This paper proposes a novel framework to analyze the symbol error probability (SEP) for multicarrier index keying orthogonal frequency-division multiplexing (MCIK-OFDM) systems. Considering two different types of detections such as the maximum likelihood (ML) and low-complexity greedy detectors (GD), we derive tight closed-form expressions for the average SEPs of MCIK-OFDM in the presence of channel state information (CSI) uncertainty. We undertake an asymptotic performance analysis with respect to three CSI conditions, which ensures to provide a comprehensive insight into the achievable diversity and coding gains as well as the impact of various CSI uncertainties on the SEP performance. The SEP performance comparison between the ML and GD is obtained under different CSI uncertainties. This interestingly reveals that the GD can achieve nearly optimal error performance as the M-ary modulation size is large or even outperforms the ML under certain CSI conditions. Finally, the theoretical and asymptotic analysis are verified via simulation results, obtaining the high accuracy of the derived SEP.