Browsing by Subject "Maximum likelihood"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Publication
    International interest-rate risk premia in affine term structure models
    (2009) Geiger, Felix
    I estimate a Gaussian two-factor affine term structure model of bond yields for three countries, the United States, the United Kingdom and Germany. I find a considerable time-varying component of excess returns in the data. They are positively correlated with the slope of the term structure and negatively with the short-term policy rate. In addition, the panel clearly indicates to co-movements in the same directions on an international level. When testing the estimated model for the expectations puzzle of the the term structure, at least at one end of the yield curve, this puzzle can be resolved when applying risk-adjusted yield changes.
  • Thumbnail Image
    Publication
    A REML method for the evidence‐splitting model in network meta‐analysis
    (2023) Piepho, Hans‐Peter; Forkman, Johannes; Malik, Waqas Ahmed
    Checking for possible inconsistency between direct and indirect evidence is an important task in network meta‐analysis. Recently, an evidence‐splitting (ES) model has been proposed, that allows separating direct and indirect evidence in a network and hence assessing inconsistency. A salient feature of this model is that the variance for heterogeneity appears in both the mean and the variance structure. Thus, full maximum likelihood (ML) has been proposed for estimating the parameters of this model. Maximum likelihood is known to yield biased variance component estimates in linear mixed models, and this problem is expected to also affect the ES model. The purpose of the present paper, therefore, is to propose a method based on residual (or restricted) maximum likelihood (REML). Our simulation shows that this new method is quite competitive to methods based on full ML in terms of bias and mean squared error. In addition, some limitations of the ES model are discussed. While this model splits direct and indirect evidence, it is not a plausible model for the cause of inconsistency.
  • Thumbnail Image
    Publication
    Towards regionalisation of soils in Northern Thailand and consequences for mapping approaches and upscaling procedures
    (2008) Schuler, Ulrich
    The purpose of this study was to identify the key factors of soil formation and distribution in North-western Thailand in order to enable predictive mapping. Further objectives were to investigate different soil mapping approaches, regarding their suitability for specific areas and scales and to assess the potential of local (soil) knowledge for soil mapping and land use planning. In order to cover the essential petrographic inventory of North-western Thailand three different petrographic areas were selected. The investigated topics were petrographic diversity, spatial organisation of soils and variability of their physical and chemical properties, as well as local soil knowledge of farmers in the respective areas. In addition thematic maps were generated comprising geology, WRB soil groups, and different soil properties. Soil mapping was carried out by using four different methods, the intensive mapping approach, maximum likelihood method, randomised grid cell approach, as well as elicitation of local knowledge. The intensive mapping approach comprised transect investigations, investigation points of the randomised grid cell approach, and additional investigation points, which were selected for areas with increased soil and petrographic variability. All maps based on the intensive mapping approach contained the highest sampling point density and maximum amount of information. These maps were used as a reference for the other mapping approaches applied here.