The first step is calculating the variance of the residuals under the assumption that the mean of the residuals is equal to the target value.
Analysis of the residuals under various operating conditions of the chilling systems and minimization of the sum of the squares of the corrected balance residuals make it possible to locate biased sensors and to estimate the magnitudes of the biases.
Otherwise, pooling is not valid since the non-stationarity of the common factors is transmitted to the residuals under the null hypothesis of stationarity because it does not fade away even asymptotically.18.18
These techniques are usually formulated in a well-known form of a Kalman filter (KF), where it has been proven that the KF innovations follow a similar statistical distribution to that of the LS residuals under equal noise assumptions [23].
Tests were based on type III sums of squares and 99.999 permutations of the residuals under a reduced model.
Predictors were normalized and were fitted conditionally in a step-wise manner, with tests based on 9999 permutations of the residuals under the reduced model [44], [45].
We chose the "Permutation of Residuals under the Reduced Model" method as it has been shown to out-perform the raw data randomization method in terms of inflation of the type-1 error rate [30].
The analysis was based on Bray-Curtis similarity on previously presence/absence transformed data, using 999 random permutations of appropriate units, with permutation of residuals under a reduced model [41].
Initial optimisation identified parameterisations all displaying residuals under ϵ = 50.
Next, residuals under the reduced model were randomly permuted 10,000 times.
