Validating analysis time window
The design of a longitudinal study involves the selection of a window size before or after data collection.
In many cases, researchers must select the window size before conducting the underlying research.
The approach is applied to four real-world, variable-sized longitudinal networks to determine their optimal window sizes.
The optimal window length for each network, determined using the approach proposed in this paper, is further evaluated via time series and data mining methods to validate its optimality.
Window size selection is considered to be central to the design of any longitudinal research study; however, researchers often overlook this component.For any given window with a specified time length, some actors exhibit higher levels of network activity than others; for example, an actor (Actor 1) in a longitudinal network might create only one new tie in a window, while another actor (Actor 2) in the same longitudinal network might forge five new ties in the same window.It may be the case that Actor 1 has exhibited a higher level of network activity at the very beginning of the next window, or Actor 2 has created all five new ties at the end of the present window.The time interval between two snapshots is referred to as the window size.A given longitudinal network can be analysed from various actor-level perspectives, such as exploring how actors change their degree centrality values or participation statistics over time.