Imandani, Dita Kirana (2024) Pemodelan Faktor-Faktor yang Mempengaruhi Jumlah Kematian Ibu dan Bayi di Provinsi Jawa Timur Menggunakan Bivariate Generalized Poisson Regression. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5003201094-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5003201094-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy |
Abstract
Salah satu jenis analisis regresi non-linear ketika variabel respons mengikuti distribusi Poisson adalah regresi Poisson. Regresi Poisson univariat merujuk pada pemodelan regresi Poisson ketika hanya ada satu variabel respon, sedangkan regresi Poisson bivariat merujuk pada pemodelan regresi Poisson ketika ada dua variabel respon. Kesamaan antara rata-rata dan varians atau equidispersi merupakan salah satu asumsi khusus dari model regresi Poisson, yang mencakup regresi Poisson univariat dan bivariat. Apabila asumsi ini tidak terpenuhi akan menghasilkan kesimpulan yang tidak valid. Jika nilai varians (overdispersi) lebih besar dari nilai rata-rata, maka telah terjadi pelanggaran asumsi. Penerapan regresi Poisson bivariat pada data yang mengalami overdispersi dikenal sebagai Bivariate Generalized Poisson Regression. Estimasi parameter global dihasilkan oleh pemodelan ini untuk seluruh lokasi (daerah). Berdasarkan hasil analisis Bivariate Generalized Poisson Regression dengan kriteria AICc diketahui bahwa model terbaik memuat keseluruhan variabel prediktor. Faktor yang mempengaruhi jumlah kematian ibu di Jawa Timur tahun 2022 adalah pelayanan kunjungan ibu hamil dengan K4 dan Ibu mendapat tablet tambah darah. Sedangkan untuk pemodelan jumlah kematian bayi diperoleh empat variabel yang berpengaruh secara signifikan adalah persentase persalinan di Fasyankes,persentase pelayanan kunjungan ibu hamil dengan K4 serta persentase Ibu mendapat tablet tambah darah.
============================================================
One type of non-linear regression analysis when variable responses follow the distribution of poisson is the regression poisson. Regression univariat refers to regression poisson modeling when there is only one response, while regression poisson bivariates to regression modeling when there are two responses. Similarities between the average and the variance or equiare one of the special assumptions of the regression model poisson, which includes the regression poisson univariat and bivariat. If this assumption is not fulfilled it will result in an invalid conclusion. If a value variances greater than an average, there is a breach of assumption. Regression application of the poisson bivariate on data known as the genervariate poisson regression. Estimates of global parameters are generated by this modeling for the entire site (region). Based on the results of a generalized bivariate poisson regression analysis with the aicc criteria it is known that the best model contains a whole predictor variable. The factor that affects the number of maternal deaths in East Java in 2022 is the visit service for pregnant women with K4 and mothers get blood supplement tablets. As for modeling the number of infant deaths, four variables were obtained that had a significant effect, namely the percentage of childbirth at the Health Facility, the percentage of visiting services for pregnant women with K4 and the percentage of mothers receiving blood tablets.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | AICc,Bivariate Generalized Poisson, Maximum Likelihood Estimation, Maximum Likelihood Ratio Test, Overdispersion, AICc,Biivariate Generalized Poisson,Maximum Likelihood Estimation, Maximum Likelihood Ratio Test, Overdispersion |
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Dita Kirana Imandani |
| Date Deposited: | 08 Aug 2024 09:00 |
| Last Modified: | 08 Aug 2024 09:00 |
| URI: | http://repository.its.ac.id/id/eprint/114748 |
Actions (login required)
 |
View Item |