Flashcards in Test 2 Deck (26):
What are the three goals of Analyzing Data?
1. Determine the magnitude of the association--use measures of associations and impact.
2. Rule out the role of chance in the results by doing confidence intervals and hypothesis is testing.
3. Rule out confounding by restriction or statisical adjustment for potential confounders.
What are the Measures of Disease Association?
The chance of something happening can be expressed as a risk or as an odd:
Risk = The chances of something happening / the chances of all things happening
Odds= The chances of something happening/ the chances of it not happening
Properties of the Relative Risk
1. Ranges from 0 to infinity ( i.e. cannot be negative)
2. If RR =1 then there is no association
3. If RR > 1 then there is a positive association
4. If RR < 1 then there is a negative association
Properties if the Odds Ratio
1. Regardless of how the data are sampled, the OR will remain the same.
2. If has similar properties to the RR in terms of range, magnitude, and statistical significance
3. Under the conditions of a rare disease, the odds ratio will be a decent approximation to the "true" relative risk
Odds Ratio Calculation?
OR = odds of exposure: given disease / odds of exposure: given no disease = a/c divided by b/d
OR= ad/ bc
Attributable Risk (AR)
The incidence of disease in the exposed population whose disease can be attributed to the exposure.
AR= R1- R0
Surveillance is the continued watchfulness of the trends of incidence and the systematic collection, consolidation, and evaluation of mortality and morbidity data and other relevant data and the distribution of the data to all who need to know.
List the essentials of a good surveillance system
Collection of relevant data
Analyze and interpret data
distribution of relevant data to all necessary parties
Name 3 types of Surveillance
Who reports surveillance data
Doctors, nurses, ICP, laboratories, hospital epidemiologist, other healthcare professionals
List 5 Wilson's criteria
1. The disease must be an important health concern
2. Diagnosis and treatment must be cost effective
3. Natural history of disease must be understood
4. Case findings must be continuous
5. Test must be simple, accurate, acceptable, sensitive and specific
What kind of measure is attributable risk?
Measure of impact
Is attack rate an incidence?
What are the two measures used to quantify the distribution of disease occurrence?
Incidence and Prevalence
What is Wilson's criteria?
A guideline for screening of diseases
What kind of measure is Relative Risk?
measure of association
What kind of measures is Odds Ratio?
Measure of association
What are 3 types of Rates?
Attributable Risk Percent (ARP)
Proportion of all cases in a general population that can be ascribed to a specific risk factor.
ARP= (incidence in total population)- (incidence in unexposed group)
Factors that Increase Prevalence
1. Longer duration of the disease
2. Prolongation of life of patient without a cure.
3. Increase in new cases (increase in incidence).
4. Out-migration of healthy people
5. In-migration of susceptible people
6. Improved diagnostic facilities (better reporting)
The complete state of physical, mental, and social well-being and not merely in the absence of disease or infirmity.
Measurements of Health and Diseases is required for:
Prevention of disease
Planning Health Services
How do you know if measurements are valid?
if a variable is a valid measure of a property if it is relevant and appropriate as a representation of that property.
4 Properties of the Relative Risk?
1. Range from 0 to infinity (I.e. cannot be negative).
2. If RR= 1 then there is no association
3. If RR> 1 then there is a positive association
4. If RR <1 then there is a negative association
The 3 properties of the Odds Ratio
1. Regardless of how the data are sampled t the OR will remain the same.
2. It has similar properties to the RR in terms of range, magnitude and statistical significance.
3. Under the condition of a rare disease, the odds ratio will be a decent approximation to the "true relative risk"