Download full-text


Available from: Nadine Chlaß, Jan 17, 2014
29 Reads
  • Source
    • "Besides, the variables imports, dependency ratio and population density were dropped after tests of stationary proved them to be of different order of integration. Moreover, the statistical performance of the estimates from VAR and VEC models has been well studied and well established for models with a few number of variables (Moneta et al., 2011). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Ethiopia is one of the countries with high fertility, rapidly growing and largely young population. At the same time, it is among countries with weak and poorly focused population policy. In light of this, this study intended to assess the causation between demographic factors and economic development in Ethiopia. To this end, it applied vector-error-correction model (VECM) to data on economic, demographic and other variables obtained from secondary sources, accompanied by descriptive analysis of the relationship of population with HDI, agricultural landholdings and forestland. VECM results indicated robust and negative long run relationship between per capita income and population growth and a positive one between the former and growth of workers – with bidirectional causality in both cases. That is, rises in per capita income reduce the growth of (dependent) population and enhance that of workers, and vice versa. Conversely, slower growth of population or faster growth of workers raises per capita income. Short run relationships turned out to be weak and non-robust to alternative model specifications. The descriptive analysis signified inverse associations of population growth with landholding, forest coverage and HDI score. These findings point to a need for meaningful efforts to incorporate population matters into the policy arena.
    10/2012; 4(10):236-251. DOI:10.5897/JEIF12.039
  • Source
    • "The assumption that external influences e i are non-Gaussian enables unique identification of a causal ordering k(i) and connection strengths b ij without using any background knowledge on the structure [14]. This feature is a big advantage [14] [15] [16] over conventional Bayesian network approaches based on conditional independences and/or Gaussianity [17] [18]. Though the Gaussian approximation has been a common approach [19], real-world data could be considered more or less non-Gaussian. "
    [Show abstract] [Hide abstract]
    ABSTRACT: A very important topic in systems biology is developing statistical methods that automatically find causal relations in gene regulatory networks with no prior knowledge of causal connectivity. Many methods have been developed for time series data. However, discovery methods based on steady-state data are often necessary and preferable since obtaining time series data can be more expensive and/or infeasible for many biological systems. A conventional approach is causal Bayesian networks. However, estimation of Bayesian networks is ill-posed. In many cases it cannot uniquely identify the underlying causal network and only gives a large class of equivalent causal networks that cannot be distinguished between based on the data distribution. We propose a new discovery algorithm for uniquely identifying the underlying causal network of genes. To the best of our knowledge, the proposed method is the first algorithm for learning gene networks based on a fully identifiable causal model called LiNGAM. We here compare our algorithm with competing algorithms using artificially-generated data, although it is definitely better to test it based on real microarray gene expression data.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Causal structure learning from time series data is a major scientific challenge. Existing algorithms assume that measurements occur sufficiently quickly; more precisely, they assume that the system and measurement timescales are approximately equal. In many scientific domains, however, measurements occur at a significantly slower rate than the underlying system changes. Moreover, the size of the mismatch between timescales is often unknown. This paper provides three distinct causal structure learning algorithms, all of which discover all dynamic graphs that could explain the observed measurement data as arising from undersampling at some rate. That is, these algorithms all learn causal structure without assuming any particular relation between the measurement and system timescales; they are thus ``rate-agnostic.’’ We apply these algorithms to data from simulations. The results provide insight into the challenge of undersampling.
    The Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS), Montréal CANADA; 12/2015