comp call (i.e., of class AgeComp). |
what |
A string indicating what type of summary to print or plot to construct. See details. |
xlab |
A character string containing an optional label for the x-axis age assignments. |
ylab |
A character string containing an optional label for the x-axis age assignments. |
conf.level |
Level of confidence to use for constructing confidence intervals (default is 0.95). |
show.n |
A boolean value indicating whether the sample sizes for each age assignment in the first column is shown (=TRUE, default) or not (=FALSE). |
... |
Additional arguments for methods. |
If one age assignment is thought to be more accurate then it should be in col.data.
If what="agreement" in the summary method then only the age-agreement table is printed. If what="differences" then only a table of the percentage of individuals by absolute difference in age is printed. If what="prec.stats" then summary statistics of overall percentage agreement, overall APE, and overall CV are printed. All of the previous items can be printed if what="precision" (the default). A data frame of the original data plus all intermediate caculations of the differences in assigned ages, average age, standard deviation of age, APE, and CV for each individual fish will be printed if what="detail". If what="symmetry" then Bowker's test of symmetry, as proposed by Hoenig (1995), to determine if systematic differences exist between paired ages assignments is printed.
If what="bias" (the default) in the plot method then an age-bias plot as described by Campana et al. (1995) is produced. The variable sent to col.data in the original age.comp call is plotted on the x-axis. The confidence intervals are computed for the data on the y-axis for each “level” of the data on the x-axis and plotted in red. Intervals that connect the minimum to the maximum value of the data on the y-axis for each “level” of the data on the x-axis is plotted in grey. The confidence level used in the confidence intervals for this option can be controlled with the conf.level argument. A 1:1 (45 degree) line is shown for comparative purposes. The sample sizes at each “level” of the data on the x-axis is shown if show.n=TRUE (the default).
If what="sunflower" (the default) in the plot method then a sunflower plot is constructed with the variable sent to col.data in the original age.comp call is plotted on the x-axis. A sunflower plot contains a point for each unique (x,y) coordinate with a “petal” added to each point for each observation that has the same (x,y) coordinate. Thus, points with more petals have more observations at that point.
A list with the following items
detail |
A data frame will all given and computed information about each fish. |
absdiff |
A table of percentage by absolute differences in age. |
agree |
The age agreement table. |
stats |
The summary statistics of percent agreement, AVE, and CV. |
col.lab |
A character string containing an optional label for the column structure or readings. |
row.lab |
A character string containing an optional label for the row structure or readings. |
Derek H. Ogle, dogle@northland.edu
Beamish, R.J. and D.A. Fournier. 1981. A method for comparing the precision of a set of age determinations. Canadian Journal of Fisheries and Aquatic Sciences, 38:982-983.
Campana, S.E. 1982. Accuracy, precision and quality control in age determination, including a review of the use and abuse of age validation methods. Journal of Fish Biology, 59:197-242.
Campana, S.E., M.C. Annand, and J.I. McMillan. 1995. Graphical and statistical methods for determining the consistency of age determinations. Transactions of the American Fisheries Society, 124:131-138.
Chang, W.Y.B. 1982. A statistical method for evaluating the reproducibility of age determination. Canadian Journal of Fisheries and Aquatic Sciences, 39:1208-1210.
Hoenig, J.M., M.J. Morgan, and C.A. Brown. 1995. Analysing differences between two age determination methods by tests of symmetry. Canadian Journal of Fisheries And Aquatic Systems, 52:364-368.
data(StripedBass1) attach(StripedBass1) ac1 <- age.comp(ageO,ageS,col.lab="Otolith Age",row.lab="Scale Age") summary(ac1) summary(ac1,what="agreement") summary(ac1,what="prec.stats") summary(ac1,what="detail") summary(ac1,what="symmetry") plot(ac1) plot(ac1,what="sunflower") detach(StripedBass1)