1. We report here about the modulation of dorsal spinocerebellar tract (DSCT) activity by limb posture. In principle, DSCT activity could represent limb position in one of several ways. According to a classical notion of DSCT function, DSCT activity might be expected to correlate with changes in individual joint angles. However, given the evidence for extensive polysynaptic convergence onto DSCT units, it is reasonable to propose that DSCT activity represents more global variables such as the orientation of limb segments or the length and orientation of the whole limb. 2. In six anesthetized cats we recorded the activity of 96 antidromically identified DSCT neurons while a robot arm passively positioned the left hindfoot in 20 positions distributed in the sagittal plane, holding each position for 8 s. For each position we measured the joint angles, limb segment angles, and the length and orientation of the limb axis (defined as the line connecting the hip joint to the hindpaw). We used regression statistics to quantify 1) possible relationships among geometric variables of the hindlimb and 2) relationships between DSCT firing rate and limb variables. 3. First, we found a statistically significant relationship among the joint angles that could be described by a covariance plane accounting for approximately 70 percent of the total variance. Thus the 3 degrees of freedom represented by the joint angles in the sagittal plane are effectively reduced to only 2 by the coupling between joints. This finding resembles that described for the behaving cat during stance. However, the correlation between the hip and ankle angles in the passively displaced hindlimb was just the opposite of that observed during active stance. Moreover, we observed that the length and the orientation of the limb axis is determined simply by a linear combination of the three joint angles. 4. Most of the DSCT neurons (82 of 96) were significantly modulated by changes in foot position (1-way analysis of variance, P < 0.001). For those cells, we explored systematically how their activity was related to limb geometric variables. We found mostly linear relationships between individual joint or limb segments angles and DSCT firing rates. However, although these relationships were statistically significant, the random variance was often quite high. Moreover, approximately 70% of the cells were modulated by more than one joint or limb segment angle, suggesting that a model incorporating global geometric variables might explain a larger fraction of the variance in the neural data. 5. Consequently we tested how well DSCT activity was modulated by the length and the orientation of the limb axis with the use of a linear regression model with length and orientation (or the equivalent linear combination of joint angles) as predictors. We found that this model explained a larger fraction of the variability in the firing pattern of nearly every modulated cell than did any of the single joint models tested. 6. We also attempted to account for the effect of the mechanical joint covariance on this result by accounting for correlated independent variables in the analysis. We used a regression model incorporating all three joint or limb segment angles and performed a backward elimination of insignificant or redundant variables. The result was that 67% of the neurons were independently modulated by at least two joint angles, indicating that the modulation did not necessarily reflect the biomechanical constraint of joint angle covariation, but rather a central convergence of sensory information from more than a single joint. 7. From these results we conclude that the firing rates of a majority of DSCT neurons encode the position of the hindfoot relative to the hip joint.(ABSTRACT TRUNCATED)