One of the ongoing controversies in interval timing concerns whether human time perception relies on multiple distinct mechanisms. This debate centres around whether subsecond and suprasecond timing may be attributed to a single semi-uniform mechanism or separate and interacting mechanisms. Whereas past studies offer valuable insights, this study overcomes previous limitations by adopting multiple convergent statistical approaches in a design with strong statistical power. We conducted two online experiments involving participants reproducing temporal intervals ranging from 400 to 2400ms (Experiment 1; N=302) and 1000 to 2000ms (Experiment 2; N=302). We contrasted the application of exploratory factor analysis and structural equation modelling to differentiate distinct latent structures underlying duration reproduction patterns. Additionally, we compared the model outcomes with results from changepoint analysis models fitted to individual participants’ data. In both experiments, these analyses yielded evidence for a two-factor model comprising a general timing factor spanning the full interval range and a second factor capturing the regression to the mean of presented stimulus intervals (central tendency bias). We observed a low proportion of detected changepoints, further supporting the limited evidence for a discontinuity between the distinct underlying mechanisms, while also finding that the changepoint detection was predicted by factor scores. These results highlight the role of central tendency effects in investigating changepoints and the continuity of timing systems. Our work contributes to integrating factor analytic and computational modelling approaches in the study of time perception and has implications for the measurement and interpretation of interval timing performance in a range of contexts.