Rk. Edgar et K. Laird, COMPUTER-SIMULATION OF ERROR RATES OF POISSON-BASED INTERVAL ESTIMATES OF PLANKTON ABUNDANCE, Hydrobiologia, 264(2), 1993, pp. 65-77
The routine assignment of error rates (confidence intervals) to Poisso
n distribution estimates of plankton abundance should be rejected. In
addition to the interval estimation procedure being pseudoreplicative,
it is not robust to common violations of its assumptions. Because the
spatial dispersion of organisms in sampling units from the counting c
hamber to the field is rarely random and because counting protocols ar
e usually terminated by a count threshold having been equalled or exce
eded, Poisson based estimates are usually derived from sampling non-Po
isson distributions. Computer simulation was used to investigate the q
uantitative consequences of such estimates. The expected mean error ra
te of 95% confidence intervals is inflated from 5% to 15% as contagion
increases, as the parametric variance-mean ratio increases from 1 to
2. Also, count threshold termination of the counting protocol effects
both a biased estimate of the parametric mean (or total) and alters ex
pected mean error rates, especially if the total count is low (< 100 o
rganisms) and the mean density in the sampling unit is low.