Skip to main content

Table 2 The six two-segment regression models considered in this study

From: Determining the transition from juvenile to mature wood microfibril angle in lodgepole pine: a comparison of six different two-segment models

Model

f 1(x)

f 2(x)

Constraints

LIN_C

\( y = a + bx \)

\( y = c \)

\( c = a + b{x_0} \)

LIN_LIN

\( y = a + bx \)

\( y = {a_2} + {b_2}x \)

\( {a_2} + {b_2}{x_0} = a + b{x_0} \)

EXP_C

\( y = a{e^{{ - bx}}} \)

\( y = c \)

\( c = a{e^{{ - b{x_0}}}} \)

EXP_LIN

\( y = a{e^{{ - bx}}} \)

\( y = {a_2} + {b_2}x \)

\( \matrix{ {{a_2} + {b_2}{x_0} = a{e^{{ - b{x_0}}}}} \hfill \\ }<!end array> \)

Q_C

\( y = a + bx + c{x^2} \)

\( y = c\prime \)

\( {c\prime = a + b{x_0} + cx_0^2} \ {x_0} = - \frac{b}{{2c}}\hfill \\ \)

Q_LIN

\( y = a + bx + c{x^2} \)

\( y = {a_2} + {b_2}x \)

\( \matrix{ {{a_2} + {b_2}{x_0} = a + b{x_0} + cx_0^2} \hfill \\ {{x_0} = - \frac{b}{{2c}}} \hfill \\ }<!end array> \)

 

  1. Note: f 1(x) applies for \( x \leqslant {x_0} \) and f 2(x) for \( x \geqslant {x_0}. \). The transition point of the two quadratic models can be obtained from the minimum point of the first quadratic segment, and for Q_C, it coincides with the smooth requirement (the first derivative of the quadratic segment being zero at the transition point)