Observational Study Design: Widana Primaningtyas Fakultas Kedokteranuns

OBSERVATIONAL STUDY DESIGN Widana Primaningtyas Fakultas KedokteranUNS

DEFINITION “ a type of study in which individuals are observed or certain outcomes are measured; no attempt is made to affect the outcome.” (NIH-NCI)

• • •

An alternatives of the experimental study ( sometimes called a natural experiment) Attempt to understand cause and effect relationships The researcher is not able to control how subjects are assigned to groups and or which treatments each group receives

TYPES Observational uncontrolled study Observation only in one group of subject (crosssectional/ survey) No control group What(s) the problem then?

Observational controlled study Observation in different group of subject Major classification: cohort (presence of exposure) and case-control studies (absence or presence of a disease)

COHORT STUDY • A research study tat compares a particular outcome in a groups of individuals who are alike in many ways but differ by a certain characteristic. • A study in which people are exposed to some factor of interest at the start of the study and then followed over a time period sufficent to allow any effects of that exposure to occur and be measured. • Framingham study... Anyone know about it?

CROSS-SECTIONAL STUDY • An oservational study that involves the analysis of data collected from a population, or a representative subset, at one specific point in time. • This study looks at population at a single point in time. It examines the relationship between exposure and outcome prevalence in a defined population without regard to changes over time

• Classic type: survey • The data being collected once; quick and inexpensive • Good to find the prevalence of a particular case or disease; could not tell us anything about the cause or the best treatment might be

CASE-CONTROL STUDY • A study that compares two groups of people; those with the disease or condition under study (cases) and a very similar group of people who do not have the disease or condition. • A study in which a group of people who have a particular disease are observed to see wether their past exposures to some factors differ from those of a similar group who don’t have the disease.

• Typically examines multiple exposures in relation to an outcome; subjects are defined as cases and controls; and the exposure historiees are compared • Generally researchers enroll two to four times more controls than cases.

• Usually involve smaller numbers of people • Could be a either population based- all the cases and controls are randomly selected from same defined geographical population- or hospital based- all the cases and controls are selected from people attending a particular hospital. • Whis one is better; hospital based or population based? Why?

Case control study : using Odds Ratio (positive disease ratio/ negative disease ratio)  ratio p/q Cohort study : using Relative Risk (positive risk factor proportion/ negative risk factor proportion)  ratio p1/p2