Quantifying accuracy and precision from continuous response data in studies of spatial perception and crossmodal recalibration

This dataset contains data and code associated with the study "Quantifying accuracy and precision from continuous response data in studies of spatial perception and crossmodal recalibration" by Patrick Bruns, Caroline Thun, and Brigitte Röder.

example_code.R contains analysis code that can be used to to calculate error-based and regression-based localization performance metrics from single-subject response data with a working example in R. It requires as inputs a numeric vector containing the stimulus location (true value) in each trial and a numeric vector containing the corresponding localization response (perceived value) in each trial.

example_data.csv contains the data used in the working example of the analysis code.

localization.csv contains extracted localization performance metrics from 188 subjects which were analyzed in the study to assess the agreement between error-based and regression-based measures of accuracy and precision. The subjects had all naively performed an azimuthal sound localization task (see related identifiers for the underlying raw data).

recalibration.csv contains extracted localization performance metrics from a subsample of 57 subjects in whom data from a second sound localization test, performed after exposure to audiovisual stimuli in which the visual stimulus was consistently presented 13.5° to the right of the sound source, were available. The file contains baseline performance (pre) and changes in performance after audiovisual exposure relative to baseline (delta) in each of the localization performance metrics.

Localization performance metrics were either derived from the single-trial localization errors (error-based approach) or from a linear regression of localization responses on the actual target locations (regression-based approach).The following localization performance metrics were included in the study:

bias: overall bias of localization responses to the left (negative values) or to the right (positive values), equivalent to constant error (CE) in error-based approaches and intercept in regression-based approaches

absolute constant error (aCE): absolute value of bias (or CE), indicates the amount of bias irrespective of direction

mean absolute contant error (maCE): mean of the aCE per target location, reflects over- or underestimation of peripheral target locations

variable error (VE): mean of the standard deviations (SD) of the single-trial localization errors at each target location

pooled variable error (pVE): SD of the single-trial localization errors pooled across trials from all target locations

absolute error (AE): mean of the absolute values of the single-trial localization errors, sensitive to both bias and variability of the localization responses

slope: slope of the regression model function, indicates an overestimation (values > 1) or underestimation (values < 1) of peripheral target locations

R²: coefficient of determination of the regression model, indicates the goodness of the fit of the localization responses to the regression line