Skip Navigation
Skip to contents

Epidemiol Health : Epidemiology and Health

OPEN ACCESS
SEARCH
Search

Search

Page Path
HOME > Search
7 "Methods"
Filter
Filter
Article category
Keywords
Publication year
Authors
Funded articles
Original Article
Item non-response imputation in the Korea National Health and Nutrition Examination Survey
Serhim Son, Hyemi Moon, Hyonggin An
Epidemiol Health. 2022;44:e2022096.   Published online October 28, 2022
DOI: https://doi.org/10.4178/epih.e2022096
  • 5,360 View
  • 107 Download
  • 1 Crossref
AbstractAbstract AbstractSummary PDFSupplementary Material
Abstract
OBJECTIVES
The Korea National Health and Nutrition Examination Survey (KNHANES) is a public health survey that assesses individuals’ health and nutritional status and monitors the prevalence of major chronic diseases. In general, sampling weights are adjusted for unit non-responses and imputation is conducted for item non-responses. In this study, we proposed strategies for imputing item non-responses in the KNHANES in order to improve the usefulness of data, minimize bias, and increase statistical power.
METHODS
After applying logical imputation, we adopted 2 separate imputation methods for each variable type: unweighted sequential hot-deck imputation for categorical variables and sequential regression imputation for continuous variables. For variance estimation, multiple imputations were applied to the continuous variables. To evaluate the performance of the proposed strategies, we compared the marginal distributions of imputed variables and the results of multivariable regression analysis for the complete-case data and the expanded data with imputed values, respectively.
RESULTS
When comparing the marginal distributions, most non-responses were imputed. The multivariable regression coefficients presented similar estimates; however, the standard errors decreased, resulting in statistically significant p-values. The proposed imputation strategies may cope with the loss of precision due to missing data, thus enhancing statistical power in analyses of the KNHANES by providing expanded data with imputed values.
CONCLUSIONS
The proposed imputation strategy may enhance the utility of data by increasing the number of complete cases and reducing the bias in the analysis, thus laying a foundation to cope with the occurrence of item non-responses in further surveys.
Summary
Korean summary
본 연구는 국민건강영양조사에서 발생한 항목무응답의 대체방법에 대해 연구한다. 본 논문에서 제시된 논리적 대체와 무응답 대체법을 이용해 대체된 데이터를 제공함으로써 결과의 편향 감소와 통계적 검정력 향상을 기대할 수 있다. 또한, 본 연구의 결과는 추후 데이터 수집시 발생하는 무응답 발생의 최소화를 위한 대책마련에 사용될 수 있다.
Key Message
The proposed logical imputation and item non-response imputation strategy may enhance the utility of data by increasing the number of complete cases and reducing the bias in the analysis, thus laying a foundation to cope with the occurrence of item non-responses in further surveys.

Citations

Citations to this article as recorded by  
  • Associations of mediterranean diet score and age-related macular degeneration in Korean elderly
    Won Jang, Jungeun Choi, Hyesook Kim
    BMC Public Health.2024;[Epub]     CrossRef
Methods
Equivalence model: A new graphical model for causal inference
Jalal Poorolajal
Epidemiol Health. 2020;42:e2020024.   Published online April 9, 2020
DOI: https://doi.org/10.4178/epih.e2020024
  • 13,895 View
  • 207 Download
  • 10 Web of Science
  • 8 Crossref
AbstractAbstract PDF
Abstract
Although several causal models relevant to epidemiology have been proposed, a key question that has remained unanswered is why some people at high-risk for a particular disease do not develop the disease while some people at low-risk do develop it. The equivalence model, proposed herein, addresses this dilemma. The equivalence model provides a graphical description of the overall effect of risk and protective factors at the individual level. Risk factors facilitate the occurrence of the outcome (the development of disease), whereas protective factors inhibit that occurrence. The equivalence model explains how the overall effect relates to the occurrence of the outcome. When a balance exists between risk and protective factors, neither can overcome the other; therefore, the outcome will not occur. Similarly, the outcome will not occur when the units of the risk factor(s) are less than or equal to the units of the protective factor(s). In contrast, the outcome will occur when the units of the risk factor(s) are greater than the units of the protective factor(s). This model can be used to describe, in simple terms, causal inferences in complex situations with multiple known and unknown risk and protective factors. It can also justify how people with a low level of exposure to one or more risk factor(s) may be affected by a certain disease while others with a higher level of exposure to the same risk factor(s) may remain unaffected.
Summary

Citations

Citations to this article as recorded by  
  • Association between birth weight and risk of nonneurological childhood cancers: a systematic review and meta-analysis
    Roya Rashti, Faezeh Ghasemi, Jalal Poorolajal
    European Journal of Cancer Prevention.2024;[Epub]     CrossRef
  • The association between major gastrointestinal cancers and red and processed meat and fish consumption: A systematic review and meta-analysis of the observational studies
    Jalal Poorolajal, Younes Mohammadi, Marzieh Fattahi-Darghlou, Fatemeh Almasi-Moghadam, Atalel Fentahun Awedew
    PLOS ONE.2024; 19(6): e0305994.     CrossRef
  • The Role of Social Support in Preventing Suicidal Ideations and Behaviors: A Systematic Review and Meta-Analysis
    Nahid Darvishi, Jalal Poorolajal, Bita Azmi-Naei, Mehran Farhadi
    Journal of Research in Health Sciences.2024; 24(2): e00609.     CrossRef
  • The role of problem-solving skills in the prevention of suicidal behaviors: A systematic review and meta-analysis
    Nahid Darvishi, Mehran Farhadi, Bita Azmi-Naei, Jalal Poorolajal, Humayun Kabir
    PLOS ONE.2023; 18(10): e0293620.     CrossRef
  • Risk of primary lung cancer after breast cancer radiotherapy: a systematic review and meta-analysis
    Bushra Zareie, Mohammad Aziz Rasouli, Jalal Poorolajal
    Breast Cancer.2022; 29(2): 361.     CrossRef
  • The effect of silica exposure on the risk of lung cancer: A dose-response meta-analysis
    Fatemeh Shahbazi, Mina Morsali, Jalal Poorolajal
    Cancer Epidemiology.2021; 75: 102024.     CrossRef
  • Factors for the Primary Prevention of Breast Cancer: A Meta-Analysis of Prospective Cohort Studies
    Jalal Poorolajal, Fatemeh Heidarimoghis, Manoochehr Karami, Zahra Cheraghi, Fatemeh Gohari-Ensaf, Fatemeh Shahbazi, Bushra Zareie, Pegah Ameri, Fatemeh Sahraei
    Journal of Research in Health Sciences.2021; 21(3): e00520.     CrossRef
  • The Epidemiology of Aggression and Associated Factors among Iranian Adult Population: A National Survey
    Jalal Poorolajal, Bahram Ebrahimi, Forouzan Rezapur-Shahkolai, Amin Doosti-Irani, Mahnaz Alizadeh, Jamal Ahmadpoor, Leila Moradi, Azam Biderafsh, Fateme Nikbakht, Zakie Golmohammadi, Ehsan Sarbazi, Samira Bahadivand, Marzieh Jahani Sayad Noveiri, Maryam R
    Journal of Research in Health Sciences.2020; 20(4): e00499.     CrossRef
Note
Theory and practice of Case-Crossover Study Design.
Moran Ki
Korean J Epidemiol. 2008;30(1):1-11.   Published online June 30, 2008
DOI: https://doi.org/10.4178/kje.2008.30.1.1
  • 65,535 View
  • 257 Download
  • 2 Crossref
AbstractAbstract PDF
Abstract
A case-crossover study design is a method to assess the effect of transient exposures on the risk of onset of acute events. Which was introduced by Maclure in 1991 for Myocardial Infarction Onset Study. The design has been used to diverse fields of epidemiology such as injury, drug adverse events, air pollution and so on. The most valuable advantage of this design is unnecessary of control selection. To estimate relative risk, the exposure frequency during a window just before outcome onset is compared with exposure frequencies during control times rather than in control persons. One or more control times are supplied by each of the cases themselves. Self-matching of cases eliminates the threat of control-selection bias and increases efficiency. To application of the case-crossover design, we need to make sure several criteria and the possibility of specific bias. This review is designed to help the reader apply a case-crossover study design to their research fields by understanding general ideas, prior conditions and limitations of the design.
Summary

Citations

Citations to this article as recorded by  
  • Risk of Falls Associated with Long-Acting Benzodiazepines or Tricyclic Antidepressants Use in Community-Dwelling Older Adults: A Nationwide Population-Based Case–Crossover Study
    Inyoung Na, Junyoung Seo, Eunjin Park, Jia Lee
    International Journal of Environmental Research and Public Health.2022; 19(14): 8564.     CrossRef
  • Comparison of Effect of Two-Hour Exposure to Forest and Urban Environments on Cytokine, Anti-Oxidant, and Stress Levels in Young Adults
    Su Im, Han Choi, Yo-Han Jeon, Min-Kyu Song, Won Kim, Jong-Min Woo
    International Journal of Environmental Research and Public Health.2016; 13(7): 625.     CrossRef
Original Articles
The Current Status and the Direction for Development of the Health Interview Survey.
Eunjeong Kang, Myoung Hee Kim, Yeon Kyeng Lee, Bo Youl Choi
Korean J Epidemiol. 2007;29(2):103-110.
  • 65,535 View
  • 18 Download
AbstractAbstract PDF
Abstract
The Health Interview Survey in the Korean National Health and Nutrition Examination Survey is a major source for planning and evaluating the national health promotion policy. The aim of the study is to find the areas for improvement of the current Health Interview Survey in light of its stated purpose and to propose possible means for the improvement. In terms of the survey content, there were several areas that needed improvement: the lack of comparability across the waves, the limit of the number of questions due to the Nutrition Survey and the Examination Survey, non-availability of seasonal statistics, and the dearth of evidence on socioeconomic position variables. To make improvements in the survey content, there is a need to clarify the purpose of the HIS in the KNANES. Second, more items need to be developed to produce the indicators of the Health Plan 2010. Third, core questions and elective questions should be defined. Fourth, multi-level socioeconomic position indicators need to be developed. In terms of the survey methods, the difficulty of managing interviewers and the inefficiency of data input and processing were found to be the areas for improvement. Possible solutions include a survey through the year and the introduction of the CAPI system. In addition, we suggest that a two-year survey period to better synchronize with the local health interview surveys which should be the major data source for the community health promotion plan.
Summary
Smoking and lung cancer: foundation of modern epidemiology.
Hae Kwan Cheong
Korean J Epidemiol. 2005;27(2):1-19.
  • 44,850 View
  • 47 Download
AbstractAbstract PDF
Abstract
Since its introduction to western world in 16th century, smoking has been one of the most popular parts of human life. Its health hazards, however, has rarely been evaluated before mid 20th century. After early suggestion of association with lip cancer and pipe smoking, which was falsely associated with the heat of the pipe smoking, association between rapidly increasing incidence of lung cancer and increasing popularity of smoking habit in the western world has been suggested in late 1940s. Initial case-control studies, in spite of its proneness to various biases, aroused the relevance of the relationship. It was supported by following well-designed case-control studies and new method, cohort studies in both coast of the Atlantic. Consistency of the results of epidemiologic studies and additional support from animal experiments made the causal relationship to be accepted from scientific community, and finally from public and governments. Establishment of criteria of causal relationship was also established in the process of investigation of the relationship between smoking and lung cancer. Smoking is most common cause attributable to lung cancers in most of the world. It is also responsible for the many cancers, including larynx, bladder, oral cavity, esophagus, pancreas, kidney, stomach, liver, and myeloid leukemia; and cardiovascular disorders, respiratory disorders, and other degenerative disorders. Passive (or environmental tobacco) smoking has also been found to be hazardous. Establishment of causal relationship between smoking and lung cancer has been a landmark in the development of epidemiologic methods and concepts, which played the key role in the evaluation of risk factors and preventive intervention on the chronic degenerative disorders.
Summary
Review
A study on epidemiological characteristics and control methods of EHEC infection in Korea.
Sang Won Lee, Bok Kwon Lee, Yong Jae Lee, Hee Soo Lee, Suk Chan Jung, Kwak Hyo Sun, Bo Youl Choi
Korean J Epidemiol. 2005;27(1):37-52.
  • 65,535 View
  • 60 Download
AbstractAbstract PDF
Abstract
E. coli is a bacterium that is commonly found in the gut of humans and warm-blooded animals. Most strains of E. coli are harmless. But some strains such as Enterohaemorrhagic E. coli(EHEC), can cause severe food borne disease. It is transmitted to humans primarily through consumption of contaminated foods, such as raw or undercooked ground meat. There is no widely agreed definition of when a shiga-toxin producing E. coli is considered to be an EHEC. But in Korea, the word "EHEC", "STEC", "VTEC" are often used as same meaning, which refer to the E.coli those producing shiga-toxin. We suggest the term STEC refers to those E. coli produce one or more shiga-toxins(stx), and the term EHEC refers only to STEC that cause a clinical illness. EHEC infection were designated as the class 1 notifiable disease in Korea in 2000. Although EHEC/STEC cases were not common in Korea, the number of STEC infection cases reported has increased since 2001. From 2001 to 2004, the number of STEC infection cases in Korea were 11, 8, 52, 118 respectively. These cases included 17 due to E. coli O157, 136 due to E. coli, serogroup non-O157, and 15 due to E. coli that were not serogrouped. The most common serotype implicated is E. coli O91 without virulent factor and clinical symptoms. But those cases involve in one epidemic in primary school in 2004. STEC infections in Korea occur in all age groups, with the highest frequencies in children less than 5 years old. Healthy cattle are the main animal reservoir for STEC and they harbor the organism as part of the bowel flora. The proportion of STEC in E. coli in animal feces was examined by using stool samples from 283 Korean beef cattle on 27 farms, 169 milk cattle on 28 frams, 455 swine on 50 farms. As determined by culture and toxin assay, the proportion of STEC was 25.8%(16 STEC/62 E. coli) in milk cattle, 18.8%(19 STEC/101 E.coli) in Korean beef cattle, 14.0%(25 STEC/178 E. coli) in swine. Effective surveillance of EHEC/STEC in humans is essential in order to protect the public health. EHEC infection is notifiable in many countries including USA, Japan, and Belgium, Finland, Italy, Netherlands, and the United Kingdom(UK), have sentinel systems. England, Wales, and Scotland have comprehensive national laboratory reporting schemes for STEC. And there has been an increase in the number of reported cases and outbreaks during the past decades in many countries Prevention of STEC infection requires control measures at all stages of surveillace, investigations and special pathogen tracing such as PulseNet.
Summary
Original Article
Population-adjusted Mean Age at Incidence (PAMA) for Comparing Incidence Patterns with Age in Different Populations.
Yoon Ok Ahn, Moo Song Lee, Weechang Kang, Chung Min Lee, Youngjo Lee
Korean J Epidemiol. 1999;21(1):31-35.
  • 5,919 View
  • 4 Download
AbstractAbstract PDF
Abstract
Standardized incidence rates have been widely used for comparing incidence patterns between populations, adjusting for differences in demographic structure. These rates can compare overall incidence levels, but to fully understand incidence patterns, an index which links incidence with age is also needed. The authors proposed a statistical method for estimating population-adjusted mean age of incidence (PAMA), based on Poisson distribution and Fieller's theorem. The index was applied with several modifications to data relating to the incidence of breast cancer among Caucasian women living in Los Angeles.
Summary

Epidemiol Health : Epidemiology and Health
TOP