Collecting data, principles of experimental design, types of designs, problems with experiments and observations

experiment

the process of applying a treatment and observing its effects

• two groups: treatment and control

observational study

the process of observing data without modifying subjects

• can not describe cause-effect relationships analyzing records

response variable

the variable that measures the outcome of the study

explanatory variable

explains or influences the changes in response

experimental unit

the object upon which the response is being measured

treatment

the specific experimental condition applied to the units/subjects

variability

differences in the response variable

experimental error

variability among observed values of the response variable or units with the same treatment

lurking variables

a variable that is not among the explanatory variables but does influence the interpretation of the relationship btwn response and explanatory

confounding variables

two variables are confounded when the effects on the response variable can not be distinguished from each other

control group

receives no treatment and used as baseline

replication

be able to repeat the experiment to measure the effect of each treatment on individuals

randomized designs

randomly assigning participants to each treatment group

randomized block designs

divides units into blocks such that variability in each block is less than btwn blocks. Participants in each block are assigned randomly to treatment

matched pairs

participants grouped into pairs based on one or more blocking variables. Then within each pair random treatments are assigned

placebo

a false drug/treatment that subjects believe is real

placebo effect

the tendency to react to a treatment regardless of its actual effectiveness

hawthorne effect

people behave differently when they know they are being watched

researcher bias

• when the researcher's beliefs or expectations influence the research design or data collection process

• non-random assignment of treatment or bad reporting

blinding

when people do not know how subjects/treatments are assigned

single blind

subjects/technicians are blinded

double blind

subjects/technicians and judges/researchers are blinded