• Communications for Statistical Applications and Methods
• /
• v.12 no.2
• /
• pp.285-294
• /
• 2005

This paper deals with the comparison of parameter estimation methods in a 3-parameter Kappa distribution which is sometimes used in flood frequency analysis. 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, three dimensional nonlinear equations are simplified to one dimensional equation which is calculated by the Newton-Raphson iteration under constraint. Based on the criterion of the mean squared error, L-ME (or MME) is recommended to use for small sample size( n$\le$100) while MLE is good for large sample size.

• Journal of Biosystems Engineering
• /
• v.25 no.3
• /
• pp.241-250
• /
• 2000

The feasibility of precision fertilizing for small size fields was studied by determining fertilizing amount of nitrogenous and calcareous to a cite specific region. A detailed soil survey at three experimental fields of $672m^2$, $300m^2$ and $140m^2$ revealed a considerable spatial variation of the pH and organic matter(OM) levels. Soil organic matter was measured using Walkley-Black method and soil pH was measured with a pH sensor. Soil sample was obtained by Grid Node Sampling Method. The soil sampling depth was 10∼20 cm from the soil surface. To display soil nutrient variation, a soil map was made using Geographic Information System (GIS) software. In soil mapping, soil data between nodes was interpolated using Inverse Distance Weighting (IDW) method. The variation was about 1∼1.8 in pH value and 1.4∼7% in OM content. Fertilizing Amount of nitrogenous and calcareous was determined by th fertilizing equation which was proposed by National Institute of Agricultural Science and Technology(NIAST). The variation of fertilizing amount was about 3∼11 kg/10a in nitrogenous and 70∼140 kg/10a in calcareous. The results showed a feasibility of precision fertilizing for small size fields.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.6
• /
• pp.1443-1452
• /
• 2016

In this paper, we study a sample design for survey on goodwill in retail properties to provide a protecting policy for small traders and tenants, to use basic data for a dispute case related to goodwill. Since goodwill in retail properties is occurred by individual rent company, we use the census on establishments from the Statistics Korea as population. First of all, we consider preferentially seven metropolitan cities in which there are more than half of population. Total sample size is decided as 8,000. We allocate the sample size for markets as stratum in each city using proportional formula and the sample size for industrial classifications in each market using root proportional formula. Also we compute survey weights and calculate estimators, standard errors and interval of estimators for each characteristic such as type of establishments and market in seven metropolitan cities.

• Proceedings of the Korean Association for Survey Research Conference
• /
• 2000.06a
• /
• pp.57-73
• /
• 2000

Small area estimation is becoming important in survey sampling due to a growing demand for reliable small area statistics. In estimating means, totals, and other parameters for small areas of a finite population, samplie sizes for small areas are typically small because the overall sample size is usually determined to provide specific accuracy at a much higher level of aggregation than that of small area. The usual direct estimators that use the only information which is gotten from the sample in a given small area provide unreliable estimates. However, indirect estimators utilize the information from the areas related with a given small area, that is borrow strength from other related areas, and so give more accurate estimates than direct estimators. In this paper we investigate small area estimation methods such as synthetic, composite and empirical best linear unbiased prediction estimator, and apply them to real domestic data which is from the Survey of Hotels and Restaurants in In-Chon as of 1996 and then evaluate the performance of these methods by measuring average squared errors. This evaluation shows that indirect estimators, which are small area estimation methods, are more efficient direct estimator.

• International Area Studies Review
• /
• v.13 no.3
• /
• pp.527-549
• /
• 2009

This paper investigates the relation of invert U-shape between the M/B ratio and leverage ratio by market, firm size, and a level of technology of firm. Our sample consists of 510 manufacturing firms continually listed on the Korea Securities Market and Kosdaq Market from January 1, 2001 to December 31, 2008. The total sample consists of the Korea Securities Market(large firms, high technology industry) sample of 2,248(1,816, 1,704) observations and the Kosdaq Market(small and medium firms, high technology industry) sample of 1,632(2,264, 2,376) observations. The empirical results show that the relation of invert U shape appears on the sample of the Kosdaq Market, small and medium firms, and high technology industry. However, the relation doesn't appear on the sample of the Korea Securities Market, large firms, and low technology industry. These mutually different results may be caused by the relatively low M/B ratio of the latter.

• Asian-Australasian Journal of Animal Sciences
• /
• v.22 no.12
• /
• pp.1620-1624
• /
• 2009

This study aimed to clarify the effect of mobile bag size and ratio of sample size to bag surface area on intestinal digestibility of forage in sheep. Four Suffolk ewes fitted with ruminal and proximal duodenal cannulae were fed second-cut Italian ryegrass (Lolium multiflorum Lam.) hay twice daily, and the same forage was used to measure intestinal digestibility. The forage samples were incubated in the rumen for 16 h and then in pepsin-HCl solution for 3 h before intestinal incubation. The incubated forage samples were placed in a nylon mobile bag. The bag sizes used were either 20 mm${\times}$20 mm (small bag size; SBS) or 30 mm${\times}$30 mm (large bag size; LBS) and the ratio of the sample size to the surface area of the bag was either 5.5 $mg/cm^{2}$ (low ratio; LR) or 11.0 $mg/cm^{2}$ (high ratio; HR) resulting in four different treatment conditions: SBS-LR, SBS-HR, LBS-LR and LBS-HR. Eight bags per animal were inserted through the duodenal cannulae at 15-min intervals and were subsequently collected from the feces of the animal. The mean intestinal bag transition time did not differ significantly between animals, but ranged from 23.2 to 27.0 h. The intestinal digestibility of dry matter (IDDM) ranged from 0.162${\pm}$0.019 g/g in the SBS-HR treatment group to 0.195${\pm}$0.018 g/g in the SBS-LR treatment. The intestinal digestibility of crude protein (IDCP) ranged from 0.610${\pm}$0.031 g/g in the LBS-LR treatment to 0.693${\pm}$0.018 g/g in the SBS-LR treatment. There was no difference in the IDDM and IDCP between different treatments. It was therefore concluded that the size of the mobile bag and the ratio of the sample size to the bag surface area did not influence the intestinal digestibility of forage. Future studies should use bags with high ratios of sample size to surface area in order to obtain sufficient residue for further analysis.

• The Korean Journal of Applied Statistics
• /
• v.26 no.1
• /
• pp.71-79
• /
• 2013

Semiparametric and nonparametric small area estimations have been studied to overcome a large variance due to a small sample size allocated in a small area. In this study, we investigate semiparametric and nonparametric mixed effect small area estimators using penalized spline and kernel smoothing methods respectively and compare their performances using labor statistics.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.5
• /
• pp.1433-1441
• /
• 2016

Small area model provides reliable and accurate estimations when the sample size is not sufficient. Our dataset has an inherent nonlinear pattern which signicantly affects our inference. In this case, we could consider semiparametric models such as truncated polynomial basis function and radial basis function. In this paper, we study four Bayesian semiparametric models for small areas to handle this point. Four small area models are based on two kinds of basis function and different knots positions. To evaluate the different estimates, four comparison measurements have been employed as criteria. In these comparison measurements, the truncated polynomial basis function with equal quantile knots has shown the best result. In Bayesian calculation, we use Gibbs sampler to solve the numerical problems.

• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.E1
• /
• pp.35-43
• /
• 2006

Ambient particle size distributions of PCBs and their dry deposition fluxes were measured at a site in Seoul to quantify dry deposition fluxes of PCBs and size characteristics of PCBs in the air, and to estimate ambient concentrations of gaseous PCBs and dry deposition fluxes. The dry deposition plate was used to measure dry deposition fluxes of particulate mass and PCBs and a cascade impactor and rotary impactor were used to measure ambient particle size distributions for small ($D_p<9{\mu}m$) and large ($D_p>9{\mu}m$) particles, respectively. Six sample sets were collected from April to July 1999. The fluxes of particulate total PCBs (the sum of 43 congeners) ranged from 160 to $607ng\;m^{-2}day^{-1}$. The size distribution of total PCBs was bimodal with two peaks in small particle size ($D_p{\sim}0.6\;and\;6{\mu}m$, respectively) and, thus, mass concentration being dominant in small particles. The mean particulate PCBs concentration was $6.9{\mu}g$ PCBs/g. The concentrations of PCB homologues in the gas phase were estimated based on the particle/gas partition coefficient ($K_p$) with the measured values of particulate PCBs in this study and they were comparable to those observed in other previous studies. Dry deposition fluxes were estimated by calculating dry deposition velocities.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.12
• /
• pp.1889-1893
• /
• 1990

In this paper, ultrasonic microscope system has been constructed with the small aperturre acoustic lens and the angle controller, and the new type of B-scanultransonic imaging has been analyzed. The system with small aperture lens was used to detect flaw existing within the thick specimen and its resolution was in the range of one wavelength at interior plane of sample. The anle controller was used to excited surface acoustic wave or shear wave. In order to obtain B-scan image of the flaw existig at interior of solids, shear wave has been excited and backscattering signals from the flaw have been processed. In experimental results, B-scan ultransonic images have been obtain from the flaws of varable shape and measured flaw size from the images has been in good agreement with practical size in the range of 10% error.