Fluorescence fluctuation spectroscopy and microscopy have been powerful tools for studying molecular organization and dynamics in cells. Fluorescence Correlation Spectroscopy (FCS) has been widely applied to probing molecular dynamics in live cells with single molecule sensitivity and the ability to resolve local molecular concentrations, aggregation states, and transport mechanisms. Despite the broad utility of FCS, interpretationf cellular FCS data is often confounded by the heterogeneityn the underlying biological process and the low signalto-noise ratio. Systematic data evaluation and interpretation become even more challenging for imaging FCS, where hundreds to thousands of FCS curves are generated in a single measurement. This thesis presents an objective Bayesian inference procedure for testing multiple competing FCS models. Bayesian inference determines model probabilities by considering the probability distributions over the full range of parameter values, thereby naturally penalizes model complexity and prevents over-fitting. We applied this procedure to imaging FCS data in order to resolve hIAPP-induced microdomain spatial organization and temporal dynamics in the cell membrane. Our analysis resolved the temporal evolution of multiple diffusing species in the spatially heterogeneous cell membrane, lending support to the "carpet model" for the association mode of hIAPP aggregates with the plasma membrane. Finally, we presented a fluctuation-based microscopy approach, Points Accumulation for Imaging in Nanoscale Topography (PAINT), that enables highly multiplexed super-resolution imaging of synaptic proteins. We employed DNA-PAINT to resolve nano-scale organization of seven targets simultaneously including synaptic proteins and cytoskeletal markers. These approaches demonstrated the broad applicability of fluorescence fluctuation spectroscopy and microscopy in resolving molecular dynamics and organization in cells.