Claim Missing Document
Check
Articles

Found 30 Documents
Search

PEMODELAN JUMLAH KEMATIAN AKIBAT DIFTERI DI PROVINSI JAWA TIMUR DENGAN REGRESI BINOMIAL NEGATIF DAN ZERO-INFLATED POISSON Fittriyah, Nurul; Hadi, Alfian Futuhul; Dewi, Yuliani Setia
Prosiding Seminar Matematika dan Pendidikan Matematik Vol 1 No 1 (2014): Prosiding Seminar Nasional Matematika 2014
Publisher : Prosiding Seminar Matematika dan Pendidikan Matematik

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penyakit Difteri merupakan salah satu penyakit menular yang berbahaya, karena terdapat 37 kasus kematian dari 955 kasus. Bakteri Corynebacterium diphteriae menyerang saluran pernafasan atas, racun menyebar melalui darah dan dapat menyebabkan kerusakan jaringan di  seluruh tubuh terutama jantung dan saraf. Analisis regresi yang digunakan untuk variabel  tak bebas berupa data count adalah analisis regresi Poisson, namun sering kali terjadi over dispers pada regresi Poisson. Hal ini dapa diatasi dengan menggunakan regresi Binomial  Negatif, namun sering kali overdispersi pada data cacahan dapat disebabkan oleh excesszeros dan untuk mengatasinya digunakan regresi Zero-Inflated Poisson (ZIP). Keterkaitan antara prosentase cakupan desa/kelurahan UCI, jumlah kasus gizi buruk, prosentase masyarakat miskin dan hamper miskin, prosentase rumah tangga yang berperilaku hidup bersih dan sehat, serta jumlah puskesmas dengan banyaknya kematian akibat penyakit difteri dapat didekati dengan analisis statistika yang mengkaji tentang hubungan variable tak bebas dan variable bebas, yaitu analisis regresi. Langkah-langkah dalam penelitian ini adalah, pertama melakukan kajian pustaka tentang difteri. Kedua, melakukan pengujian model regresi Poisson pada data. Ketiga, mengidentifikasi overdispersi serta excesszeros. Keempat melakukan  pengujian  model regresi Binomial Negatif dan ZIP secara saturated dan full model dengan  bantuan program R. Langkah terakhir membandingkan nilai log-likelihood dari model yang didapatkan untuk mendapatkan model terbaik. Hasil penelitian ini menunjukkan bahwa model terbaik diperoleh dari model regresi ZIP dengan nilai log-likelihood sebesar-29,29.
The Application of the Regression Method with Tree Structure on the Estimation of the Student Thesis Duration Dewi, Theresia Trias Candra; Dewi, Yuliani Setia; Pradjaningsih, Agustina
Majalah Ilmiah Matematika dan Statistika Vol 17 No 1 (2017): Majalah Ilmiah Matematika dan Statistika
Publisher : Jurusan Matematika FMIPA Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/mims.v17i1.23751

Abstract

The tree regression is one of the regresion methods that can be used to find out the influence of independent X variable to the dependent Y variable. The tree regression method analyzes data by doing step by step isolation. The prunning tree process is used in order to get the optimal tree size. Prunning tree is done based on cost complexity. This paper is written in order to apply the tree regression method in data of graduated student from Faculty of MIPA at 2001-2005 that used to find out the variable which has an influence to the long student minithesis. The research result shows that the long student minithesis is influenced by GPA and department.
Analisis Biplot Untuk Mendeskripsikan Ciri-Ciri Kecamatan-Kecamatan di Kabupaten Jember Dewi, Yuliani Setia; Andayani, Nonik
Majalah Ilmiah Matematika dan Statistika Vol 15 No 2 (2015): Majalah Ilmiah Matematika dan Statistika
Publisher : Jurusan Matematika FMIPA Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/mims.v15i2.23725

Abstract

This research aims to describe subdistricts’ characteristics in Jember districts based on society prosperity indicators by using biplot analysis. Biplot analysis is the method of analysis presenting position of n relative object of observation with p variable simultaneously in two dimensions. Biplot analysis with exploration approach through a concept of object relative distance and variable, can be made as suggestions to develop subdistricts in achieving society prosperity. From the result of biplot analysis, it can be obtained that there is a correlation of each society prosperity indicators. According to subdistrict’s characteristics, it can be known about change happened, that is if family planning programme is success for certain subdistricts in the year of 2000, so family planning programme has spread almost throughout all subdistricts in the year of 2001.
Model of Free Grading to Guess Cell Probability in Incomplete Contingency Table Dewi, Yuliani Setia
Majalah Ilmiah Matematika dan Statistika Vol 16 No 1 (2016): Majalah Ilmiah Matematika dan Statistika
Publisher : Jurusan Matematika FMIPA Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/mims.v16i1.23732

Abstract

The problem of estimating cell probabilities from incomplete tables, that is when either the row or column variable missing for some of the subjects is very common. This article describes Lattice Conditional Independence Model to estimate cell probabilities in incomplete contingency table.
Relationship of Explicitly and Implicitly Constrained Mixed Model Dewi, Yuliani Setia
Majalah Ilmiah Matematika dan Statistika Vol 17 No 1 (2017): Majalah Ilmiah Matematika dan Statistika
Publisher : Jurusan Matematika FMIPA Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/mims.v17i1.23749

Abstract

In linear models with independent observations, parameter constraints are usually handled by transforming the explicitly constrained model to implicitly constrained model, that takes the form of reduced-parameter. In this paper will be proofed that in mixed linear models (can used to analyze longitudinal data), explicitly constrained mixed model equivalent to the implicitly constrained mixed model with using general solution for linear equality constrains on the parameter.
Optimations of Product Combinations with Goal Programming Method B., Rika N.; Pradjaningsih, Agustina; Dewi, Yuliani Setia
Majalah Ilmiah Matematika dan Statistika Vol 15 No 2 (2015): Majalah Ilmiah Matematika dan Statistika
Publisher : Jurusan Matematika FMIPA Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/mims.v15i2.23723

Abstract

Goal programming is linear programming technique which is used to solve problem with some goals. This method used to minimize the undesirable deviation from some targets which want to be reached. The targets expressed in a mathematic equation called constraint function. There are two constraint functions, goal constraint function and structural constraint function. On this paper solution of the optimal product combinations problems will be finded from nata de coco packs which have purpose to minimize ripening and sale maximization.
Covariance Based approach SEM with Bollen-Stine Estimation (Case Study Analysis of The Effect of Teacher and Principal Competence on Achievement of National Standards) Kasmuri Kasmuri; I Made Tirta; Yuliani Setia Dewi
Jurnal ILMU DASAR Vol 16 No 2 (2015)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (378.054 KB) | DOI: 10.19184/jid.v16i2.899

Abstract

Applications of covariance Based SEM (CB-SEM) generally use the maximum likelihood, based upon the assumption on the normal distribution of data. One alternative that could be applied if the data were not normally distributed is estimation using  Bollen-Stine bootstrap approach. In this study, the method is applied to reveal the influence of teacher competence, the principal competence, to the value of achievement of national education standards in secondary schools in Banyuwangi.The objective of this paper was to determine and analyze the relationship and to know the  the most dominant indicators of  measure latent variables between the  the principal, teachers competences on national standards of educational attainment in secondary schools in Banyuwangi. The results  indicate that all of the indicator of variables are  valid and reliable to measure corresponding latent variables. Each latent variable has the most dominan indicator. For the principal competence  latent variables the most dominant  indicator is the entrepreneurial competence, for teachers competency the most dominant is personal competence, whereas for  national education standards, the most dominant  standard of facilities. Principal competence  has indirect influence on national education standard achievement, but directly affect the competence of teachers.  Teacher competence directly influence national education standards.Keywords: Power Competence Teachers, Competence Principal, National Education Standards,  covariance Based SEM, Bollen-Stine Bootstrap Estimates
Application of Tree Regression in Long Study of University of Jember‘s Student Use R Program Yuliani Setia Dewi
Jurnal ILMU DASAR Vol 8 No 1 (2007)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (437.66 KB)

Abstract

This research aimed to implemate tree  regression with one respon and six explanatory variables in R programand apply it to know variables which distinguish long study of University of Jember’ student. We can use “tree”function to form tree regression in R.  The result of  research shows that the rate of long study University ofJember’s Student is 1802 days. Based on structure of tree we can know that variables can used to distinguishuniversity of Jember’s students in long study are GPA, time used for doing minithesis and faculty Fromimplementation of tree regression,it is known that tree regression can identify variables locally, revealinteractions in the data set, no variable is assumed to follow any kind of statistical distribution and easy tointerpret. Keywords : tree regression, R program , tree function, long study
OLS, LASSO dan PLS Pada data Mengandung Multikolinearitas Yuliani Setia Dewi
Jurnal ILMU DASAR Vol 11 No 1 (2010)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (332.009 KB)

Abstract

Correlation between predictor variables (multicollinearity) become a problem in regression analysis. There are some methods to solve the problem and each method has its own complexity. This research aims to explore performance of OLS, LASSO and PLS on data that have correlation between predictor variables. OLS establishes model by minimizing sum square of residual. LASSO minimizes sum square of residual subject to sum of absolute coefficient less than a constant and PLS combine principal component analysis and multiple linear regression. By analyzing simulation and real data using R program, results of this research are that for data with serious multicollinearity (there are high correlations between predictor variables), LASSO tend to have lower bias average than PLS in prediction of response variable. OLS method has the greatest variance of MSEP, that is mostly not consistent in estimating the Mean Square Error Prediction (MSEP). MSEP that is resulted by using PLS is less than that by using LASSO. 
Structural Equation Modeling of the Factors Affecting the Nutritional Status of Children Under Five in Banyuwangi Region using Recursive (one-way) GSCA I Made Tirta; Nawal Ika Susanti; Yuliani Setia Dewi
Jurnal ILMU DASAR Vol 16 No 1 (2015)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1517.157 KB) | DOI: 10.19184/jid.v16i1.534

Abstract

Structural Equation Modeling is one among popular multivariate analysis, especially applied in pschology and marketing. There are two main types of Structural Equation Modeling namely covariance-based or CB-SEM and variance-based or Partial Least Square (PLS)- SEM. Both types have advantages and disadvantage. To overcome its limitation, Generalized Structured Component Analysis (GSCA) was then proposed as an extension of PLS-SEM. In estimating the parameters, GSCA uses Alternating Least Squares (ALS) and in estimating the standard error of the parameter estimates it uses the bootstrap method. In this paper, GSCA is applied to study the causality model of Infant nutritional status, in relation with socio-economic status and infantcare status in Banyuwangi Region. The results show that both socio-economic and infantcare status have significant positive influence on infant nutritional status.Keywords:  Alternating least square, generalized structural component analysis,  nutritional status of infants,  structural equation modelling