Search results for "regression"
showing 10 items of 2619 documents
Bayesian Analysis of Population Health Data
2021
The analysis of population-wide datasets can provide insight on the health status of large populations so that public health officials can make data-driven decisions. The analysis of such datasets often requires highly parameterized models with different types of fixed and random effects to account for risk factors, spatial and temporal variations, multilevel effects and other sources on uncertainty. To illustrate the potential of Bayesian hierarchical models, a dataset of about 500,000 inhabitants released by the Polish National Health Fund containing information about ischemic stroke incidence for a 2-year period is analyzed using different types of models. Spatial logistic regression and…
Design Of Experiments for the optimization the process parameters of thixotropic aluminum alloy
2006
The success of the thixoforming process depends on the possibility to confer to material, when it is found in the semisolid state, a microstructure characterized by globular particles of solid phase surrounded by a continuous film of liquid phase; such microstructure is obtainable through particular thermo-mechanical treatments. In the present research, in order to optimize the influence of process parameters in the step in which the thixotropic properties are conferred to the AA7075 aluminum alloy, the statistic technique of the Design Of Experiments (DOE) has been used. The advantages in the application of such technique are expressible in terms of reduction the times of development of pr…
When cooler heads prevail: peacemakers in a sports riot.
1999
Male sports fans (N = 74) were asked to estimate the likelihood that they would intervene in a crowd disturbance in an attempt to stop the fighting. They also completed a battery of measures that included their attitude toward law and order, fight history, the false consensus effect, impulsivity, psychopathy, sensation seeking, anger, physical aggression and identification with their favorite team. Law and order, body mass, anger and the false consensus effect were positively related to peacemaking whereas sensation seeking was negatively related. A multiple regression analysis yielded a solution that accounted for 32.3% of the variance with anger and attitude toward law and order emerging …
Family influence on firm performance: Finnish publicly held family firm perspective
2011
The study aims at examining the effect of family influence on firm performance. An empirical focus is put on comparison of return on investment of publicly held family and non family firms in Finland. The income statement and balance sheet data of the companies covers the years 2000–2005. The study shows that families are present in 25% of the companies listed on the OMX Helsinki, Finland Stock Exchange. The data indicates that publicly held family firms create close the same value added per employee than non-family firms. According to the results, family firms are less indebted and perform slightly better than non-family firms measured by return on investment. The observations of the study…
The Election of the Big 4 Audit Firms In Mexico An Empirical Analysis (2000-2007)
2015
In this article, we present the results of an empirical study on the factors that determine the election of the Big 4 in Mexico during the period from 2000 to 2007. To this purpose, we have estimated a logistic regression model using a sample of companies listed on the Mexico Stock Exchange and its financial statements audited by an independent auditor. The results indicate that corporate features such as; the presence of controlling shareholders, the debt level, the presence of foreign investors, business size and requirement for additional services by audited companies are some of the factors determining the election of the Big 4 in Mexico.
Analysis of the Aggregate Financial Behaviour of Customers Using the Transtheoretical Model of Change
2014
Abstract The authors addressed the problem of aggregate financial behaviour of customers by using the transtheoretical model of change. Aggregate financial behaviour of customers was studied by analyzing payment cards, private pension savings and mortgage loans. The transheoretical model of change was chosen as a theoretical framework for the analysis. Conclusions are based on results of regression analysis of empirical evidence of customers’ financial behaviour relation to the given products during the time period 2001-2013 in Latvia and further logical inferences by authors, which are consistent with the chosen theoretical framework of the transtheoretical model of change
Homeward Bound FDI: Are Migrants a Bridge over Trouble Finance?
2016
Migrants can lower cross-border investment barriers, help investors by providing information about their homeland and reduce transaction costs by sharing expertise on regulations, customs and procedures. In addition to generating these well-known networking effects, migrants can also provide valuable information about local finance, thereby easing the credit constraints foreign investors faced during the 2007 financial crisis. This paper sheds new light on the underlying mechanisms through which migration may affect foreign investment in the migrant's homeland by distinguishing between the effects on FDI's intensive and extensive margins. Gravity estimates for 140 countries for the period 2…
Does Methodology Determine the Identification of Stock Split Motivations?: Evidence from Spain
2006
This study investigates the robustness of the results obtained for the possible motivations for firms listed on the Spanish stock market to execute a stock split using different methodologies. Although surveys from executives emphasize the use of stock splits as a way to increase the liquidity of shares, the empirical evidence is not conclusive. Our results, taken from the logit regression, the Kaplan-Meier method, the Cox regression and the automatic interaction detection, all support the hypotheses of signalling and optimal range.
Using the Hermite Regression Formula to Design a Neural Architecture with Automatic Learning of the “Hidden” Activation Functions
2000
The value of the output function gradient of a neural network, calculated in the training points, plays an essential role for its generalization capability. In this paper a feed forward neural architecture (αNet) that can learn the activation function of its hidden units during the training phase is presented. The automatic learning is obtained through the joint use of the Hermite regression formula and the CGD optimization algorithm with the Powell restart conditions. This technique leads to a smooth output function of αNet in the nearby of the training points, achieving an improvement of the generalization capability and the flexibility of the neural architecture. Experimental results, ob…
Tracking of Quantized Signals Based on Online Kernel Regression
2021
Kernel-based approaches have achieved noticeable success as non-parametric regression methods under the framework of stochastic optimization. However, most of the kernel-based methods in the literature are not suitable to track sequentially streamed quantized data samples from dynamic environments. This shortcoming occurs mainly for two reasons: first, their poor versatility in tracking variables that may change unpredictably over time, primarily because of their lack of flexibility when choosing a functional cost that best suits the associated regression problem; second, their indifference to the smoothness of the underlying physical signal generating those samples. This work introduces a …