If you don't remember your password, you can reset it by entering your email address and clicking the Reset Password button. You will then receive an email that contains a secure link for resetting your password
If the address matches a valid account an email will be sent to __email__ with instructions for resetting your password
We agree that there may be aspects that are not revealed by a correlation coefficient
and that an analysis of the residuals may provide further insights. Our article already
provides a figure showing linear regression lines based on the individual data points.
As suggested in Morone's letter, we have now further created residual plots to look
at whether the variations in residuals plotted against the predicted walking speed
are systematic or not. As shown in figure 1, the variations in residuals are nonsystematic in our group of stroke patients. In
the multiple sclerosis (MS) patients, the residual plot bears a slight resemblance
to an inverted U-shape, indicating that the relation between the 2 tests might be
better represented by a curvilinear model. However, fitting to a second-order polynomial
instead of a linear regression would only minimally increase the predictive power
of the fit (r=.97 vs .95). The residuals of the control group do not seem to vary systematically.
Fig 1Residual plots showing individual differences between measured 6MWT speed and 6MWT
speed predicted from linear regression between the 10mWT and 6MWT tests. Stroke patients,
MS patients, and controls are shown separately. For details on subjects and methods
see the Dalgas et al article.
We read with great interest the article by Dalgas et al.1 Dalgas found a strong correlation between walking speeds evaluated during the 10 meter walk test and the 6 minute walk test (6MWT) in patients affected by chronic stroke and in patients with multiple sclerosis (MS), whereas a weaker correlation was found in healthy subjects.
