Article
Refine
Year of publication
- 2020 (124) (remove)
Document Type
- Article (124) (remove)
Language
- English (93)
- German (30)
- Multiple languages (1)
Keywords
- Adaptive control (1)
- Anwendungsorientierter Forschungsansatz (1)
- Biofuel (1)
- Biorefinery (1)
- Brownian Pillow (1)
- Butanol (1)
- Clostridium acetobutylicum (1)
- Crámer–von-Mises distance (1)
- Design Science Research (1)
- E-Learning (1)
- Enhanced Telecom Operations Map (1)
- Experimental validation (1)
- Hoeffding-Blum-Kiefer-Rosenblatt independence test (1)
- INODIS (1)
- Incomplete data (1)
- Iterative learning control (1)
- Lignocellulose (1)
- Literaturanalyse (1)
- Literaturrecherche (1)
- MILP (1)
Institute
- Fachbereich Medizintechnik und Technomathematik (40)
- IfB - Institut für Bioengineering (26)
- Fachbereich Luft- und Raumfahrttechnik (19)
- Fachbereich Energietechnik (13)
- Fachbereich Wirtschaftswissenschaften (13)
- Fachbereich Chemie und Biotechnologie (10)
- Fachbereich Elektrotechnik und Informationstechnik (10)
- Fachbereich Bauingenieurwesen (9)
- Fachbereich Maschinenbau und Mechatronik (9)
- INB - Institut für Nano- und Biotechnologien (9)
- ECSM European Center for Sustainable Mobility (8)
- Institut fuer Angewandte Polymerchemie (4)
- Nowum-Energy (4)
- Solar-Institut Jülich (4)
- IBB - Institut für Baustoffe und Baukonstruktionen (2)
- MASKOR Institut für Mobile Autonome Systeme und Kognitive Robotik (2)
- Arbeitsstelle fuer Hochschuldidaktik und Studienberatung (1)
- Fachbereich Architektur (1)
- ZHQ - Bereich Hochschuldidaktik und Evaluation (1)
We discuss the testing problem of homogeneity of the marginal distributions of a continuous bivariate distribution based on a paired sample with possibly missing components (missing completely at random). Applying the well-known two-sample Crámer–von-Mises distance to the remaining data, we determine the limiting null distribution of our test statistic in this situation. It is seen that a new resampling approach is appropriate for the approximation of the unknown null distribution. We prove that the resulting test asymptotically reaches the significance level and is consistent. Properties of the test under local alternatives are pointed out as well. Simulations investigate the quality of the approximation and the power of the new approach in the finite sample case. As an illustration we apply the test to real data sets.