Since given data is incomplete, we assume it as follows:
The following data resulted from 5 experimental runs made on four independent variables and a single response y.
Here n=5. Write 5 equations with 4 explanatory variables in matrix notation.
Solution:
Here n=5, k=4.
Assuming that the model is
y = β 0 + β 1 X 1 + β 2 X 2 + … + β 4 X 4 + ε y=\beta_{0}+\beta_{1} X_{1}+\beta_{2} X_{2}+\ldots+\beta_{4} X_{4}+\varepsilon y = β 0 + β 1 X 1 + β 2 X 2 + … + β 4 X 4 + ε
the n-tuples of observations are also assumed to follow the same model. Thus they satisfy
y 1 = β 0 + β 1 x 11 + β 2 x 12 + … + β 4 x 14 + ε 1 ⋮ y 4 = β 0 + β 1 x 51 + β 2 x 52 + … + β 4 x 54 + ε 5 \begin{aligned}
&y_{1}=\beta_{0}+\beta_{1} x_{11}+\beta_{2} x_{12}+\ldots+\beta_{4} x_{1 4}+\varepsilon_{1} \\
&\vdots \\
&y_{4}=\beta_{0}+\beta_{1} x_{5 1}+\beta_{2} x_{5 2}+\ldots+\beta_{4} x_{54}+\varepsilon_{5}
\end{aligned} y 1 = β 0 + β 1 x 11 + β 2 x 12 + … + β 4 x 14 + ε 1 ⋮ y 4 = β 0 + β 1 x 51 + β 2 x 52 + … + β 4 x 54 + ε 5
These 5 equations can be written in matrix notation as
( y 1 y 2 ⋮ y 5 ) = ( 1 x 11 x 12 ⋯ x 14 1 x 21 x 22 ⋯ x 24 ⋮ ⋮ ⋮ ⋮ 1 x 51 x 52 ⋯ x 54 ) ( β 0 β 1 ⋮ β 4 ) + ( ε 1 ε 2 ⋮ ε 5 ) \left(\begin{array}{l}y_{1} \\ y_{2} \\ \vdots \\ y_{5}\end{array}\right)=\left(\begin{array}{ccccc}1 & x_{11} & x_{12} & \cdots & x_{1 4} \\ 1 & x_{21} & x_{22} & \cdots & x_{2 4} \\ \vdots & \vdots & \vdots & \vdots \\ 1 & x_{5 1} & x_{5 2} & \cdots & x_{54}\end{array}\right)\left(\begin{array}{l}\beta_{0} \\ \beta_{1} \\ \vdots \\ \beta_{4}\end{array}\right)+\left(\begin{array}{l}\varepsilon_{1} \\ \varepsilon_{2} \\ \vdots \\ \varepsilon_{5}\end{array}\right) ⎝ ⎛ y 1 y 2 ⋮ y 5 ⎠ ⎞ = ⎝ ⎛ 1 1 ⋮ 1 x 11 x 21 ⋮ x 51 x 12 x 22 ⋮ x 52 ⋯ ⋯ ⋮ ⋯ x 14 x 24 x 54 ⎠ ⎞ ⎝ ⎛ β 0 β 1 ⋮ β 4 ⎠ ⎞ + ⎝ ⎛ ε 1 ε 2 ⋮ ε 5 ⎠ ⎞
Comments