Statistical non-parametric mapping in sensor space

Abstract

Establishing the significance of observed effects is a preliminary requirement for any meaningful interpretation of clinical and experimental Electroencephalography or Magnetoencephalography (MEG) data. We propose a method to evaluate significance on the level of sensors whilst retaining full temporal or spectral resolution. Input data are multiple realizations of sensor data. In this context, multiple realizations may be the individual epochs obtained in an evoked-response experiment, or group study data, possibly averaged within subject and event type, or spontaneous events such as spikes of different types. In this contribution, we apply Statistical non-Parametric Mapping (SnPM) to MEG sensor data. SnPM is a non-parametric permutation or randomization test that is assumption-free regarding distributional properties of the underlying data. The method, referred to as Maps SnPM, is demonstrated using MEG data from an auditory mismatch negativity paradigm with one frequent and two rare stimuli and validated by comparison with Topographic Analysis of Variance (TANOVA). The result is a time- or frequency-resolved breakdown of sensors that show consistent activity within and/or differ significantly between event or spike types. TANOVA and Maps SnPM were applied to the individual epochs obtained in an evoked-response experiment. The TANOVA analysis established data plausibility and identified latencies-of-interest for further analysis. Maps SnPM, in addition to the above, identified sensors of significantly different activity between stimulus types.

Keywords: EEG; Evoked Response; MEG; Statistical non-Parametric Mapping; Topographic Analysis of Variance.

Fig. 1

Averages for the three stimulus types, plotted at the locations of the sensors. Sensors are identified by their numbers. Waveforms cover latencies from −100 to 600 ms. Dashed red lines are used for dev1, dotted blue lines for dev2, and solid black lines for standard. The sensor array is viewed from above using a spherical projection, with the nose pointing upwards

Fig. 2

TANOVA consistency test results for stimulus types dev1 (first row), dev2 (second row), and standard (third row). White areas indicate consistency, with p < 0.0203, while gray areas indicate that significance could not be established. Waveforms are MGFPs of the average per stimulus type and shown for guidance only. To the left of each row, field topography maps are shown for the 225 ms latency. The contour line distance is 10 fT and negative contour lines are dashed and rendered in blue, while positive contour lines are solid and red. The zero-line is solid and black. The sensor array is viewed from above using a spherical projection, with the nose pointing upwards

Fig. 3

TANOVA difference test results for stimulus types dev1 vs. standard (first row) and dev2 vs. standard (second row). White areas indicate significant topography map differences, with p < α, while gray areas indicate that significance could not be established. Waveforms are p values, displayed using a logarithmic scale. The horizontal dotted line marks the corrected significance threshold of α = 0.0203. The numbers in the upper right of each row are the p values for the 225 ms latency. To the left of each row, channel impact maps are shown, where darker colors indicate a higher impact. The sensor array is viewed from above using a spherical projection, with the nose pointing upwards

Fig. 4

Maps SnPM consistency test results for stimulus types dev1 (first row), dev2 (second row), and standard (third row). White areas indicate significant consistency on the channel level in at least one channel, with p < α, while gray areas indicate that significance could not be established for any channel. Waveforms are p values, displayed using a logarithmic scale. The horizontal dotted line marks the corrected significance threshold of α = 0.0203. The numbers in the upper right of each row are the p values for the 225 ms latency. To the left of each row, channel significance maps are shown, where darker colors indicate higher t values and thus significance, while all other channels that are not significant are rendered in white. For comparability, channel significance maps are normalized to their largest entry. The sensor array is viewed from above using a spherical projection, with the nose pointing upwards

Fig. 5

Maps SnPM difference test results for stimulus types dev1 vs. standard (first row) and dev2 vs. standard (second row). White areas indicate significant channel data differences in at least one channel, with p < α, while gray areas indicate that significance could not be established for any channel. Waveforms are p values, displayed using a logarithmic scale. The horizontal dotted line marks the corrected significance threshold of α = 0.0203. The numbers in the upper right of each row are the p values for the 225 ms latency. To the left of each row, channel significance maps are shown, where darker colors indicate higher F values and thus significance, while all other channels that are not significant are rendered in white. For comparability, channel significance maps are normalized to their largest entry. The sensor array is viewed from above using a spherical projection, with the nose pointing upwards