Data errors on a communications channel in a computer system are corrected. The data is transmitted over the communications channel in a sequence of time-multiplexed phases. A storage device accumulates the phases of data. An error detector and correction device checks the accumulated data for a data error and corrects the data error. The error detection and correction device can correct a one-bit data error, a two-bit data error, and a three-bit data error. Multiple bit errors can be corrected if the multiple bits of data are transmitted over one cable wire in multiple time phases. The communications channel carries the data over N sub-channels, and a parity check generator employs a predetermined parity check matrix based upon the N sub-channels and a probability that multiple errors in the accumulated data are attributable to a faulty sub-channel that affects the same data position in different time phases of the data. The error detection and correction device is operated based upon the parity check matrix. The communications channel includes a cable having N wire pairs, and the N sub-channels include the N wire pairs.