Textbook Notes (363,339)
United States (204,494)
PUBHLTH 1 (8)
Chapter 7

# PUBHLTH 1 Chapter 7: Chapter 7 Notes Premium

4 Pages
88 Views

School
University of California - Irvine
Department
Public Health
Course
PUBHLTH 1
Professor
Zuzana Bic
Semester
Spring

Description
Chapter 7 Statistics: Making Sense of Uncertainty Science of epidemiology all public health rests on statistics bc concerned with populations, relies on statistics to provide and interpret data Term statistics refers to numbers that describe the health of populations and the science that helps to interpret those numbers Science of statistics is set of concepts and methods used to analyze data in order to extract information Makes possible translation of data into information about causes and effects, health risks, and disease cures The Uncertainty of Science In many cases, not enough data to give degree of certaintyinsufficient data to allow for valid conclusion Contradictory results from epidemiologic studies are common, bc many sources of errors in the research E.g. bias, confounding variables, etc Pressure from politicians eager to get credit for supporting womens health led to pretense of scientific certainty where none existed Most scientific information is of probable nature.. not certainty. What [is concluded] is the best opinion at the moment, and things may be updated in the future. Probability Probabilities used to describe the variety and frequency of past outcomes under similar conditions as a way of predicting what should happen in the future Improbably happens more often than most people think One concept used to express degree of probabilityimprobability is p value P value expresses probability that the observed result could have occurred by chance alone. P value of 0.05 means if experiment repeated 100 times, same answer would result 95 times while 5 would yield different results P value of 0.05 or less arbitrarily taken as criterion for a result to be considered statistically significant Another way to express degree of certainty of experimental result is by calculating confidence interval Range of values within which the true result probably falls The narrower the confidence interval, the lower chance of random error Confidence intervals often expressed as margins of error e.g + 3 Wrong to place too much confidence in experiment for its low p value or narrow confidence interval Low pvalue can cause biasconfounding Law of Small Probabilities probable is not always what happens Most improbable things bound to happen occasionally recover spontaneously from terminal illness Another consequence is phenomenon of cancer clusters
More Less

Related notes for PUBHLTH 1

OR

Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.