Papers :On mis-specification
Schmidt-Catran & Fairborht 2015. The Random Effects in Multilevel Models: Getting Them Wrong and Getting Them Right
Nakagawa - nested by design?
Mis specification results in pseudoreplication.
Forstmeir et al 2016 Detecting and avoiding likely false-positive findings – a practical guid
Table 1: "Non-independence of data points (e.g. related individuals, temporal and spatial autocorrelation) "
- Test for non-independence, autocorrelation
- Fit grouping variables as random effects (intercepts, slopes, space, time, pedigrees)
- Run analysis at the level where independence is met
- Balance experiments for confounding effects
example " (a) Pseudoreplication at the individual level