Estimasi Parameter Distribusi Weibull Dan Aplikasinya pada Pengendalian Mutu Dengan Memanfaatkan Kuantil
Abstract
Abstract. Weibull distribution is one of the continuous probability distributions. As the other distributions, Weibull distribution is also characterized by Mean, Variance and Moment Generation Function. The advantage of this distribution compared to other distributions is its flexibility, that is, this distribution can change to another distribution such as an exponential distribution depending on the value of the selected distribution parameters, namely scale parameters and form parameters. From the distribution graph, it can be shown that, the flexibility will appear very clear. One application of the Weibull distribution is in statistical process control. Because not all data is normally distributed, the Shewhart control chart cannot be used. One way to solve this problem is that the data is analyzed with Weibull control charts by utilizing quantiles, namely 0.00135, 0.5 and 0.99865. Quantile 0.00135 is the bottom quintile used to form the Lower Control Limit, the Middle Line is the median of the data, which is 0.5 which replaces the average and the last to form the Upper Control Limit the top quintile is 0.99865. By generating 200 data with Weibull distribution, if the data is analyzed by Shewhart control charts then there is a lot of data that is outside the control limit so it will be concluded that the graph is out of control. Therefore, if the data is not from a Normal distribution, the use of Shewhart control charts is not recommended.
Keywords: Weibull Distribution, Maximum Likelihood Estimation (MLE), Quality Control, Weibull Control Charts
Abstrak. Distribusi Weibull merupakan salah satu distribusi probabilitas kontinu. Sama halnya dengan distribusi lainnya, distribusi Weibull pun dicirikan dengan Mean, Variansi dan Fungsi Pembangkit Momen. Kelebihan distribusi ini dibandingkan dengan distribusi lainnya adalah fleksibilitasnya, yaitu distribusi ini dapat berubah menjadi distribusi lain seperti distribusi eksponensial tergantung pada nilai parameter distribusi yang dipilih yaitu parameter skala dan parameter bentuk. Jika dilihat dari grafik distribusinya maka akan tampak sangat jelas fleksibilitas tersebut. Salah satu aplikasi dari distribusi Weibull yaitu dalam pengendalian proses statistik. Oleh karena tidak semua data berdistribusi normal maka grafik pengendali Shewhart tidak dapat digunakan. Salah satu cara menyelesaikan masalah tersebut adalah data dianalisis dengan grafik pengendali Weibull dengan memanfaatkan kuantil-kuantil yaitu 0,00135, 0,5 dan 0,99865. Kuantil 0,00135 adalah kuantil bawah yang digunakan untuk membentuk Batas Pengendali Bawah, Garis Tengah adalah median dari data yaitu 0,5 yang menggantikan rata-rata dan untuk membentuk Batas Pengendali Atas digunakan kuantil atas yaitu 0,99865. Dengan membangkitkan data sebanyak 200 data berdistribusi Weibull, jika data tersebut dianalisis dengan grafik pengendali Shewhart maka terdapat banyak data yang berada diluar batas pengendali sehingga akan disimpulkan bahwa grafik tak terkendali. Oleh karena itu, jika data bukan berasal dari distribusi Normal, penggunaan grafik pengendali Shewhart tidak disarankan.
Kata Kunci: Distribusi Weibull, Estimasi Maximum Likelihood, Pengendalian Mutu, Grafik Pengendali Weibull
References
[2] Zhang, M, Performance of Control Charts For Weibull Processes. Electronic Theses, Treatises and Dissertations (ETDs) 537,1-59, 2008.
[3] Ahmad,S., Abdollahian, S., Zeephongsekul, P., dan Abbasi, B, Performance Analysis For Skewed Data. http://www.ubicc.org/files/pdf/UBICC_IKE07_Performance%20Analysis%20for%20skewed%20data_191_191.pdf diakses tanggal 17 Maret 2018.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish in UJMC (Unisda Journal of Mathematics and Computer Science) agree to the following terms:
1.Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
2.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
3.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.