Search Results

You are looking at 1 - 10 of 671 items for :

  • "regression analysis" x
  • Refine by Access: All Content x
Clear All

Abstract  

A new method of calculation of parameters of enthalpy relaxation models is proposed. Regression analysis treatment compares the experimental and calculated values of relaxation enthalpy. The experimental values of relaxation enthalpy are obtained by numerical integration of the difference between the two DSC curves. Contrary to the overall shape of the DSC curve the integral values are not affected by particular heat flow conditions during the DSC experiment. The Narayanaswamy's numerical model based on the Kohlrausch—William—Watts relaxation function was used to calculate the theoretical values of relaxation enthalpy. The application of the proposed method on the DSC experimental data of enthalpy relaxation of As2Se3 is shown.

Restricted access
Journal of Thermal Analysis and Calorimetry
Authors: Mihaela-Ligia Ungureşan, Andrada Măicăneanu, Francisc-Vasile Dulf, Eva-Henrietta Dulf, and Delia Maria Gligor

, modifications to a number of similar phenomena such as ion exclusion and ligand exchange [ 9 ]. Linear regression analysis has been the most commonly used technique to evaluate the fit of experimental data and isotherm models for ion exchange on natural

Restricted access

Perception of tax evasion by individual citizens is of considerable interest to politicians, since people’s perceived attitudes affect the approach to tax compliance throughout the society. It is thus worth identifying personal characteristics that are related to a higher degree of tolerance and justification for tax evasion. Based on the 2008 European Values Survey data and using descriptive statistics, the paper discusses the relationship between the respondents’ characteristics and their tendency to justify tax evasion. The study finds a strong relationship between this tendency and age, educational attainment and economic activity, the two other variables (parenthood and income) indicating only a weak relationship. Moreover, the current issue allows us to convincingly argue against the regression analysis stereotypes which often yield biased and confl icting results. The paper confirms our constructive criticism, thus opening up space for an extended discussion of a more balanced use of both descriptive statistics and regression models.

Restricted access
Cereal Research Communications
Authors: S. Gupta, R. Yadav, K.B. Gaikwad, A. Arora, A. Kumar, A. Kushwah, and N.K. Bainsla

Physiological breeding complementing the conventional approach is increasingly being explored in wheat in view of stagnating annual genetic yield gain. Designing improved plant types required knowledge about physiological traits associated with yield gain in the past. Fourteen wheat varieties including 12 historically important and popular (mega) wheat cultivars and two recently registered varieties were observed for various physiological traits for two years. Both breeding period and genotypes within breeding period accounted for significant differences for most of the physiological traits. Regression analysis indicated curvilinear trend for leaf area index (LAI), flag leaf area, and root length and root weight. Near perfect leaf area index (LAI 5.94) with semi-erect leaves and higher flag leaf area was observed in all time mega variety HD 2967 indicated the importance of plant architecture and crop canopy in yield maximization. Linear declining trend was observed for coleoptile length, number of stomata per cm2 and flag leaf length. Increasing trend for total chlorophyll content and normalized difference for vegetative indices (NDVI) at both vegetative and flowering stage indicated the importance of leaf greenness in yield improvement. Root length has continuously declined except for the latest released varieties, however no such trend was observed for root weight. We propose that grain yield stabilization at still higher level can be achieved by increasing photosynthetic capacity, optimizing the crop canopy slightly less than the optimum, and better partitioning to grain yield through directed physiological based breeding.

Restricted access

Abstract  

This study aims to investigate whether known carcinogenic chemical elements in atmospheric deposition might be associated with child mortality due to leukemia in the Portuguese population. A Bayesian hierarchical model was used to explore the association between lichen biomonitoring measurements of four elements—As, Hg, Ni, Pb—and childhood leukemia death counts taken at small administrative units. This geographical epidemiological study found a non-significant positive association between the risk of childhood leukemia and levels of arsenic, mercury and lead, and a non-significant negative association between the disease and the level of nickel. Lead seems to show a weaker association with childhood leukemia than arsenic and mercury.

Restricted access

This investigation is one of the first to adopt quantile regression (QR) technique to examine covariance risk dynamics in international stock markets. Feasibility of the proposed model is demonstrated in G7 stock markets. Additionally, two conventional random-coefficient frameworks, including time-varying betas derived from GARCH models and state-varying betas implied by Markov-switching models, are employed and subjected to comparative analysis. The empirical findings of this work are consistent with the following notions. First, the beta smile (beta skew) curve for the Italian, U.S. and U.K. (Canadian, French and German) markets. That is, covariance risk among global stock markets in extremely bull and/or bear market states is significantly higher than in stable periods. Additionally, the Japanese market provides a special case, and its beta estimate at extremely bust state is significantly lower, not higher than that at the middle region. Second, the quantile-varying betas are identified as possessing two key advantages. Specifically, the comparison of the system with quantile-varying betas against that with time-varying betas implied by GARCH models provides meaningful implications for correlation-volatility relationship among international stock markets. Furthermore, the quantile-varying beta design in this study relaxes a simple dual beta setting implied by Markov-switching models of Ramchand — Susmel (1998) and can identify dynamics of asymmetry in betas.

Restricted access

separately involved into the regression analysis with the groundwater level (GW2) and the water level of the Danube (DWL). The results can be seen in Figs  6 – 9 . Figure  6 shows the north tilt of the stable part of the high bank. It can be seen that when

Open access

The Micro-Deval test method is used for testing of aggregate durability. The present paper focuses on two Hungarian andesites obtained from the quarries of Recsk (Mátra Mountains, Hungary) and of Nógrádkövesd (Cserhát Mountains, Hungary). The aim of this study is to find a simple test method based on the original Micro-Deval test method to assess the long-term durability of aggregates. An additional part of the research was to develop suitable mathematical models that can describe the behavior of the andesite aggregates under continuous abrasive impact. The relevant standard (EN 1097-1:2012) recommends 12,000 rotations to determine the Micro-Deval coefficient required for classification of the aggregates. Within the framework of this research, a modified Micro-Deval test was applied: the number of rotations was increased in several steps and the degree of abrasion was measured afterwards. Regression analyses were used to outline mathematical forms which characterize the dependence between the number of rotations and the degree of abrasion. According to the results, the long-term Micro-Deval tests significantly modify the assessed durability and thus provide information on the long-term abrasive impact. The degree of change depends on the studied material: the ratio of the long-term Micro-Deval coefficients of the two studied andesite types is larger than 3. The regression analyses of the measured Micro-Deval coefficients revealed that quadratic curves are suitable to describe these tendencies for both andesite aggregates.

Open access

The investigations presented in this paper were aimed at empirical definition  of ground motion under Vrancea earthquakes.  They were based on the recorded accelerogrammes from the occurred strong Vrancea earthquakes of 1977, 1986 and 1990 obtained from the accelerographs installed in the territory of former Yugoslavia, Romania and Bulgaria. A methodological approach to empirical prediction of ground motion parameters under strong earthquake effects was developed and empirical attenuation laws of horizontal peak ground acceleration (PGA) were defined.  A new empirical mathematical model was applied. In this model the amplitudes of strong ground motion are in function of earthquake magnitude, epicentral distance, focal depth, azimuth of the instrument location in respect to  the radiation pattern and the ratio between the semi-axes of the seismic field  ellipse. Through the so called non-homogeneity function of the region, the model indirectly involves the effect of the focal mechanism and the non-homogeneity of the region through which the seismic waves propagate.  The mathematical model applied in these investigations contributed to the  empirical definition of the attenuation laws that play an important role in seismic  hazard analyses and hence in evaluation of the seismic hazard a country or a  region is exposed to.  The results obtained from these investigations are important not only for   Macedonia but for the entire Balkan region and beyond.  The presented methodology and the applied mathematical model of functional relationships are of a particular importance since they are different from the empirical models of strong ground motion that have so far been applied in the world.

Restricted access

The aim of this study is to shed some light on the factors determining the investment decisions of Sovereign Wealth Funds. Using the financial data from companies listed on the Warsaw Stock Exchange, the author employs a logit model to analyse the probability that firms are targeted for investment by the Norwegian Sovereign Wealth Fund. These findings suggest that not only the growth of earnings per share increases the probability of such investment, but that also a company whose shares have been bought by the Government Pension Fund Global has, on average, a higher level of earnings per share than companies not targeted by the Fund. This study contributes to a deeper understanding of the investment activities of the world’s largest Sovereign Wealth Fund.

Restricted access