Consistent Non-parametric Estimation for a One-dimensional Line Segment Process Observed in an Interval

摘要: A line segment process on the is observed through a finite window (0, x). This means that data consists of segments are non-empty intersections with window. The EM-algorithm used to construct NPMLE t) distribution function length segments. Furthermore provides self-consistency equations. unique and consistent. Consistency proved by generalizing method Jewell (1982), which can be in other models. approach based convexity arguments. Some applications, another estimator an extension two-dimensional will discussed.