When the multi-state process is Markov, a consistent estimator of these transition probabilities is provided by the Aalen-Johansen estimator (see Aalen and Johansen
1978). For this, consider
n i.i.d. realisations
\(X_i(t)\) of
X(
t), where for subject
i we define the at risk process for state
j as
\(Y_j^{(i)}(t) = 1\{ X_i(t-) = j\}\) and the transition counting process for transition
\(j \rightarrow k \in E\) as
\(N_{jk}^{(i)}(s,t) = \sum _{u \in (s,t]} 1\{X_i(u-) = j, X_i(u) = k\}\). We assume that all transition counting processes are locally finite i.e. at most a finite number of transitions happens on bounded intervals, hence justifying the summation index for the counting process just defined. Then, the aggregated at risk process
$$\begin{aligned}&\overline{Y}_{j}(t) := \sum _{i = 1}^{n} 1\{X_i(t-) = j\} \end{aligned}$$
corresponds to the number of individuals in state
j just before time
t, and the transition counting processes
$$\begin{aligned}&\overline{N}_{jk}(t) := \sum _{i = 1}^{n} \sum _{u \in (s,t]} 1\{X_i(u-) = j, X_i(u) = k\}, \end{aligned}$$
corresponds to the number of transitions directly from state
j to state
k in the interval (
s,
t]. Let
\(\overline{\mathbf {Y}}(t) := (\overline{Y}_{1}(t), \ldots , \overline{Y}_{K}(t))\) and
\(\overline{Y}_{\bullet }(t) = \sum _{j=1}^K \overline{Y}_j(t)\) be the total number of subjects at risk at time
t. For
\(J_{j}(t) := 1\{\overline{Y}_j(t) > 0\}\) let
$$\begin{aligned} \widehat{{\varLambda }}_{jk}(t) := \int _{s}^{t} \frac{J_{j}(u) \mathrm {d}\overline{N}_{jk}(u)}{\overline{Y}_{j}(u)} \end{aligned}$$
(2)
be the Nelson-Aalen estimator of the transition rates and
\(\widehat{{\varvec{{\Lambda }}}}(t)\) a
\(K \times K\) matrix with (
j,
k)th element (
\(j \ne k\)) equal to
\(\widehat{{\varLambda }}_{jk}(t)\) and diagonal elements
\(\widehat{{\varLambda }}_{jj}(t) = - \sum _{k \not = j} \widehat{{\varLambda }}_{jk}(t)\). The Aalen-Johansen (AJ) estimator of the transition probability matrix
\(\mathbf {P}(s, t)\), with elements
\(P_{jk}(s,t)\), is then given by
$$\begin{aligned} \widehat{\mathbf {P}}^{\text {AJ}}(s,t)&:= \prod _{u \in (s,t]} \left( \mathbf {I} + \varDelta \widehat{{\varvec{{\Lambda }}}}(u) \right) \end{aligned}$$
where the product is ordered according to the time ordering and consist of a finite number of terms due to the locally finite behaviour of the counting processes. Estimated state occupation probabilities at time
t may be obtained by
$$\begin{aligned} \widehat{{\pi }}^{\text {AJ}}(t) = \widehat{{\pi }}(0) \widehat{\mathbf {P}}^{\text {AJ}}(0,t), \end{aligned}$$
(3)
where
\(\widehat{{\pi }}(0)\) is the row vector of empirical state occupation probabilities at
\(t=0\), given by
\(\widehat{\pi }_j(0) := \overline{Y}_j(0+) / \overline{Y}_{\bullet }(0+)\). Here, the
\(+\) in
\((t+)\) means that the numbers observed to be in state
j at time
t, rather than just before time
t are to be taken. Datta and Satten (
2001) argued that the estimated state occupation probabilities in (
3) are consistent, even if the multi-state model is non-Markov. The Aalen-Johansen (AJ) estimator of the transition probabilities
\(\mathbf {P}_l(s, t)\) from (
1) is then given by
$$\begin{aligned} \widehat{\mathbf {P}}_{l}^{\text {AJ}}(s,t)&:= e_{l} \prod _{u \in (s,t]} \left( \mathbf {I} + \varDelta \widehat{{\varvec{{\Lambda }}}}(u) \right) , \end{aligned}$$
where
\(e_{l}\) is a vector with the
lth element equal to 1, and all other elements 0.