Let (X(t), t ≥ −1) and (Y (t), t ≥ 0) be stochastic processes satisfying dX(t) = aX(t)dt + bX(t − 1)dt + dW (t) and dY (t) = X(t)dt + dV (t), respectively. Here (W (t), t ≥ 0) and (V (t), t ≥ 0) are independent standard Wiener processes and ϑ = (a, b) is assumed to be an unknown parameter from some subset Θ of R 2. The aim here is to estimate the parameter ϑ based on continuous observation of (Y (t), t ≥ 0). Sequential estimation plans for ϑ with preassigned mean square accuracy ε are constructed using the so-called correlation method. The limit behaviour of the duration of the estimation procedure is studied if ε tends to zero.