Articles

Found 33 Documents
Search

Interval Konfidensi Serempak Bagi Rataan Respons Dengan Metode Bootstrap Persentil pada Regresi Linier Sederhana Fauzy, Akhmad
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 2, No 2 (2002)
Publisher : Program Studi Statistika Unisba

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

Abstract

Seringkali kita ingin membuat interval konfidensi bagi rataan respons pada beberapa nilai X daridata sampel yang sama. Cara yang sering digunakan dalam mengestimasi E{Yh} pada berbagai nilaiXh adalah menghitung nilai tersebut sendiri-sendiri dan ternyata mempunyai kelemahan. Hal inidisebabkan keduanya berasal dari data sampel yang sama. Bonferroni telah mencoba membuatinterval konfidensi serempak bagi nilai tersebut. Metode ini ternyata juga mempunyai kelemahan,karena data yang diperoleh membutuhkan asumsi kenormalan. Tulisan ini akan menggunakanmetode lain, yaitu metode Bootstrap persentil. Akan ditunjukkan bahwa metode bootstrap persentilmenghasilkan interval konfidensi serempak yang lebih baik apabila dibandingkan dengan metodeBonferroni.
INTERVAL ESTIMATION FOR TWO PARAMETERS EXPONENTIAL DISTRIBUTION UNDER MULTIPLE TYPE-II CENCORING ON SIMPLE CASE WITH BOOTSTRAP PERCENTILE Fauzy, Akhmad; Ibrahim, Noor Akma; Daud, Isa; Abu Bakar, Mohd Rizam
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 3, No 1 (2003)
Publisher : Program Studi Statistika Unisba

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

Abstract

In the article, two methods are proposed to give the interval estimation for twoparameters exponential distribution under multiple type-II cencoring on simple case. Balakrishnan(1990) use approximate maximum likehood estimator to construct interval estimation. All of thesemethod need an assumtion that sample is exounentially distributed. Method give shorter intervalthan the traditional method and this method does not need an assumtion that the sample isdistributed exponentially
Metode Bootstrap Persentil Pada Sensor Tipe II Berdistribusi Eksponensial Fauzy, Akhmad
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 7, No 1 (2007)
Publisher : Program Studi Statistika Unisba

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

Abstract

Metode bootstrap adalah suatu metode berbasis komputer yang sangat berpotensi pada masalahketakstabilan dan keakurasian, khususnya dalam menentukan selang kepercayaan. Selang yangsering dicari pada sensor tipe II berdistribusi eksponensial adalah selang bagi parameter, fungsitahan hidup dan kuantil tahan hidup. Rumus yang digunakan memerlukan distribusi χ2 dan F.Dengan metode bootstrap persentil akan lebih baik, kerana selang yang dihasilkan lebih pendek dantidak memerlukan bantuan distribusi
Selang Kepercayaan dari Parameter Distribusi Log-Normal Menggunakan Metode Bootstrap Persentil Fauzy, Akhmad
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 8, No 1 (2008)
Publisher : Program Studi Statistika Unisba

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

Abstract

In this article, two methods are proposed to give the interval estimation for two parameters Log-Normal distribution. We usually use traditional method to construct interval estimation. This intervalneeds a t distribution and chi-square distribution and namely traditional method. We will useanother method, namely bootstrap percentile. Bootstrap percentile method more potential inconstructing two parameters interval and give shorter interval than traditional method. This methoddoes not need an assumption that the sample has to have t and chi-square distributions.
Confidence Bands for Survivor Function of Two Parameters Exponential Distribution under Double Type-II Censoring with Bootstrap Percentile Fauzy, Akhmad
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 9, No 1 (2009)
Publisher : Program Studi Statistika Unisba

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

Abstract

This paper describes existing methods and develops new methods for constructing confidence bandsfor survivor function of two parameters exponential distribution under double type-II censoring. Ourresults are built on extensions of previous work by [11] and Balakrishnan [1]. They use maximumlikelihood estimator to construct interval estimation under double type-II censoring. The confidencebands are developed for survivor function using the confidence region about survivor function. We willuse another method, known as the bootstrap percentile from [4]. This method gives shorterconfidence bands compared to the traditional method.
Interval Konfidensi untuk Satu Parameter Distribusi Eksponensial di Bawah Sensor Lengkap dengan Metode Bootstrap (Studi Kasus Data Waktu Tunggu Bencana Gempa Bumi di Bulan Maret 2013) Fauzy, Akhmad
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 13, No 1 (2013)
Publisher : Program Studi Statistika Unisba

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

Abstract

In this research will be discussed on an interval estimate for the one parameter exponentialdistribution under complete censored data with a case study of data waiting time for earthquakedisaster in March 2013. The exponential distribution has immensely contributed in the analysis oflifetime. Historically the exponential distribution was the first lifetime model in which statisticalmethods in survival analysis were extensively developed. For samples that are singly failure-censoredon the complete censored, confidence intervals on one parameter exponential distribution areobtained from the exact sampling distribution on the following quantity related to the total time ontest T.
Predicting Interval of Product Reliability With Bootsrap Percentile Method Fauzy, Akhmad; Supandi, Epha Diana
Jurnal ILMU DASAR Vol 11, No 2 (2010)
Publisher : Fakultas MIPA Universitas Jember

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

Abstract

In this article, two methods are proposed to give the interval estimation for reliability function from a product. Reliability function is a probability of an individual (product) surviving till time t. Some resecearchers usually use traditional method to construct interval estimation. This interval needs an assumption that sample is exponentially distributed. This research applied another method, namely Bootstrap percentile. Bootstrap method is more potential in constructing interval estimation for reliability function from a product . Keywords: Bootstrap percentile, exponential distribution, reliability function
Interval Estimation for Quantile on Two Parameters Exponential Distribution Under Multiple Type-II Censoring on Complex Case with Bootstrap Percentile Fauzy, Akhmad
Jurnal ILMU DASAR Vol 10, No 1 (2009)
Publisher : Fakultas MIPA Universitas Jember

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

Abstract

In this article, two methods are proposed to give the interval estimation for quantile on two parametersexponential distribution under multiply type II censoring. The interval estimation for quantile can be constructedthe estimated parameters. Those researchers have use approximate maximum likelihood estimator to constructinterval estimation for two parameters exponential distribution under multiply type II censoring. All of thesemethod need an assumption that sample is exponentially distributed. We will use another method, known as thebootstrap percentile. This method gives shorter interval than the traditional method and this method does notneed an assumption that the sample is distributed exponentially.
Interval Konfidensi Serempak Bagi Rataan Respons dengan Metode Bootstrap Persentil pada Regresi Linier Sederhana Fauzy, Akhmad; Ibrahim, Noor Akma; Daud, Isa; Bakar, Mohd. Rizam Abu
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 2, No 2 (2002)
Publisher : Program Studi Statistika Unisba

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

Abstract

Seringkali kita ingin membuat interval konfidensi bagi rataan respons pada beberapa nilai X daridata sampel yang sama. Cara yang sering digunakan dalam mengestimasi E{Yh} pada berbagai nilaiXh adalah menghitung nilai tersebut sendiri-sendiri dan ternyata mempunyai kelemahan. Hal inidisebabkan keduanya berasal dari data sampel yang sama. Bonferroni telah mencoba membuatinterval konfidensi serempak bagi nilai tersebut. Metode ini ternyata juga mempunyai kelemahan,karena data yang diperoleh membutuhkan asumsi kenormalan. Tulisan ini akan menggunakanmetode lain, yaitu metode Bootstrap persentil. Akan ditunjukkan bahwa metode bootstrap persentilmenghasilkan interval konfidensi serempak yang lebih baik apabila dibandingkan dengan metodeBonferroni.
INTERVAL ESTIMATION FOR TWO PARAMETERS EXPONENTIAL DISTRIBUTION UNDER MULTIPLE TYPE-II CENCORING ON SIMPLE CASE WITH BOOTSTRAP PERCENTILE Fauzy, Akhmad; Ibrahim, Noor Akma; Daud, Isa; Bakar, Mohd. Rizam Abu
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 3, No 1 (2003)
Publisher : Program Studi Statistika Unisba

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

Abstract

In the article, two methods are proposed to give the interval estimation for twoparameters exponential distribution under multiple type-II cencoring on simple case. Balakrishnan(1990) use approximate maximum likehood estimator to construct interval estimation. All of thesemethod need an assumtion that sample is exounentially distributed. Method give shorter intervalthan the traditional method and this method does not need an assumtion that the sample isdistributed exponentially