Time-variations in wireless channels affect opportunistic selection in a multi-node wireless system in two ways. First, the selected node can become sub-optimal by the time data transmission commences. Second, the channel changes during data transmission. We develop a comprehensive and tractable analytical framework that accurately accounts for both these effects. It differs from the extensive existing literature that primarily focuses on time-variations until the data transmission starts. We first develop a novel concept of a time-invariant effective signal-to-noise ratio (TIESNR), which tractably and accurately captures the time-variations during the data transmission phase with partial channel state information available at the receiver. Thereafter, we model the joint distribution of the signal-to-noise ratio at the time of selection and TIESNR during the data transmission and analyze the average packet error rate (PER). Extensive numerical results verify the accuracy of each step of our approach and show that ignoring the correlated time-variations during the data transmission phase can significantly underestimate the average PER. © 2016 IEEE.