Randomized Intervention Analysis and the Interpretation of Whole‐Ecosystem Experiments

Abstract

Randomized intervention analysis (RIA) is used to detect changes in a manipulated ecosystem relative to an undisturbed reference system. It requires paired time series of data from both ecosystems before and after manipulation. RIA is not affected by non—normal errors in data. Monte Carlo simulation indicated that, even when serial autocorrelation was substantial, the true P value (i.e., from nonoautocorrelated data) was <.05 when the P value from autocorrelated data was <.01. We applied RIA to data from 12 lakes (3 manipulated and 9 reference ecosystems) over 3 yr. RIA consistently indicated changes after major manipulations and only rarely indicated changes in ecosystems that were not manipulated. Less than 3% of the data sets we analyzed had equivocal results because of serial autocorrelation. RIA appears to be a reliable method for determining whether a nonrandom change has occurred in a manipulated ecosystem. Ecological arguments must be combined with statistical evidence to determine whether the changes demonstrated by RIA can be attributed to a specific ecosystem manipulation.

Long-Memory and Spurious Breaks in Ecological Experiments

“…However, their points concerned incorrect specification of the process mean structure and not the process autocorrelation structure. An examination of RIA for correlated data is in Carpenter et al [2]. However, the autocorrelations studied were short-memory and moderate at most in strength.…”

“…One examination is in Carpenter et al [2]. The authors simulated data from short-memory AR(1) and MA(1) processes and analyzed these with a permutation test.…”

“…Carpenter et al appear to have introduced RIA in [2]. The RIA permutation test examines all possible permutations of the observed pre-intervention and post-intervention differences, determines a distribution from this for the absolute value of the difference between the pre-intervention and the postintervention means and uses this distribution to compute a p-value for the observed data.…”

“…Examples are observations of population densities such as the relative abundance of the white sea urchin (Lytechinus anamesus) in an area offshore the San Onofre Nuclear Generating Station (Schroeter et al [1]), or of the difference in chlorophyll concentrations between two lakes (Carpenter et al [2]). This data need not satisfy the standard assumption of independent observations but can in fact be autocorrelated.…”

“…The original BACI analysis uses a 2-sample t-test to compare the pre-intervention mean paired difference with the post-intervention mean paired difference. An alternative to the 2-sample t-test is Randomized Intervention Analysis (RIA) [2], which uses a permutation test to conduct the comparison. BACI and RIA both assume the pre-intervention differences and the post-intervention differences from the repeated measurements on the control and the impact units form two independent random samples.…”