This preview shows pages 1–10. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Outline Review of Public Health Studies 9/8/2011 Review of Public Health Studies Outline Outline 1 Measures of disease occurrence 2 Measures of Effect 3 Study Designs Review of Public Health Studies Measures of disease occurrence Measures of Effect Study Designs Caveat Much more can be written or said about virtually every slide in this lecture. PubH 8300 and PubH 8140 provide far more detail about all of the concepts I introduce here. My intention in this lecture is to give us a common point of understanding from which we can talk about statistics/probability, not to be comprehensive. Review of Public Health Studies Measures of disease occurrence Measures of Effect Study Designs Outline 1 Measures of disease occurrence 2 Measures of Effect 3 Study Designs Review of Public Health Studies Measures of disease occurrence Measures of Effect Study Designs Study Population A well defined group (cohort) of people It should be crystalclear who is in your cohort and who is not It should be defined in terms of time, as well Following people forward in time? when? A single point in time? when? Review of Public Health Studies Measures of disease occurrence Measures of Effect Study Designs Risk Consider a study population of all nondiabetic incoming male freshmen at UMN in Fall, 2010 academic year Let’s say we want to measure the proportion of these students who become diabetic by the last day of class, 2014 This proportion is called a risk Risk: The proportion of people in a study population who develop the outcome during some defined period of time Competing risks complicate matters somewhat as we’ll see later Also called incidence proportion Review of Public Health Studies Measures of disease occurrence Measures of Effect Study Designs Risk Example In our study of 7,327 (I couldn’t find the real number!) students, 612 of them develop diabetes by the last day of class 2014. 1 What is the risk of diabetes in this cohort? 2 How do we interpret it? 3 Can we use this risk in other contexts? 4 Are there any obvious flaws here? Review of Public Health Studies Measures of disease occurrence Measures of Effect Study Designs Rate We might consider other ways to measure the occurrence of disease Risk is intuitive, but it doesn’t account for the amount of time it takes to develop the outcome Rather than dividing the number of events by the total number of people in the study population, we could divide the number of events by the total amount of time people in the cohort spent at risk for disease This quantity is called a rate: number of events/total incidence time Also called an incidence rate, incidence density or hazard rate Review of Public Health Studies Measures of disease occurrence Measures of Effect Study Designs Example Say we follow 10 people for 10 years. Person 1 is followed for 2 years before developing disease and person 5 is followed for 7 years before developing disease. What is the incidence rate?...
View
Full
Document
This note was uploaded on 11/21/2011 for the course PUBH 7401 taught by Professor Richmaclehose during the Spring '11 term at Minnesota.
 Spring '11
 RichMacLehose

Click to edit the document details