• Communications for Statistical Applications and Methods
• /
• 제28권2호
• /
• pp.189-204
• /
• 2021

In a regression analysis, a single best model is usually selected among several candidate models. However, it is often useful to combine several candidate models to achieve better performance, especially, in the prediction viewpoint. Model combining methods such as stacking and Bayesian model averaging (BMA) have been suggested from the perspective of averaging candidate models. When the candidate models include a true model, it is expected that BMA generally gives better performance than stacking. On the other hand, when candidate models do not include the true model, it is known that stacking outperforms BMA. Since stacking and BMA approaches have different properties, it is difficult to determine which method is more appropriate under other situations. In particular, it is not easy to find research papers that compare stacking and BMA when regression model assumptions are violated. Therefore, in the paper, we compare the performance among model averaging methods as well as a single best model in the linear regression analysis when standard linear regression assumptions are violated. Simulations were conducted to compare model averaging methods with the linear regression when data include outliers and data do not include them. We also compared them when data include errors from a non-normal distribution. The model averaging methods were applied to the water pollution data, which have a strong multicollinearity among variables. Simulation studies showed that the stacking method tends to give better performance than BMA or standard linear regression analysis (including the stepwise selection method) in the sense of risks (see (3.1)) or prediction error (see (3.2)) when typical linear regression assumptions are violated.

• 한국군사과학기술학회지
• /
• 제20권6호
• /
• pp.822-834
• /
• 2017

In M&S, radar model is a software module to identify position data of simulation objects. In this paper, we propose a radar performance model for simulations of air defenses. The previous radar simulations are complicated and difficult to model and implement since radar systems in real world themselves require a lot of considerations and computation time. Moreover, the previous radar simulations completely depended on radar equations in academic fields; therefore, there are differences between data from radar equations and data from real world in mission level analyses. In order to solve these problems, we firstly define functionality of radar systems for air defense. Then, we design and implement the radar performance model that is a simple model and deals with being independent from the radar equations in engineering levels of M&S. With our radar performance model, we focus on analyses of missions in our missile model and being operated in measured data in real world in order to make sure of reliability of our mission analysis as much as it is possible. In this paper, we have conducted case studies, and we identified the practicality of our radar performance model.

• ETRI Journal
• /
• 제22권4호
• /
• pp.51-65
• /
• 2000

In this paper, we investigate on the determinants of new venture performance empirically and suggest a new venture performance model in the Korean Information and Telecommunications (IT) industry. A total of seven hypotheses is established and tested using a combination of factor analysis, cluster analysis, analysis of variance, and correlation analysis. Ninety-two sample ventures in the Korean IT industry were investigated and analyzed to test hypotheses. We found that new ventures performance depends on their environment, strategy, internal resources factors, and, most importantly, two-way and three-way interactions of these factors. These findings could be interpreted as supporting the general strategy theory that when environment and internal resources and fitted, performance might be maximized and, further, strategy is the means that make internal resources and environment fit. The venture performance model presented in this paper can explain how new ventures achieve their successes. The strategic implications to the venture firms are also discussed.

• International Journal of Contents
• /
• 제4권3호
• /
• pp.20-28
• /
• 2008

To obtain realistic performance measures for wireless networks, one should consider changes in performance due to failure related behavior. In performability analysis, simultaneous consideration is given to both pure performance and performance with failure measures. SRN is an extension of stochastic Petri nets and provides compact modeling facilities for system analysis. In this paper, a new methodology to model and analyze performability based on stochastic reward nets (SRN) is presented. Composite performance and availability SRN models for wireless handoff schemes are developed and then these models are decomposed hierarchically. The SRN models can yield measures of interest such as blocking and dropping probabilities. These measures are expressed in terms of the expected values of reward rate functions for SRNs. Numerical results show the accuracy of the hierarchical model. The key contribution of this paper constitutes the Petri nets modeling techniques instead of complicate numerical analysis of Markov chains and easy way of performance analysis for channel allocation under SRN reward concepts.

• 한국IT서비스학회지
• /
• 제6권1호
• /
• pp.65-81
• /
• 2007

Recently, the affiliates of the Ministry of Information and Communication have been conducting a performance evaluation study on IT policy projects, based on the performance evaluation model of the U.S. Office of Management and Budgets, with regard to investment in computerization. The performance evaluation model for the policy project could provide the objective information required for the planning, development, and operation of the policy project. However, the performance of the most policy project is likely to be evaluated using the subjective evaluation criteria of evaluators. Therefore, this case study evaluates the relative efficiency using DEA (Data Envelopment Analysis) in order to improve the performance evaluation method of the digital pioneer' project implemented by the Korea IT Industry Promotion Agency. The improvement value of inefficient Decision Making Units (DMUs) was measured by a static efficiency analysis. The measured value will suggest a objective viewpoint of the performance between DMUs to evaluators. In doing so, it will show an appropriate direction for the policy project to be evaluated successfully.

• 대한기계학회논문집B
• /
• 제27권7호
• /
• pp.963-972
• /
• 2003

Performance characteristics of the planar-type solid oxide fuel cell (SOFC) are investigated by the analysis of flow fields coupled with heat and mass transfer phenomena in anode and cathode channels. For these purposes, performance analysis of the SOFC is conducted based on electrochemical reaction phenomena in electrodes and electrolyte coupled with flow fields in anode and cathode channels. In the present study, the isothermal model adopted in the previous paper prepared by the same authors is extended to the non-isothermal model by solving energy equation additionally with momentum and mass transfer equations using CFD technique. It is found that the difference between isothermal and non-isothermal models come from non-uniform temperature distribution along anode and cathode electrodes by solving energy equation in non-isothermal model. Non-uniform temperature distribution in non-isothermal model contributes to the increase of average temperature of the fuel cell and influences its performance characteristics.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 통신소사이어티 추계학술대회논문집
• /
• pp.129-132
• /
• 2003

This paper proposes a performance analysis model of security sowers. Performance analysis of security server reflects both the session and data traffic load. The proposed model is the bases of estimating the maximum response time and minimum queue size of a security server comprising a session association processor whose throughput is 1000 connection/s.

• 한국태양에너지학회 논문집
• /
• 제31권6호
• /
• pp.103-110
• /
• 2011

The aim of this study was to analysis the Heating/cooling performance and Daylighting performance of Solar Window System built in apartments. the solar window is the idea to integrate daylight as a third form of solar energy into a PV/Solar Collector system. The process of this study is as follows: 1)Solar Window system was designed through the investigation of previous paper and work. 2)The simulation program(Lightscape3.2) was used in daylighting performance analysis. the reference model of simulation was made up to analysis daylighting performance on Solar Window system. 3)The simulation program(ESP-r, Therm5.0, Window6.0) was used in energy performance analysis. the reference model of simulation was made up to analysis energy and daylighting performance on Solar Window system. 4)The Size of Simulation model for daylighting and heating/cooling energy analysis was $148.5m^2$ 5)The lighting performance analysis was carried out with various variants, such as the size and installed area of Solar Window system. 6)Energy performance simulation was carried out with various variants, such as Integrated U-value of Solar Window system according to its position, installed angle and insulation thickness. Consequently, When Solar Window system is equipped with balcony window of Apartment, Annual heating and cooling energy of reference model was cut down at the average of $4.1kWh/m^2$ or 4.2%.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2006년도 하계학술발표대회 논문집
• /
• pp.651-656
• /
• 2006

A performance analysis model has been developed for fin-tube type heat exchanger for $CO_2$ heat pump. The model uses the tube-by-tube method Because air-side thermal resistance has a great portion among total thermal resistances, it is important to understand air-side heat transfer characteristics. The air-side heat transfer correlation has been proposed from experiments using water. The developed model was confirmed by experimental results and can be used for the performance analysis of heat exchanger.

• 한국정밀공학회지
• /
• 제24권11호
• /
• pp.101-107
• /
• 2007

Jettability analysis using one-dimensional(1D) lumped parameter model has been investigated to design the industrial inkjet head with proper drop velocity and drop volume. By simplifying the inkjet head system into an equivalent electrical circuit, lumped model has been developed. Performance of the lumped model is verified by the comparison between measured results of droplet velocity and ejection volume and predicted value. Also, the jetting performance of an inkjet head is characterized by varying the design parameter and driving condition. As a result, simulation results shows good agreement with the experimentally measured value. The developed lumped model enables to easily understand the effect of dimension change and predict the jetting performance.