• Title/Summary/Keyword: 상대위험도 시각화

Search Result 2, Processing Time 0.119 seconds

Spatio-temporal analysis with risk factors for five major violent crimes (위험요인이 포함된 시공간 모형을 이용한 5대 강력범죄 분석)

  • Jeon, Young Eun;Kang, Suk-Bok;Seo, Jung-In
    • The Korean Journal of Applied Statistics
    • /
    • v.35 no.5
    • /
    • pp.619-629
    • /
    • 2022
  • The five major violent crimes including murder, robbery, rape·forced indecent act, theft, and violence are representative crimes that threaten the safety of members of society and occur frequently in real life. These crimes have negative effects such as lowering the quality of citizens' life. In the case of Seoul, the capital of Korea, the risk for the five major violent crimes is increasing because the population density of Seoul is increasing as a large number of people in the provinces move to Seoul. In this study, to reduce this risk, the relative risk for the occurrence of the five major violent crimes in Seoul is modeled using three spatio-temporal models. In addition, various risk factors are included to identify factors that significantly affect the relative risk of the five major violent crimes. The best model is selected in terms of the deviance information criterion, and the analysis results including various visualizations for the best model are provided. This study will help to establish efficient strategies to sustain people's safe everyday living by analyzing important risk factors affecting the risk of the five major violent crimes and the relative risk of each region.

The Effect Measures for Diagnostic Test: A Graph Approach (진단검사에서 측도들의 효과적인 표현: 그래프를 활용한 방법)

  • Cho, Tae-Kyoung;Son, Chang-Kyoon
    • The Korean Journal of Applied Statistics
    • /
    • v.26 no.1
    • /
    • pp.15-22
    • /
    • 2013
  • In clinical study or epidemic research, the $2{\times}2$ frequency table is useful to present a summary statistic The values of four cells in $2{\times}2$ table use to calculate the effect measures such as risk ratio, relative ris ratio or odds ratio. In this paper, we suggest that the improved visualization method using a radar diagram supported by MS-office Excel from the $2{\times}2$ frequency table is able to understand and draw easily betweendiagnosti measures such as sensitivity, specificity, predictivity, and likelihood ratio. We use some numerical example in order to show the usage of the proposed method.