When individuals are nested within groups or organizations, or when repeated measures are taken from the same individuals, data points are not independent and standard techniques such as linear regression models are not suitable. Multilevel modeling (aka linear mixed-effects regression) is an extension of linear regression models that uses additional variance and covariance terms to account for the local dependencies implied by nested data structures. How do they work? How to conduct multilevel analyses?
Experience Sampling Methods (ESM) include a set of tools for the repeated and systematic sampling of psychological states, experiences, and activities in real time, in free-living conditions.
As described by Mihaly Csikszentmihalyi, one of the main pioneers of this methodology, ESM aim at “obtaining self-report for a representative sample of moments in people's life” to study the frequency, intensity, and patterning of self-reported experiences (thoughts, psychological states etc.), and daily activities (social interactions, changes in locations etc.