9.7 Linear case. The state estimate $\widehat {\mathrm {x}}\left (t\right )$xˆ(t) at any point in time $t$ is a linear combination of the initial state estimate $\widehat {\mathrm {x}}\left (t_{0}\right )$xˆ(t₀), and

1. all of the observations $\underline {\ell }_{i}=\underline {\ell }\left (t_{i}\right )$l_i = l(t_i)
2. only the observations for which $t_{i}\lt t$t_i < t
3. only the observations for which $t_{i}>t$t_i > t.