Andere Kunden interessierten sich auch für
![Estimation of Hedonic Regression Models with Missing Observations]( "Estimation of Hedonic Regression Models with Missing Observations")
Estimation of Hedonic Regression Models with Missing Observations40,99 €![A Novel Statistical Model for Poverty Estimation]( "A Novel Statistical Model for Poverty Estimation")
A Novel Statistical Model for Poverty Estimation32,99 €![Some Methods of Robust Regression Model]( "Some Methods of Robust Regression Model")
Some Methods of Robust Regression Model23,99 €![Least Absolute Deviation Regression Theory and Methods]( "Least Absolute Deviation Regression Theory and Methods")
Least Absolute Deviation Regression Theory and Methods32,99 €![Parameter Estimation for PDEs using Stochastic Methods]( "Parameter Estimation for PDEs using Stochastic Methods")
Parameter Estimation for PDEs using Stochastic Methods40,99 €![Robust Random Regression Imputation for Missing Data]( "Robust Random Regression Imputation for Missing Data")
Robust Random Regression Imputation for Missing Data46,99 €![A Semi-Parametric Copula Estimation under Censoring]( "A Semi-Parametric Copula Estimation under Censoring")
A Semi-Parametric Copula Estimation under Censoring44,99 €
This research paper exhibits different methods in estimating poverty incidence in the barangay level. It focused on using the multiple linear, Poisson, and the negative binomial regression models. Estimates obtained were ranked according to barangays with highest poverty incidence. The data that was used was the 2009 CBMS Marinduque data, this was the latest and complete data of Marinduque from the Community-Based Monitoring System. Significant correlates were obtained by using the chi-square test of independence and showed that the use of solar electricity, electric battery, and other sources of energy is not significant thus removed from the data. To ensure that multicollinearity would not be present in the data, the Principal Component Analysis was used to reduce the predictor variables. Both the original significant predictor variables and the reduced variables were used to model the data for comparison. Among all the models acquired, multiple linear and negative binomial with parameter equal to one regression models were used to compare with the actual poverty proportions. Poisson regression model was not used for the goodness-of-fit test showed that the model is overdispersed