Backwards Stepwise Binary Logistic Regression for Determination Population Growth Rate Factor in Java Island

Abstract

The high population growth rate can impact various fields due to several factors. Some of the impacts of this high rate are high poverty rates, unemployment, consumption levels, inequality in education figures, gender empowerment index, and increasingly narrow land or area. Therefore, research on the rate of population growth using data on poverty, unemployment, consumption levels, education rates, gender empowerment index, and area makes sense. This data was taken from the official website of the Central Statistics Agency for six provinces on the island of Java, Indonesia. The data used contains missing data so that the missing data is presumed by using the k-nearest neighbour method. The estimated missing data values were modelled using binary logistic regression. Variables that significantly affect the rate of population growth, namely the level of consumption, gender empowerment index, and area, are obtained using the backward stepwise method and are selected based on the smallest Aikakes criterion information value or the one with the most excellent accuracy rate.

Prevalence and risk factors of depression in patients with chronic obstructive airway disease: a tertiary care hospital, outpatient setting

“…A univariate logistic regression analysis was used to calculate the p value and unadjusted odds ratio for the studied variables. Factors were input into the multiple logistic regression analysis using the backward method to provide the best model [ 24 ]. The factors remaining in the predictive model were those with a p of less than 0.20.…”

Síndrome de Burnout en odontólogos de Centros de Salud de Acapulco, México

“…El SB fue operacionalizado en una variable dicotómica a partir del punto de corte, por lo que se aplicó una regresión logística binaria que estableció la relación entre la variable dependiente (SB severo) y los demás factores, a través de un modelo explicativo con la razón de momios y su intervalo de confianza del 95% como estimadores 17 . El modelo inicial permitió conocer la influencia de los factores sobre el SB severo, y se eliminaron en cada paso variables con las asociaciones más débiles, mediante el método backward , hasta quedar aquellas con nivel de significancia p < 0,05 en el modelo final 18 .…”

Effect of extrusion parameters on physical, microstructural and functional quality of lentil-quinoa extruded snack enriched with pumpkin by stepwise response surface methodology

“…The stepwise regression method is a combination of forward selection and backward elimination. Stepwise regression uses to overcome the multicollinearity problem [14,15]. In other words, stepwise regression models included only significant coefficients and variables (P < 0.05), and this method provides one of the most effective predictive models [16].…”