S3) Epidemiological Investigation Flashcards
What is epidemiology?
Epidemiology is the study of the distribution and determinants of health-related states or events (including disease), and the application of this study to the control of diseases and other health problems
Which methods can be used to carry out epidemiological investigations?
- Surveillance and descriptive studies are used to study distribution
- Analytical studies are used to study determinants
Define statistics
Statistics is the collection, presentation, description and analysis of data (sometimes themselves called ‘statistics’) which are measurable in numerical forms
Prevalence is the measurement of existing case.
How can one calculate prevalence?
Calculated per 1000 people then converted to a percentage:
E.g. Today, 80 people have cancer out of 1,500 people
Prevalence = 80/1,500 = 53 per 1,000 = 5.3%
(numerator & denominator both refer to persons)
Incidence is the measurement of new cases.
How can one calculate incidence rate?
Incident rate is measured in events per persons per time (year):
E.g. 300 heart attacks in 50 000 factory workers over 1.5 years
Incidence rate = 300/(50 000 x 1.5) = 0.004 heart attacks per worker per year i.e. 4 heart attacks per 1000 workers per year
What is person-years and how do we calculate it?
‘Person-years’ is the sum of the total time of everybody followed up in a study
- E.g. 1 person followed up for 10 years +*
- 3 people followed up for 2 years +*
- 7 people followed up for 0.1 years*
- = (1 × 10) + (3 × 2) + (7 × 0.1)*
- = 10 + 6 + 0.7*
- = 16.7 person-years or 16.7 p-y*
How else can one calculate prevalence?
Prevalence= Incidence x Duration of Disease
In terms of the relationship between incidence and prevalence, state how prevalence is affected by the following”
- Increase incidence?
- Keep patients alive longer?
- Cure more patients?
- Kill more patients?
- Increase incidence? → increase prevalence
- Keep them alive longer? → increase prevalence
- Cure more patients? → lower prevalence
- Kill more patients? → lower prevalence
Using an example, explain the relationship between tendency and observation
Our observed value is our best estimate of the true or underlying tendency:
- Tendency: the true or underlying proportion of diabetic patients with foot problems is 15%
- Observation: in a random sample of 1,000 diabetics, the number with foot problems was 123, i.e. 12.3%
What is a hypothesis?
A hypothesis is a statement that an underlying tendency of scientific interest takes a particular quantitative value
- E.g. The coin is fair (i.e. probability of heads is 0.5)*
- E.g. The new drug is neither better nor worse than the standard treatment (i.e. ratio of survival rates = 1.0)*
How do we test hypotheses?
Calculate the probability of getting an observation as extreme as, or more extreme than, the one observed assuming that the stated hypothesis is true
What is the significance of small probability in hypothesis testing?
Either something very unlikely has occurred with the true hypothesis or the stated hypothesis is wrong
The calculated probability is called the p-value.
How can one interpret a p-value < 0.05?
- “Reasonable to reject the stated hypothesis”
- “Observations are statistically significant”
- “Data inconsistent with the stated hypothesis”
How can we interpret a p-value ≥ 0.05?
“P-value ≥ 0.05” does not mean that the hypothesis has been proven i.e. failing to reject the hypothesis does not mean that the hypothesis has been proven
What is a 95% confidence interval?
The 95% Confidence Interval is the range within which we can be 95% certain that the true value of the underlying tendency really lies
E.g. The observed value is 0.87 and the 95% confidence limits are 0.59 and 1.14:
