We used computer simulations to evaluate different procedures for measuring changes in the onset latency of a representative range of event-related components (the auditory and visual N1, P3, N2pc, and the frequency-related P3 difference wave). These procedures included several techniques to determine onset latencies combined with approaches using both single-participant average waveforms and jackknife-subsample average waveforms. In general, the jackknife-based approach combined with the relative criterion technique or combined with the fractional area technique (J.C. Hansen & S.A. Hillyard, 1980; S.J. Luck, 2005) provided the most accurate method and the greatest statistical power, with no inflation of Type I error rate.Descriptors: ERP latency, Jackknife, N1, P3, N2pc, Frequency-related P3Research using event-related potentials (ERPs) often focuses on differences in amplitudes as well as differences in latencies of ERP components. However, for both measurements there are several scoring methods, and quite often researchers have to decide rather arbitrarily which method might be most appropriate. In this article we compare several methods for determining ERP latency differences. To evaluate the methods we ran computer simulations based on data of five ERP components: the visual N1, the auditory N1, the P3 (hereafter used to mean the P3b), the N2pc, and the frequency-related P3 component (infrequent minus frequent difference wave).These five components were chosen because they are very different and representative of a broad range of components, as is apparent from the following brief review of these components. The N1 components (visual, auditory) are relatively early components, strongly influenced by physical properties of the stimulus. They are characterized by a clear onset and a sharply increasing amplitude, but clearly reflect different underlying neural generators. In contrast, the P3 is a late component that is relatively insensitive to the physical properties of the stimulus (with the exception of tone intensity; see Covington & Polich, 1996), but is influenced by probabilities, expectations, and resource allocation (see Johnson, 1986). Quite often the P3 does not show a clear onset, and its peak latency is difficult to determine because the component has a wide temporal extension without a sharp peak. The N2pc and frequency-related P3, for their part, are measured from difference waves that are obtained by subtracting ERP waveforms computed at different electrode sites or at same electrode sites but in different experimental conditions. The N2pc is an index of the allocation of visualspatial attention and is isolated by subtracting the ERP at posterior electrode sites ipsilateral to an attended item from the ERP at the corresponding contralateral electrode site, whereas the frequency-related P3 is isolated by subtracting the ERP elicited by frequent targets from the ERP elicited by infrequent targets.For all components, researchers are often interested in estimating the latency differences a...