Surveys of empirical results are a much needed element of economic knowledge, informing theorists of the validity of their theoretical predictions, guiding budding empirical researchers on previous findings and helping policy-makers to assess the likely outcomes of policy options.However, whilst the best of such surveys are carried out with admirable scientific rigour, this tends to be the exception rather than the rule. When faced with a mass of empirical results -with key estimates differing in significance, magnitude and even sign -subjective judgements readily emerge, of which results to give most weight to and which to discount. Should more weight be given to the most significant results, to the most recent results, to results for the home country, to those from prestigious researchers, to those that come from large data sets or sophisticated estimation techniques, etc.?Of course, these factors may well be important and should not be ignored, but they should be allowed for in a clear objective manner, so that the reader can see which of these elements are important and even how much difference they make. MRA offers a means of objectively explaining why, and quantifying how, estimates differ from a range of empirical studies.Since 1989, MRA has become easier to apply, with computers providing increased processing power and easier access to bibliographical resources to search for and download relevant empirical research. Also, the range of economics topics to which MRA has been applied has increased dramatically. However, the techniques themselves have been developed and new issues are
INTRODUCTIONWhen economic models are estimated from time series data it is usually assumed that the specified relationship remains constant through time. The estimated parameters are used to explain behaviour during the sample period and to generate predictions. For this to be a valid procedure it is important that the structural parameters of the model should not change significantly over time. This note reports an investigation into the validity of the constancy assumption when estimating a key economic relationship, the employment function, from post war data for U.K. SIC production industries.Interest in the employment function and the stability of its structural parameters when considering a long period of data arises through observing inconsistencies that resulted from our earlier attempts to estimate sector and industry level models [4, 181. The apparent instability of the parameter estimates when new data is incorporated into the basic time series is a cause €or concern. Employment functions which model the employmentfoutput relatiomhip at various levels in an economy are now widely used in full econometric models [2, 17, 191 and also as single equation prediction models for use in manpower planning applications [lo]. Whilst most forecasters attempt to make some allowance for the impact of structural change in the prediction model, the specification of dummy variables is often a highly subjective exercise yielding uncertain results. A systematic analysis of structural breaks in an employment function, across a wide range of different industries, is likely to prove useful for many model-building exercises [5].
An atlas in the context of atlas-based segmentation refers to a pre-selected image with labelled anatomical regions of interest. Atlas-based segmentation is the propagation of these labels to a novel image after both images have been registered. The goal of an atlas is to be representative of an anatomical category, but in practice there exists variability in human anatomy. One solution to maintain consistent segmentation accuracies is to use multiple atlases, with a system for selecting the most appropriate atlas at the time of segmentation. This paper describes a method for selecting an atlas using a linear regression model to predict the segmentation accuracy based on image similarity measures. It goes further to present an offline method for automatically selecting a set of atlases, representative of the training set to be used during segmentation; all of this illustrated by segmentation of the heart and kidneys in 3D CT images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.