• Survey Research
• /
• v.5 no.1
• /
• pp.1-26
• /
• 2004

The aim of this study lies in answering the question "How to form weighting cells to enhance sample representativeness in telephone, Internet and mobile surveys\ulcorner". For this, we explored 2% raw data of Year 2000 Population and Housing Census of Korea looking for meaningful patterns for ownership of telephones, the usage of Internet and/or mobile phones. We found that telephone coverage rates vary significantly by household size; 84.6% for one member households, contrasting 98.5% for two-or-more member households. Thus, telephone survey samples need to be weighted differently in sub-groups by household size for proportional representation of target population. Searching socio-demographic factors influencing the use of Internet by C5.0 tree models, we found that education levels and the occupation (or housing type, the automobile ownership) are two most important factors in addition to gender and age. Thus, surveyor might form weighting cells by such factors at the stage of post-stratification or set quotas, a priori, proportional to size of the cells by such factors. For mobile surveys, we approached similarly and found that education levels and the occupation (or the automobile ownership, marriage status) are two additional factors that may be used in forming weighing cells or in setting quotas for cells.

• Survey Research
• /
• v.9 no.3
• /
• pp.55-69
• /
• 2008

In most telephone surveys in Korea, telephone numbers are selected from the directories. Inevitably, such samples may lack representativeness due to poor coverage rate. To resolve the problem, Kang et al.(2008) implemented RDD(random digit dialing) method for nationwide sampling in Korea. The aim of this study is to compare an RDD sample with a traditional telephone quota sample that were collected independently by two survey institutes commissioned by the KBS-MBC consortium for the 2007 Presidential Election of Korea.

• Journal of Korean Society for Atmospheric Environment
• /
• v.18 no.E1
• /
• pp.1-12
• /
• 2002

One technique for determining dry acid deposition fluxes involves measurement of time - averaged ambient concentrations of dry acid deposition species using filter packs (FP) coupled with estimates of mean deposition velocities for the exposure period. A critical problem associated with filter pack data comparisons between various field sampling networks is the use of diverse sampling flow rates and duration protocols. Field experiments were conducted to evaluate the effects of varying sampling flow rates, from 1.5 to 10 standard liters per minute, on total nitrate and sulfate measurements of specific dry acid deposition species . Collocated FP samplers were used to determine sampling and analysis data reproducibility and representativeness . Ambient air samples were simultaneously collected using groups of filter packs operated at various flow rates over identical 7 day periods. The species measured were sulfur dioxide, particulate sulfate , nitric acid and particulate nitrate. Statistical results (ANOVA; alpha level 5%) showed that neither the low nor high sampling flow rates caused a significant difference in the measurements of total sulfate and adjusted total nitrate (ATN) . However, it was concluded that for high flow rate sampling measurements, total nitrate (TN) could be affected during extended sampling durations because of potential nitric acid overloading and breakthrough. Although the previous workers (Costello, 1990; Quillian, 1990) used much higher sampling flow rates (~ 17 sLpm) than employed here, it was assumed that for a high loading (> 50$\mu\textrm{g}$ HNO$_3$) of nitric acid on the Nylon filters, a significant fraction (~10%) of nitric acid could pass through the Nylon filters and be collected on the carbonate impregnated filters. It was concluded that even at the highest sampling flow rate employed (10 sLpm) at the Cary Forest site, nitric acid breakthrough was less than 10% of the total HNO$_3$ collected. However, for a heavily polluted urban airshed or with longer sampling times , higher filter loadings could result in substantial nitric acid breakthrough and HNO$_3$concentrations would be underestimated.

• Survey Research
• /
• v.8 no.1
• /
• pp.55-79
• /
• 2007

This article attempts to provide an overview of the exit polls for the 2006 local elections in Korea. The sampling method, sampling error, non-response rate, and prediction error of the exit polls are reviewed. Also, we explore the fact that the propensity to vote varies according to age and gender of voters. In terms of age and gender, the representativeness of the sample is investigated by comparing to the data released by the National Election Commission. Through this empirical research, we show that the exit poll samples are unbalanced in terms of age and this unbalance may be one of the causes of bias occurred in the prediction of the 2006 local election results. The design effects of the sample design implemented for the exit polls are also examined.

• Journal of Radiation Protection and Research
• /
• v.38 no.4
• /
• pp.228-233
• /
• 2013

It has been continuously generated the requirement for the replacement of the main components such as a steam generator due to the deterioration of the nuclear power plant all around the world. Also, a large amount of radioactive metal was generated during the decommissioning in a short period. It is required to make an accurate measurement of the residual radioactivity for recycling the metal waste for releasing from regulatory control. In planning the measurement procedures, the influence of geometry, self-absorption, density and other relevant factors on the representativeness of the measurements should be considered for the decommissioning metal waste. In this study, the method for measurement procedures, the source term evaluation, the ways to secure representative samples, the measurement device for wide area and the self-absorption correction factors for different density were evaluated. The metal samples for measurement were prepared for securing the simple geometry and representative by melting process. The developed correction method for measuring the radioactivity a variety density of metal waste could improve the reliability of the evaluation results for clearance.

• International Commerce and Information Review
• /
• v.4 no.1
• /
• pp.107-128
• /
• 2002

In order to clarify the relationship between the Internet utilization of the Korean small export firms for export marketing and it's performance, first, a research model and hypothesis have been made on a theoretical basis. This research hypothesis has been examined through gathering survey data and a statistical analysis based on MANOVA. The conclusion, as well as the main point of this thesis, is that, in most cases, there was a significant statistical connection between the variables of export performances and Internet-utilized export marketing strategies, which are both based on the classical AIDA model of effective hierarchy of communication for sales and advertising. This conclusion brings forth a substantial topic as well as provides meaningful implications for the Korean small export firms when putting together a marketing strategy using the Internet. It is also hoped that this will come as a reference for other researchers henceforth. However, there is an issue of lack of representativeness when considering that the samples were chosen on the basis of the convenience sampling method. Another issue may be that a portion of the subjects were not related to actual trade, but were, in fact, Web masters who operated e-trade systems. Furthermore, there are also numerous problems of missing data, and 6 out of the 8 main hypotheses possessed the issue of fitness level with the data. Therefore, in order to enhance both the representative and fitness levels of the data of further research for this topic, future respondents will have to have special trade knowledge, as well as technical knowledge of e-trade. However, unless the Internet begins to greatly contribute to export marketing of corporations, this type of enterprising spirit by corporations in gathering suitable respondents will not surface. Although not used in examining the hypotheses of this particular thesis, the relationship between competitive and circumstantial variables, which were added to the upcoming survey, and export performances will soon be analyzed and announced in order to atone for some of the standards this thesis fell short of.

• Journal of Labour Economics
• /
• v.25 no.1
• /
• pp.47-74
• /
• 2002

Since the Economic Crisis at the end of 1997, unemployment rate soared up to the record-high 8.6% (February 1999) and, for youth aged 15~29, it was 14.6% (27.8% for aged 15~19). In spite of economic recovery after the crisis, new participants in labor market at the school-to-work transition have faced with difficulties in finding their first jobs and, even further, the ratio of youth at out-of the labor force but not in school has remained at a higher level. It is important to calibrate the negative effects of nonemployment in the short-run as well as in the long-run, but there has been few study on the school-to-work transition in Korea. This study focus on the nonemployment duration to first job after formal education and comparison of its pattern before and after the crisis. A proportional hazard model, considering job prenaration before graduation (21.4% of the sample), with the semi-parametric baseline hazard is applied to the sample from the Korean Labor and Income Panel Survey(1998~2000) and its Youth Supplemental survey(2000). Interview of the Survey is conducted, by the Korea Labor Institute, to the same 5,000 household and 13,738 individual sample, guaranteeing nationwide representativeness. The Supplemental Survey consists of 3,302 young individuals aged 15 to 29 at the time of survey and 1,615 of them who are not in school and provide appropriate information is used for the analysis. The empirical results show that there exists negative duration dependence at the first three or for months at the transition period and no duration dependence since a turning point of the baseline hazard rate and that unemployment rate reflecting labor demand conditions has a positive effect on exiting the nonemployment state, which is inconsistent with a theoretical conclusion. Estimation with samples separated by the date of graduation before and after the crisis shows that the effect of unemployment rate on the hazard was negative for the pre-crisis sample but positive for the post-crisis sample.