Long-Term Forest Health Monitoring Program in the Eastern Mountains and Rivers Network Evaluation of the Statistical Power to Detect Temporal Trends

We evaluated the power of the ERMN Forest and Soil Monitoring Program's sampling design to detect trends in 30 key forest health variables. We used a simulation approach to examine the statistical power to detect temporal trends in 17 non-count variables and four count variables using the variance components estimated from mixed models. We were unable to perform power analyses for nine of the count variables because mixed models failed to converge (i.e., estimates of variance...
More Description

We evaluated the power of the ERMN Forest and Soil Monitoring Program's sampling design to detect trends in 30 key forest health variables. We used a simulation approach to examine the statistical power to detect temporal trends in 17 non-count variables and four count variables using the variance components estimated from mixed models. We were unable to perform power analyses for nine of the count variables because mixed models failed to converge (i.e., estimates of variance components were not achieved).