İktisadi ve İdari Bilimler Fakültesi / Faculty of Economics and Administrative Sciences

Permanent URI for this collectionhttps://hdl.handle.net/11727/1399

Browse

Filters

2021 - 20232

Settings

Author: search.filters.author.Farnoudkia, Hajarsearch.filters.applied.f.rights: search.filters.rights.info:eu-repo/semantics/openAccess

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Malmquist Index Evaluation of Countries: 2000-2019
    (2023) Farnoudkia, Hajar
    One of the sophisticated mathematical techniques for evaluating the relative efficiency of decision-making units (DMUs) in a multi-inputs-output setting is data envelopment analysis. A non-parametric productivity index called the Malmquist index (MI) tracks changes in a DMU's overall factor output over time. This study seeks to present a broad overview of the changes in the MI for nearly all of the world's nations over 19 years beginning in 3061. This research evaluates a time series data set made up of 16 economic indexes. Each nation's MI, which compares 2000 and 2019, shows how each nation has changed over that period. One of the most important purposes of this study comparing the countries by their MI is that it allows for a fair comparison of productivity across different time periods and regions. It also provides insights into the sources of productivity growth, such as changes in technology or improvements in efficiency. As a result, the countries can allocate resources more wisely and develop more effective investment plans by understanding the elements that lead to productivity increase. By implementing some statistical techniques, nations are further divided into four categories based on their MI. Furthermore, a yearly distribution of the MI has been included to illustrate its trends between the years 2000 to 2019. Finally, the changing flow for some countries of each category is shown in three-year tracks.
  • No Thumbnail Available
    Item
    Vine copula graphical models in the construction of biological networks
    (2021) Farnoudkia, Hajar; Purutcuoglu, Vilda
    The copula Gaussian graphical model (CGGM) is one of the major mathematical models for high dimensional biological networks which provides a graphical representation, espe-cially, for sparse networks. Basically, this model uses a regression of the Gaussian graphical model (GGM) whose precision matrix describes the conditional dependence between the variables to estimate the coefficients of the linear regression model. The Bayesian inference for the model parameters is used to overcome the dimensional limitation of GGM under sparse networks and small sample sizes. But from the application in bench-mark data sets, it is seen that although CGGM is successful in certain systems, it may not fit well for non-normal multivariate observations. In this study, we propose the vine copulas to relax the strict normality assumption of CGGM and to describe networks from a variety of copulas alternates besides the Gaussian copula. Accordingly, we evaluate the best fitted bivariate copula distribution for every pairwise gene and compute the estimated adjacency matrix which denotes the presence of an edge between the corresponding genes. We assess the performance of our proposed approach in three network data via distinct accuracy measures by comparing the outputs with the results of the CGGM.