Indeks Pembagunan Manusia (IPM) mer

Indeks Pembagunan Manusia (IPM) merupakan suatu indeks komposit yang mencakup tiga dimensi pokok pembangunan manusia yang dinilai mencerminkan status kemampuan dasar penduduk yaitu kesehatan, pencapaian pendidikan, dan daya beli masyarakat. Pada penelitian ini IPM dikategorikan/diklasifikasikan menjadi dua, yaitu menengah rendah dan menengah tinggi. Secara data didapati bahwa terdapat kemiripan nilai IPM antar wilayah yang berdekatan secara geografis yang mengakibatkan klasifikasi IPM wilayah yang berdekatan tersebut sama. Hal ini diduga karena adanya dependensi/keterkaitan hubungan antar wilayah. Dari penjabaran di atas, maka data IPM dalam penelitian ini didasarkan pada metode regresi probit spasial. Penelitian ini bertujuan mengkaji penaksir parameter yang diaplikasikan pada data klasifikasi IPM di Pulau Jawa dan memodelkan faktor-faktor yang mempengaruhi klasifikasi IPM di pulau Jawa serta menentukan model terbaik dengan menggunakan model regresi probit spasial autoregressive. Pemilihan variabel dilakukan secara backward elimination, sedangkan estimasi parameter dilakukan menggunakan metode MCMC Gibbs sampler dengan pendekatan Bayesian. Menggunakan delapan variabel prediktor, dua variabel diantaranya yaitu variabel persentase penduduk miskin dan rata-rata umur kawin pertama wanita dinyatakan signifikan secara statistik untuk dimasukkan ke dalam model.

Hasil (Inggris) 1:

human pembagunan index (HDI) is a composite index that includes three basic dimensions of human development is considered to reflect the status of the health of the population's basic skills, educational attainment, and purchasing power. in this study ipm categorized / classified into two, namely the low medium and medium high.the data is found that there are similarities between the HDI value of geographically adjacent regions which resulted in the classification of the adjacent ipm same region. it is suspected because of the dependencies / inter-regional linkages. from the translation of the above, then the data ipm in this study are based on the spatial probit regression method.This study aims to assess the parameter estimator is applied to data classification ipm on the island of Java and modeling the factors that affect classification ipm in Java as well as determine the best model using spatial autoregressive probit regression model. election conducted backward elimination variable,whereas the parameter estimation is done using the mcmc gibbs sampler with Bayesian approach. using eight predictor variables, two variables are variables such as the percentage of poor and average first marriage age of women was statistically significant for inclusion in the model.

Hasil (Inggris) 2:

The Human Development Index (HDI) is a composite index that includes three basic dimensions of human development are assessed reflect the status of the basic capabilities of the population, namely health, educational achievement, and purchasing power. On the research of the HDI classified/classified into two, namely low and medium medium high. The data found that there were similarities between the HDI values of adjacent territories, geographically, which resulted in an adjacent region of HDI classification is the same. This is allegedly due to dependencies/relationship of interdependence between regions. From the above discussion, the HDI data in this study is based on a spatial probit regression method. This study aims at assessing the parameters estimator applied to the HDI classification data in Java and model the factors that affect the classification of the HDI in Java as well as determine the best model by using spatial autoregressive probit regression models. The selection of variables was conducted in backward elimination, While parameter estimation is performed using MCMC methods of Gibbs sampler with a Bayesian approach. Use the predictor variables are eight, among which two variables a variable percentage of poor people and the average age of first marriage for women is revealed statistically significant to be included in the model.