The smoothness of a fitted curve depends on the size of the neighbourhood that is used to calculate the smoothed value at a particular point.

If the neighbourhood is small the smoothing function will be rough and may have a high variance

If the neighbourhood is large, the estimate may be too smooth and will not pick up curvature in the underlying function i.e. it might be biased

Statistical software usually provides

* A default span, or
* Calculates an optimum span, by cross-validation