• Journal of applied mathematics & informatics
• /
• 제8권1호
• /
• pp.253-260
• /
• 2001

In this paper we suggest a conditional unrelated question randomized response model by using the Carr et. al.’s model(1982) and Greenberg et. al.’s model(1969). Our model can obtain more comprehensive information about the sensitive character A. We suggest the conditions that make our model efficient compared with models of Greenberg et. al. and Carr et al..

• Communications for Statistical Applications and Methods
• /
• 제7권3호
• /
• pp.721-729
• /
• 2000

In this paper, we propose a new conditional randomized response model that has improved the Carr et al.'s model in view of he variance and the protection of privacy of respondents. We show that he suggested model is more effective and protective than the Loynes' model and Carr et al.' model.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제14권4호
• /
• pp.249-273
• /
• 2010

Often in practice, the implied volatility of an option is calculated to find the option price tomorrow or the prices of, nearby' options. To show that one does not need to adhere to the Black- Scholes formula in this scheme, Figlewski has provided a new pricing formula and has shown that his, alternating passive model' performs as well as the Black-Scholes formula [8]. The Figlewski model was modified by Henderson et al. so that the formula would have no static arbitrage [10]. In this paper, we show how to construct a huge class of such static no arbitrage pricing functions, making use of distortions, coherent risk measures and the pricing theory in incomplete markets by Carr et al. [4]. Through this construction, we provide a more elaborate static no arbitrage pricing formula than Black-Sholes in the above scheme. Moreover, using our pricing formula, we find a volatility curve which fits with striking accuracy the synthetic data used by Henderson et al. [10].

• Journal of the Korean Data Analysis Society
• /
• 제20권6호
• /
• pp.2883-2893
• /
• 2018

본 논문에서는 모집단이 층으로 구성되어 있고 얻고자 하는 속성이 민감할 때, 덜 민감한 속성 B와 강요응답으로 구성되어 있는 확률장치를 통해 "예"라고 응답한 사람들에게만 민감한 속성 A 와 무관한 속성 Y를 포함하고 있는 Greenberg et al.(1969)의 무관질문모형을 사용하도록 하여 모집단이 층화된 경우 층화추정을 위한 층화 조건부 무관질문모형을 제안하였다. 그리고 제안한 층화 조건부 무관질문모형에서 각 층에 표본을 배분할 때 비례배분과 최적배분 문제를 다루었다. 또한 층화 조건부 무관질문모형을 무관한 속성이 미지인 경우 두 개의 독립표본을 이용하는 층화 이표본 조건부 무관질문모형으로 확장하였으며, 제안한 층화 이표본 조건부 무관질문모형의 두 번째 단계에서 사용되는 h층의 표본의 크기에 대한 최적값을 도출하여 최소분산을 구하였다. 마지막으로 층화 조건부 무관질문모형이 층화 무관질문모형과 층화 Carr et al.(1982)의 모형보다 효율적이 되는 조건을 제시하여 일정한 조건하에서 제안한 모형이 기존 모형들보다 효율적임을 보였으며, 제안한 층화 조건부 무관질문모형이 ${\pi}_{h2}$ 값이 작고 ${\pi}_{hy}$ 값이 작을수록 층화 Carr et al.(1982)의 모형보다 효율적임을 수치적으로 보였다.

• Journal of applied mathematics & informatics
• /
• 제9권2호
• /
• pp.825-835
• /
• 2002

In this paper, we extend the conditional unrelated question model which was suggested by Lee and Hong(2000) to two-sample case when there is no information about the true proportion of the unrelated character Y. Conditions are obtained under which the proposed model is more efficient than Carr et al.\`s conditional modal and Greenberg et al.'s two-sample unrelated question model.