1. Cross Sectional Studies
Son Hee Jung
2013/03/25

2. Type of Epidemiological Studies
Type of study Alternative name Unit Experimental RCT clinical trial individuals Observational Ecological correlational population Cross sectional prevalence individuals Case-control case-reference individuals Cohort follow up individuals

3. Study Designs & Corresponding Questions
Cross-sectional How common is this disease
or condition?
Ecologic What explains differences
between groups?
Case-control What factors are associated
with having a disease?
Prospective How many people will
get the disease?
What factors predict
development?

4. Contents Definition Basic approach Advantage & disadvantage Sampling
Measures of disease
Prevalence
Bias

5. Cross-sectional study-definition

6. Cross Sectional Study
연구대상 집단
한 시점
연구 진행
요인 노출과 질환에 관한 정보 수집

7. Cross-sectional study- Characteristics

8. Basic approach
Include a sample of all persons in a population at a given time without regard to exposure or disease status
Typically exposure and diseases assessed at that one time
Exposure subpopulations can be compared with respect to disease prevalence

9. Basic approach
For some questions, temporal ordering between exposure and disease is clear and cross sectional studies can test hypothesis
Example: genotype, blood type
When temporal ordering is not clear can be used to examine relations between exposure and outcomes descriptively, and to generate hypotheses
Can combine a cross sectional study with follow up to create a cohort study

10. Basic approach Issues with addressing etiology
Temporal ordering between exposure and outcome cannot be assured
Length biased sampling
Cases with long duration will be over represented

11. Cross -Sectional Studies: Advantages
Inexpensive for common diseases
Should be able to get a better response rate than other study designs
Relatively short study duration
Can be addressed to specific populations of interest

12. Cross-Sectional Studies : Disadvantages
Unsuitable for rare or short duration diseases
High refusal rate may make accurate prevalence estimates impossible
More expensive and time consuming than case-control studies
No data on temporal relationship between risk factors and disease development

13. Why sample?

14. Sampling from the source population

15. Non-probability sampling
Common convenience sampling methods
Street surveys
Use convenient place such as mall, hospital
Mail-out questionnaires
Most dangerous
Feel very strongly about the issue->bias
Volunteer call
Selection bias

16. Non-probability sampling-Convenience sampling
Select a sample through an easy, simple or inexpensive method
Problem
High risk of creating a bias
May provide misleading information
Can be accepted, but…
Be careful in assessing
And the results they produce

17. Basic probability sampling
Simple random sampling
Each sample of the chosen size has the same probability of being selected

18. Basic probability sampling
Systematic sampling
Obtain a lost of an available population, ordered according to an unrelated factor
Pick a number n as step size
Pick every n-th subject of the list

19. Stratified random sampling

20. Cluster random sampling

21. Multistage sampling

22. The National Health and Nutrition Examination Survey (NHANES)

23. NHANES Interviews & Examinationsㅍ

24. NHANES Sample Design

25. Analyses of NHANES Data

26. Weighting in NHANES ㅍ

27. NHANES base probability of selectionㅍ

28. Oversampling

29. Sample Weights

30. Why weight?

31. Probability weight – simple example

32. Example of weighting Imagine 100 male & 100 female in sample
But only 80 males & 75 females respond
Male respondent will get weight of
100/80->1/(80/100)=1.25
Female respondent will get weight of
100/75->1/(75/100)=1.33

33. 국민건강영양조사의 표본추출방법 예

34. 다단계 표본추출 단순무작위 표본추출의 실제적 어려움을 해결하기 위해 고안된 방법 전국 규모의 여론조사에 이용
“series” of simple random samples in stages
국민건강영양조사 국가 시도
시군구
읍면동
random
sampling

35. 유병률 산출: 가중치 적용
목적: 국민건강영양조사의 표본이 우리나라 국민을 대표하도록 가중치를 사용

36. Direct age adjustment-before
population
No. of death
Death rates per 100,000
Death rates per 100,000
900,000
862 96
1,130
126 A B
Age group
population
No. of death
Death rates per 100,000
Death rates per 100,000
All ages
900,000
862 96
1,130
126
30-49
500,000 60 12
300,000 30 10
50-69
396
132
400,000
400
100
70+
100,000
406
200,000
700
350

37. Direct age adjustment-afterB
population
No. of death
Death rates per 100,000
Death rates per 100,000
900,000
862 96
1,130
126
Age group
Standard
population
“A" age-specific
mortality rates
per 100,000
Expected No. of
deaths using
“A" rates
“B" age-specific
mortality rates per 100,000
Expected No. of deaths using
“B" rates
All ages
1,800,000
30-49
800,000 12 96 10 80
50-69
700,000
132
924
100
700
70+
300,000
406
1,218
350
1,050
Total
2,238
1,830
Age-adjusted rates
124.3
101.7
Age-adjusted rates: 2238/ = / =101.7

38. Indirect age adjustment (Standardized Mortality Ratio)
When
number of deaths for each age-specific strata are not available
Study mortality in an occupational exposure population
Defined
Observed number of deaths per year
Expected number of deaths per year
SMR of 100
Observed number of deaths is the same as expected number of deaths
SMR=
X100

39. Sampling, Inference, and generalization

40. Sampling, Inference, and generalization

41. Sampling, Inference, and generalization
If you tell the truth you don't have to remember anything. by Mark Twain 1894

42. Why do we measure disease prevalence?

43. Measuring burden: prevalence

44. Prevalence

45. Measuring burden: prevalence

46. Person-time at risk: exposed and unexposed

47. Censored individuals

48. Censoring

49. Measuring of prevalence

50. Point and period prevalence: example

51. Point prevalence at several time points

52. Period prevalence

53. Lifetime prevalence
Life time prevalence 4/5

54. Prevalence of diabetes

55. Utility of prevalence

56. Sloppy use of risk

57. Sloppy use of rate

58. Classic example of rate that is not a rate

59. Case fatality(rate?)

60. Proportional mortality (rate?)

61. Total deaths united states 2004

62. Deaths , U.S ages Years

63. What ‘s a possible inferential problem with proportional mortality?

64. Measuring risk: cumulative incidence

65. Measuring risk: cumulative incidence

66. Cumulative incidence is a proportion

67. Calculating the cumulative incidence

68. Odds

69. Odds

70. Odds

71. Odds

72. Odds and probabilities
The higher the incidence, the higher the discrepancy.

73. Prevalence, Incidence, disease duration

74. Disease prevalence depends on

75. Incidence rates can be calculated for each transition in health status

76. Incidence rates can be calculated for each transition in health status

77. Relationship among prevalence, incidence rate, disease duration at steady state

78. Relationship among prevalence, incidence rate, disease duration at steady state

79. Relationship among prevalence, incidence rate, disease duration at steady state

80. Mean duration of disease

81. Relationship among prevalence, incidence rate, disease duration at steady state

82. Relationship among prevalence, incidence rate, disease duration at steady state

83. Relationship among prevalence, incidence rate, disease duration at steady state

84. What does steady state mean in the context of estimating P from I and D?

85. Example varying prevalence, incidence rates and duration of disease

86. Cross-sectional Bias Incidence-Prevalence bias Type of selection bias
If exposed cases have different duration that no-exposed prevalent cases, prevalence ratio will be biased
E.g., cases with severe emphysema more likely to smoke, have higher fatality than cases with less severe emphysema, so the prevalence of emphysema in smokers will be underestimated compare to incidence
Solution-use incident cases
Duration ratio bias
Point prevalence complement ratio bias
Temporal bias
Information bias

87. Incidence-Prevalence bias
PR과 IRR의 관계
Prev= incidence X duration X (1-prev) PR
* Duration ratio bias
* Point prevalence complement ratio bias

88. Duration ratio bias Type of selection bias
드문 질환에서 이환기간이 노출여부와 상관없이 동일하다면 비뚤림 발생하지 않음
노출여부에 따라 질병 이환기간이 다를 때 발생
만성질환의 경우 질병의 duration이 생존기간과 관련이 있기 때문에 이런 경우 생기는 bias가 survival bias

89. Point prevalence complement ratio bias
이환기간이 동일하다면, PR이 IRR을 과소측정하는 경향이 발생
노출그룹의 유병률: 0.04, 비노출그룹 유병률: 0.01
PR : 4
Point prevalence complement ratio=0.96/0.99=0.97
노출그룹의 유병률: 0.4, 비노출그룹 유병률: 0.1
Point prevalence complement ratio=0.6/0.9=0.67
PR, 유병률 크면 → bias 크기 커짐

90. Selection bias -- Berkson’s bias
Admission-rate bias
Cases and/or controls selected from hospitals
Result from differential rates of hospital admission for cases and controls
If hospital based cases and controls have different exposures that population based, OR will be biased.
E.g., If hospital controls are less likely to have exposures, OR will be over-estimated.
E.g., Case control for pancreatic cancer and coffee drinking: Controls were selected from GI patients. However, GI patients are less likely to drink coffee that population. OR was artificially increased.
Solution: use population based control, or controls with disease not related to the exposure

91. Temporal bias 시간적 선후관계가 모호 질병의 위험요인 검정 측면에서의 결정적 단점 예: 영양결핍과 우울증 연구
시간적 경과에 따른 변동이 없는 노출요인의 경우에는 이러한 제한점에 구애 받지 않음 – 유전적 요인
시간적 선후관계가 뒤집어져 있는 연구는 비추
예: 가설) 식이요인이 초경나이에 미치는 영향
대상) 중년여성을 대상으로 초경나이와 최근
의 식이습관 조사
전체 유병환자 중 Incident cases만 포함하여 분석함으로 단점을 최소화  또 다른 bias ?
Historical information 으로 단점 최소화

92. screening is most likely to pick up less aggressive cancers, because they have a longer interval of being visible on scans while remaining asymptomatic

93. you find out something earlier but don’t actually change the outcome, and therefore the apparent survival after diagnosis is longer without better survival

94. Simpson’s paradox
aggregated
disaggregated

95. Simpson’s paradox
Aggregated and disaggregated data tell two different stories
       치료 종류        환자 수   성 공   실 패    성공률(%)
합계 (n=700)
  개복술             350      273                78
  경피술             350           61           83
돌의 크기 < 2cm (n=357)
  개복술              87              6          
  경피술             270     234    36           87
돌의 크기 ≥ 2cm (n=343)
  개복술             263                      
  경피술              80              25          

96. 단면조사연구 정리 특정 시점 또는 짧은 기간 동안 표본 추출조사 – “스냅 사진” 장점 단점 편리하고 비용 효과적
여러 노출과 질병 연구 가능
가설 생성 가능
일반적 인구집단을 대표 단점
시간적 선후관계 모호
생존자만 연구, 비뚤림 가능
짧은 이환 기간의 질환은 과소측정

97. Any question?
If you tell the truth you don't have to remember anything. by Mark Twain 1894