Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Media Statistika

RANCANGAN D-OPTIMAL UNTUK MODEL EKSPONENSIAL GENERAL Tatik Widiharih; Sri Haryatmi; Gunardi Gunardi
MEDIA STATISTIKA Vol 7, No 2 (2014): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (457.702 KB) | DOI: 10.14710/medstat.7.2.71-76

Abstract

Exponential model is widely used in biology, chemistry, pharmacokinetics and microbiology. D-optimal criteria is criteria with the purpuse to minimize the variance of  the estimator of parameters in the model. In this paper will discuss the D-optimal design for the generalized exponential model with  homoscedastics  errore assumtion. We used minimally supported design with the proportion of  each design point is uniform. The optimization is used  modified Newton, and the results obtained that the  design points are  interior points of the design region. Keywords: D-Optimal, Generalized Exponential, Minimally Supported Design, Support Point, Homoscedastics
VALUE AT RISK IN STOCK PORTFOLIO USING T-COPULA: Case Study of PT. Indofood Sukses Makmur, Tbk. and Bank Mandiri (Persero), Tbk. Qorina Rara Sartika; Tatik Widiharih; Moch Abdul Mukid
MEDIA STATISTIKA Vol 12, No 2 (2019): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (560.471 KB) | DOI: 10.14710/medstat.12.2.175-187

Abstract

Value at Risk (VaR) is a measuring tool that can calculate the amount of the worst losses that occur in the stock portfolio with a certain level of confidence and in certain period of time. In general, financial data has a high volatility value, which is caused the variance of residual model is not constant and nonnormally distributed. In this case, Copula-GARCH can be used to calculate the VaR. The Generalized Autoregressive Conditional Heterocedasticity (GARCH) model can resolve the time series models that have non-constant residual variance. This research use the t-Copula to model the dependency structure in the combined distribution of stock returns. The t-copula function is good in terms of reaching the extreme value state that often occurs in the financial data of stock returns and has heavytails. The empirical data uses the stock return data of PT. Indofood Sukses Makmur, Tbk (INDF) and Bank Mandiri (Persero) Tbk (BMRI) in the period of October 8, 2012 - October 8, 2017. In this research, Value at Risk is calculated using the period 1 day ahead at 90% confidence level that is 0.042, at 95% confidence level that is 0.025 and at 99% confidence level that is 0.017 with weight of each stock is 50%.
CREDIT SCORING MENGGUNAKAN METODE LOCAL MEANS BASED K HARMONIC NEAREST NEIGHBOR (MLMKHNN) Tatik Widiharih; Moch Abdul Mukid
MEDIA STATISTIKA Vol 11, No 2 (2018): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (207.293 KB) | DOI: 10.14710/medstat.11.2.107-117

Abstract

Credit Scoring is designed so that lenders can easily make decisions regarding whether a loan proposal from a prospective customer is worthy of approval or not. This study examines the application of the Multi Local Means Based K Harmonic Nearest Neighbor (MLMKHNN) method in the case of motorcycle credit in a financial institution. The classification capability of this method in detecting potential borrowers into the credit category is either good or bad compared to its previous method, Local Means Based K Harmonic Nearest Neighbor (LMKNN). In this case the MLMKHNN method has not shown better performance than the LMKNN method. At the same level of total accuracy, MLMKHNN requires more numbers of neighbors than the number of neighbors required by the LMKNN method. Keywords: sampling design, all possible samples, statistical efficiency, cost efficiency