• Communications for Statistical Applications and Methods
• /
• v.18 no.5
• /
• pp.645-655
• /
• 2011

Chandrasekar et al. (2004) introduced a generalized Type-II hybrid censoring. In this paper, we propose generalized doubly Type-II hybrid censoring. In addition, this paper presents the statistical inference on the scale parameter for the half logistic distribution when samples are generalized doubly Type-II hybrid censoring. The approximate maximum likelihood(AMLE) method is developed to estimate the unknown parameter. The scale parameter is estimated by the AMLE method using two di erent Taylor series expansion types. We compar the AMLEs in the sense of the mean square error(MSE). The simulation procedure is repeated 10,000 times for the sample size n = 20; 30; 40 and various censored samples. The $AMLE_I$ is better than $AMLE_{II}$ in the sense of the MSE.

• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.155-164
• /
• 2014

This paper proposes a new method to determine the recognition units for large vocabulary continuous speech recognition (LVCSR) in Korean by applying unsupervised segmentation and merging. In the proposed method, a text sentence is segmented into morphemes and position information is added to morphemes. Then submorpheme units are obtained by splitting the morpheme units through the maximization of posterior probability terms. The posterior probability terms are computed from the morpheme frequency distribution, the morpheme length distribution, and the morpheme frequency-of-frequency distribution. Finally, the recognition units are obtained by sequentially merging the submorpheme pair with the highest frequency. Computer experiments are conducted using a Korean LVCSR with a 100k word vocabulary and a trigram language model obtained by a 300 million eojeol (word phrase) corpus. The proposed method is shown to reduce the out-of-vocabulary rate to 1.8% and reduce the syllable error rate relatively by 14.0%.

• 한국데이터정보과학회:학술대회논문집
• /
• 2006.04a
• /
• pp.163-169
• /
• 2006

This paper deals with the comparison of parameter estimation methods in a 3-parameter Kappa distribution which is sometimes used in flood frequency analysis. The method of moment estimation(MME), L-moment estimation(L-ME), and maximum likelihood estimation(MLE) are applied to estimate three parameters. The performance of these methods are compared by Monte-carlo simulations. Especially for computing MME and L-ME, ike dimensional nonlinear equations are simplied to one dimensional equation which is calculated by the Newton-Raphson iteration under constraint. Based on the criterion of the mean squared error, the L-ME is recommended to use for small sample size $(n\leq100)$ while MLE is good for large sample size.

• Wind and Structures
• /
• v.31 no.4
• /
• pp.311-319
• /
• 2020

India is a developing nation and heavily spends on the development of wind power plants to meet the national energy demand. The objective of this paper is to investigate wind power potential of Ennore site using wind data collected over a period of two years by three parameter Weibull distribution. The Weibull parameters are estimated using maximum likelihood, least square method and moment method and the accuracy is determined using R² and root mean square error values. The site specific capacity factor is calculated by the mathematical model developed by three parameter Weibull distribution at different hub heights above the ground level. At last, the wind energy economic analysis is carried out using capacity factor at 30 m, 40 m and 50 m height for different wind turbine models. The analysis showed that the site has potential to install utility wind turbines to generate energy at the lowest cost per kilowatt-hour at height of 50 m. This research provides information of wind characteristics of potential sites and helps in selecting suitable wind turbine.

• Journal of Korean Society for Quality Management
• /
• v.38 no.4
• /
• pp.480-490
• /
• 2010

In this paper, two estimation methods(least square estimation and maximum likelihood estimation) were compared for Weibull distribution and Type I censoring. Data obtained by Monte Carlo simulation were analyzed using two estimation methods and analysis results were compared by MSE(Mean Squared Error). Comparison results show that maximum likelihood estimator is better for censored data and complete data with more than 30 samples and least square estimator is better for small size complete data(less than and equal to 20 samples).

• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• pp.1055-1066
• /
• 2009

Many articles have considered a hybrid censoring scheme, which is a mixture of Type-I and Type-II censoring schemes. We introduce a double hybrid censoring scheme and derive some approximate maximum likelihood estimators(AMLEs) of the scale parameter for the half logistic distribution under the proposed double hybrid censored samples. The scale parameter is estimated by approximate maximum likelihood estimation method using two different Taylor series expansion types. We also obtain the maximum likelihood estimator(MLE) and the least square estimator(LSE) of the scale parameter under the proposed double hybrid censored samples. We compare the proposed estimators in the sense of the mean squared error. The simulation procedure is repeated 10,000 times for the sample size n = 20(10)40 and various censored samples. The performances of the AMLEs and MLE are very similar in all aspects but the MLE and LSE have not a closed-form expression, some numerical method must be employed.

• Communications for Statistical Applications and Methods
• /
• v.20 no.1
• /
• pp.63-75
• /
• 2013

In this paper, we derive maximum likelihood estimators (MLEs) and approximate maximum likelihood estimators (AMLEs) of unknown parameters in a generalized half logistic distribution under Type-II hybrid censoring. We also obtain approximate confidence intervals using asymptotic variance and covariance matrices based on the MLEs and the AMLEs. As an illustration, we examine the validity of the proposed estimation using real data. Finally, we compare the proposed estimators in the sense of the mean squared error (MSE), bias, and length of the approximate confidence interval through a Monte Carlo simulation for various censoring schemes.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.18 no.4
• /
• pp.4232-4241
• /
• 1976

This study was carried out to clarify the stochastic characteristics of monthly rainfalls and to select a proper model for generating the sequential monthly rainfall amounts. The results abtained are as follows: 1. Log-Normal distribution function is the best fit theoretical distribution function to the empirical distribution of monthly rainfall amounts. 2. Seasonal and random components are found to exist in the time series of monthly rainfall amounts and non-stationarity is shown from the correlograms. 3. The Monte Carlo model shows a tendency to underestimate the mean values and standard deviations of monthly rainfall amounts. 4. The 1st order Markov model reproduces means, standard deviations, and coefficient of skewness with an error of ten percent or less. 5. A correlogram derived from the data generated by 1st order Markov model shows the charaterstics of historical data exactly. 6. It is concluded that the 1st order Markov model is superior to the Monte Carlo model in their reproducing ability of stochastic properties of monthly rainfall amounts.

• Journal of the Korea Safety Management & Science
• /
• v.9 no.2
• /
• pp.215-233
• /
• 2007

Even though the ad hoc Shewhart methods remain controversial due to various mathematical flaws, there is little disagreement among researchers and practitioners when a set of process data has a skewness distribution. In the context and language of process control, the error related to the process data shows that time to signal increases when a control parameter shifts to a skewness direction. In real-world industrial settings, however, quality practitioners often need to consider a skewness distribution. To address this situation, we developed an enhanced design method to utilize advantages of the traditional attribute control chart and to overcome its associated shortcomings. The proposed design method minimizes bias, i.e., an average time to signal for the shift of process from the target value (ATS) curve, as well as it applies a variable sampling interval (VSI) method to an attribute control chart for detecting a process shift efficiently. The results of the factorial experiment obtained by various parameter circumstances show that the VSI c control chart using nearly unbiased ATS design provides the smallest decreasing rate in ATS among other charts for all experimental cases.

• The KSFM Journal of Fluid Machinery
• /
• v.13 no.4
• /
• pp.11-17
• /
• 2010

The developed control valves, installed on the hot water distribution manifolds for the floor heating system, consist of the balancing valves and the shut-off valves. The balancing valve was designed to improve the flow control performance and to reduce the noise emitted from the valve by modification of the general V port. The port of the shut-off valve was designed with two ceramic plates, working by rotating upper plate, to improve the duration and to reduce the noise. For the evaluation of the new valves, the flow rate was measured and noise level test was carried out. The test results showed that the error of the flow rate accuracy test for the flow balance of each manifold circuit was less than ${\pm}3%$ and the noise level was less than 35 dB(A).