OBJ - Stats I & II Flashcards
Statistics vs Biostatistics
Statistics:
A branch of mathematics dealing with the collection, analysis, interpretation, and presentation of numerical data
Biostatistics:
Statistics applied to the analysis of biological data
Epidemiology vs. Clinical Epidemiology
Epidemiology:
- Fletcher: The study of disease occurrence in human populations
- Last: The study of the distribution and determinants of health-related states or events in specified populations and the application of this study to the control of health problems
Clinical Epi:
The science of making predictions about individual patients based on observations in groups of similar patients
Evidence-based medicine (EBM)
(1) The application of clinical epidemiology to the care of patients
(2) the conscientious, explicit, and judicious
use of current best evidence in making
decisions about the care of individual patients.
Sampling of populations
1 part of a population
May be representative or not, randomized or not
Make inferences based on sample
Bias vs. Chance
Bias (systematic error)
- looking at accuracy
Selection Bias:
Occurs when comparisons are made between
groups of patients that differ in ways other
than the main factors under study, and these
differences affect the outcome of the study
Measurement Bias:
Occurs when the methods of measurement
are different in different groups of patients
Chance (random error)
- looking at reliability
Internal validity
– Do the results reflect the truth for the sample?
External validity
– Generalizability from sample to population
– Do the results reflect the truth for the population?
Generalizability of medical information
– Do the results apply to my patient?
Incidence
Number of people that develop the disease, during a specified period of time in a population at risk for developing the disease
Measurement of risk
Prevalence
Number of people that already have the disease
Disease duration
@ specific time/time period # existing cases / number in the population
• Point Prevalence = snap shot
• Period Prevalence =
= point prevalence + incidence
• Lifetime Prevalence
= Period prev over a subject's whole life
Uses:
• Assess the public health impact of a specific disease in a community
• Obtain periodic estimates of disease occurrence to track changes in disease patterns over time
• Plan and allocate health resources
Limitations:
• Impact of patients who are able to survive disease (e.g. HIV/AIDS)
• Change in incidence
• Prevalence does NOT measure risk
Case-fatality
(Total number of deaths from a specific disease)
divided by
(Total number of people with the disease)
For one year
Infant-mortality
# deaths of infants under 1 year of age/ 1,000 live-births
For one year
Confounding factors
Distort or mask the true effect of the exposure or risk factor
- a risk factor for the outcome
- associated with the exposure
- not caused by the exposure
Descrip1ve Epidemiology
– Count cases
– Describe cases (person, place, time)
– Determine risk and burden of disease
Average Disease Duration
Average duration = prevalence/incidence
Relationship between incidence & prevlance
Think of sink analogy with water flowing in (incidence) & out (deaths or recovery)
