Time-series analysis for rapid event-related skin conductance responses

Abstract

Event-related skin conductance responses (SCRs) are traditionally analysed by comparing the amplitude of individual peaks against a pre-stimulus baseline. Many experimental manipulations in cognitive neuroscience dictate paradigms with short inter trial intervals, precluding accurate baseline estimation for SCR measurements. Here, we present a novel and general approach to SCR analysis, derived from methods used in neuroimaging that estimate responses using a linear convolution model. In effect, the method obviates peak-scoring and makes use of the full SCR. We demonstrate, across three experiments, that the method has face validity in analysing reactions to a loud white noise and emotional pictures, can be generalised to paradigms where the shape of the response function is unknown and can account for parametric trial-by-trial effects. We suggest our approach provides greater flexibility in analysing SCRs than existing methods.

Fig. 1

Convolved time-series: an example from functional magnetic resonance imaging (fMRI). Top: event onsets are specified as a stick, or delta function. Middle: the canonical hemodynamic response function is the most parsimonious response function used in fMRI research. Bottom: convolution of the event onset function with the response function results in a time series that reflects the overlay of single responses.

Fig. 2

Basis set for an uninformed finite impulse response model, with 30 time bins of 1 s length. Each time bin codes a regressor across events. An idealised example for typical parameter estimates in fMRI is shown below. This procedure of estimating a response function is profoundly different from “averaging” responses, since during averaging, overlapping segments are accounted for several times.

Fig. 3

Principal component analysis (PCA) of the responses across all participants, conditions, and trials. Top: the three first components that together explain 78.9% of the overall variability in response shape. Note that the second component resembles a derivative with respect to time of the first component. Bottom: A smoothed gamma distribution (dotted) was fitted to the first component of the PCA (solid line, depicted with standard deviation as grey shadow) to describe the response function's analytical form.

Fig. 4

Orthogonalised informed basis set and the effect of adding derivatives to the CRF in order to shift or smooth the response peak.

Fig. 5

Experiment 2: Example of estimating the response shape, using an uninformed finite impulse response model that consists of a number of boxcar functions for each time bin during the response. Here, we used 30 post-stimulus time bins of 1 s length. Top: Fitted responses across the study sample for the three different ISIs, mean ± standard error across participants. For comparison, the broken line depicts the canonical response function (CRF), derived from experiment 1. Middle: Continuous data for one participant at an ISI of 3 s. Event onsets are marked on the x-axis. The observed and predicted responses are shown as solid and broken lines, respectively. Bottom: Similar to the middle panel, this panel shows observed and predicted responses for the same participant, using the canonical response function and its two derivatives. Note that for comparison, this model did not include adaptation parameters. Adaptation parameters further improved the model fit, as pointed out in the text.