• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.465-472
• /
• 1999

We considered a bootstrap method for constructing confidenc intervals for a one parameter model using multinomial sampling. The convergence rates or the proposed bootstrap method are calculated for model-based maximum likelihood estimators(MLE) using multinomial sampling. Monte Carlo simulation was used to compare the performance of bootstrap methods with normal approximations in terms of the average coverage probability criterion.

• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.525-534
• /
• 2003

If a restriction is imposed only to a (proper) subset of parameters of interest, we call it a local restriction. Statistical inference under a local restriction in multinomial setting is studied. The maximum likelihood estimation under a local restriction and likelihood ratio tests for and against a local restriction are discussed. A real data is analyzed for illustrative purpose.

• Communications for Statistical Applications and Methods
• /
• v.14 no.1
• /
• pp.121-131
• /
• 2007

In this paper, we examine the problem of estimating the sensitive characteristics and behaviors in a multinomial randomized response model using Bayesian approach. We derived a posterior distribution for parameter of interest for multinomial randomized response model. Based on the posterior distribution, we also calculated a credible intervals and mean squared error (MSE). We finally compare the maximum likelihood estimator and the Bayes estimator in terms of MSE.

• Journal of the Korean Statistical Society
• /
• v.26 no.4
• /
• pp.453-465
• /
• 1997

The family of power-divergence statistics conditional on margins is considered for testing homogeneity of .tau. multinomial populations with equal sample size and the exact Bahadur slope is obtained. It is shown that the likelihood ratio test conditional on margins is the most Bahadur efficient among the family of power-divergence statistics.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.259-267
• /
• 2003

Though naive Bayes text classifiers are widely used because of its simplicity, the techniques for improving performances of these classifiers have been rarely studied. In this paper, we propose and evaluate some general and effective techniques for improving performance of the naive Bayes text classifier. We suggest document model based parameter estimation and document length normalization to alleviate the Problems in the traditional multinomial approach for text classification. In addition, Mutual-Information-weighted naive Bayes text classifier is proposed to increase the effect of highly informative words. Our techniques are evaluated on the Reuters21578 and 20 Newsgroups collections, and significant improvements are obtained over the existing multinomial naive Bayes approach.

• Earthquakes and Structures
• /
• v.26 no.2
• /
• pp.87-96
• /
• 2024

This paper proposes a logistic multinomial regression approach to model the spatial cross-correlation of damage probabilities among different damage states in an expanded transportation network. Utilizing Bayesian theory and the multinomial logistic model, we analyze the damage states and probabilities of bridges while incorporating damage correlation. This correlation is considered both between bridges in a network and within each bridge's damage states. The correlation model of damage probabilities is applied to the seismic assessment of a portion of Tehran's transportation network, encompassing 26 bridges. Additionally, we introduce extra daily traffic time (EDTT) as an operational parameter of the transportation network and employ the shortest path algorithm to determine the path between two nodes. Our results demonstrate that incorporating the correlation of damage probabilities reduces the travel time of the selected network. The average decrease in travel time for the correlated case compared to the uncorrelated case, using two selected EDTT models, is 53% and 71%, respectively.

• Journal of Korean Society of Transportation
• /
• v.7 no.1
• /
• pp.35-42
• /
• 1989

The multinomial logit model has been applied for various choice problems. Among others, the joint destination mode choice, the mode choice and the route choice are the three major modeling topics for korean transportation planners. This paper examines with real world data (the Olympic road and its competing two major arterials) the usefulness of a Logit route choice model. Quites surpisingly, it is found that the multinomial route choice behavioral model calibrated for this study based on (0,1) individula data base can not provide a good estimate for O-D trips less than 6㎞. 400data points and 3case studies might not be sufficient for a sound conclusion. It is, however, believed from a series of similar studies conducted by the authors that the route choice behavior is more sensitive (more demand elastic with respect to travel time changes) than the mode choice and the shorter trip, the more sensitive. The travel time parameters for destination choice models are usually smalle than the travel time parameters for mode choice models and these parameters (for mode choice models) turn our smaller than the travel time parameters for route choice models from this study. Table 2 in this paper shows parameter changes for three different markets and Table 3 shows the modeling errors when the estimated individual probabilities are aggregated into a route level.

• Management Science and Financial Engineering
• /
• v.20 no.2
• /
• pp.27-31
• /
• 2014

This paper studies the assortment optimization problem in online retailing by using a multinomial logit model in order to take consumer choice behavior into account. We focus on two unique features of online purchase behavior: first, there exists increased amount of uncertainty (e.g., size and color of merchandize) in online shopping as customers cannot experience merchandize directly. This uncertainty is captured by the scale parameter of a Gumbel distribution; second, online shopping entails unique shopping-related disutility (e.g., waiting time for delivery and security concerns) compared to offline shopping. This disutility is controlled by the changes in the observed part of utility function in our model. The impact of changes in uncertainty and disutility on the expected profit does not exhibit obvious structure: the expected profit may increase or decrease depending on the assortment. However, by analyzing the structure of the optimal assortment based on convexity property of the profit function, we show that the cardinality of the optimal assortment decreases and the maximum expected profit increases as uncertainty or disutility decreases. Therefore, our study suggests that it is important for managers of online retailing to reduce uncertainty and disutility involved in online purchase process.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.34 no.1
• /
• pp.42-51
• /
• 2011

Poisson model and Gamma-Poisson model are popularly used to analyze statistical behavior from defective data. The methods are based on binary criteria, that is, good or failure. However, manufacturing industries prefer polytomous criteria for classifying manufactured products due to flexibility of marketing. In this paper, I introduce two multivariate Gamma-Poisson(MGP) models and estimation methods of the parameters in the models, which are able to handle polytomous data. The models and estimators are verified on defective pixels of LCD manufacturing. Experimental results show that both the independent MGP model and the multinomial MGP model have excellent performance in terms of mean absolute deviation and the choice of method depends on the purpose of use.

• Journal of Korean Society of Transportation
• /
• v.26 no.1
• /
• pp.145-153
• /
• 2008

Existing shortest-path algorithms mainly consider a single attribute. But traveler actually chooses a route considering not single attribute but various attributes which are synthesized travel time, route length, personal preference, etc. Therefore, to search the optimal path, these attributes are considered synthetically. In this study route searching algorithm which selects the maximum utility route using discrete choice model has developed in order to consider various attributes. Six elements which affect route choice are chosen for the route choice model and parameters of the models are estimated using survey data. A multinomial logit models are developed to design the function of route choice model. As a result, the model which has route length, delay time, the number of turning as parameter is selected based on the significance test. We use existing shortest path algorithm, which can reflect urban transportation network such as u-turn or p-turn, and apply it to the real network.