Figure 3:
The influence of the parameterisation choice on the parameter landscape. A straight line is fitted through three datapoints. In subplot (a) the line is parameterized by intercept Ym(0) and slope s, giving Y = s*X + Ym(0). This parameterisation leads to the landscape shown under (b), which has a valley shape. In subplot (c) the line is parameterized by the two values Ym(1) and Ym(2), giving Y = (Ym(2)-Ym(1))*(X-1) + Ym(1). This parameterisation gives the trough-shaped parameter landscape shown under (d). Changing the parameterisation therefore drastically changes the landscape.

The influence of the parameterisation choice on the parameter landscape. A straight line is fitted through three datapoints. In subplot (a) the line is parameterized by intercept Ym(0) and slope s, giving Y = s*X + Ym(0). This parameterisation leads to the landscape shown under (b), which has a valley shape. In subplot (c) the line is parameterized by the two values Ym(1) and Ym(2), giving Y = (Ym(2)-Ym(1))*(X-1) + Ym(1). This parameterisation gives the trough-shaped parameter landscape shown under (d). Changing the parameterisation therefore drastically changes the landscape.

Close
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close

This PDF is available to Subscribers Only

View Article Abstract & Purchase Options

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Close