apc.lines {Epi} | R Documentation |
When an APC-frame has been produced by apc.frame
, this
function draws a set of estimates from an APC-fit in the frame. An
optional drift parameter can be added to the period parameters and
subtracted from the cohort- and age parameters.
apc.lines( A, P, C, scale = "log", frame.par = c(min(C[, 1]) + max(A[, 1]), ifelse( scale == "log", exp(mean(A[, 2])), exp(mean(log(A[, 2]))))), drift = 0, c0 = median(C[, 1]), a0 = median(A[, 1]), p0 = c0 + a0, ci = rep(FALSE, 3), lwd = c(3, 1, 1), lty = rep(1, 3), col = rep("black", 3))
A |
Age effects. A 4-column matrix with columns age, age-specific rates, lower and upper c.i. |
P |
Period effects. Rate-ratios. Same form as for the age-effects. |
C |
Cohort effects. Rate-ratios. Same form as for the age-effects. |
scale |
Are effects given on a log-scale? Character variable, one
of "log" , "ln" , "rates" , "inc" ,
"RR" . If "log" or "ln" it is assumed that
effects are log(rates) and log(RRs) otherwise the actual effects are
assumed given in A , P and C . |
frame.par |
2-element vector with the cohort-period offset, and
RR multiplicator. This will typically be the result from the call of
apc.frame |
drift |
The drift parameter to be added to the period effect. If
scale="log" this is assumed to be on the log-scale, otherwise
it is assumed to be a multiplicative factor per unit of the first
columns of A , P and C |
c0 |
The cohort where the drift is assumed to be 0; the subtracted
drift effect is drift*(C[,1]-c0) . |
a0 |
The age where the drift is assumed to be 0. |
p0 |
The period where the drift is assumed to be 0. |
ci |
Should confidence interval be drawn. Logical or
character. If character, any occurrence of "a" or "A"
produces confidence intervals for the age-effect. Similarly for
period and cohort. |
lwd |
Line widths for estimates, lower and upper confidence limits. |
lty |
Linetypes for the three effects. |
col |
Colours for the three effects. |
The drawing of three effects in an APC-frame is a rather trivial task, and the main purpose of the utility is to provide a function that easily adds the functionality of adding a drift so that several sets of lines can be easily produced in the same frame.
A list of three matrices with the effects actually plotted is returned invisibly.
Bendix Carstensen, Steno Diabetes Center, http://www.pubhealth.ku.dk/~bxc