A practical method is proposed to determine the minimum embedding dime
nsion from a scalar time series. It has the following advantages: (1)
does not contain any subjective parameters except for the time-delay f
or the embedding; (2) does not strongly depend on how many data points
are available; (3) can clearly distinguish deterministic signals from
stochastic signals; (4) works well for time series from high-dimensio
nal attractors; (5) is computationally efficient. Several time series
are tested to show the above advantages of the method.