Causality

TTIV & T.M: Expectancies of experiment staff

change among experimental subjects is due to positive expectancies of the staff who are delivering the treatment, rather than the treatment itself.

TTIV: Maturation

change in outcomes scores that involve lengthy treatment periods. Subjects may age, gain experience, or knowledge all part of the natural maturation experience and respond differently to the posttest

Quasi E.D: Before and After Designs

consisting of several before and after treatment comparisons involving the same variables but no comparison groups

Experiments

experimental research provides the most powerful design for testing causal hypotheses because it allows us establish confidently the first 3 criteria for causality (association, time order, non-spuriousness)

TTIV: History

external events. Things happening outside the experiment could change subject's scores.

Quasi E.D: Non-equivalent control groups

have experimental and comparison groups that are designated before the treatment occurs but are not created by random assignment

Criteria of causality: Non-spuriousness

when a relationship between two variables is not due to a third variation in a third variable

TTIV : Selection bias

when the subjects in your group are initially different. Ex. Harvard students are successful people but Harvard admits students who are likely to be successful. Maybe Harvard has no effect on them.

True experiments have at least 3 features that help us meet the 3 criteria to establish causality

1. Two comparison groups (in simplest, experimental and control group) which establish association 2. Variation in the ind variable before assessment of change in depe variable, time order. 3. Random assignment to the two or more comparison groups, non spuriousness

What is a experimental group?

the group of subjects that receives the treatment or experimental manipulation

Pretest

Measurement of an outcome (dependent) variable prior to an experimental change in a presumed independent for some reason. The pretest is the exact same as the posttest but is administered at a different time

Criteria of causality: Time order

The cause must come before its presumed effect. The variation in the presumed cause (ind) must occur before the variation in the presumed effect (depe)

What is a control group?

a comparison group that receives no treatment

Random assignment in experiments

a procedure by which experimental subject is placed in a group randomly. Not the same as random sampling of individuals from some larger population (does in fact not help at all if they are representative) What is does do is creates two or more equivalent groups, which is useful for ensuring internal validity, not generalizability

TTIV : Testing

taking the pretest can influence post test score by giving the subject an advantage by getting used to the test format

Quasi-Experimental Design

if a true experiment is not available ( too costly, not ethical, or treatment events already occurred) researchers can use this type to retain several components of experimental design but differ in important details. This is a research design in which there is a comparison group that is comparable to the experimental group in critical ways but subjects are not randomly assigned to the comparison and experimental groups.

What is the comparison group?

in an experiment, groups that have been exposed to different treatments, or values of the ind variable (e.g. a control group and an experimental group)

Experiment have ___ external validity

low

TTIV : Instrument Decay

measurement instruments of all sorts wear out producing different results for cases studied later in the research

Posttest

measurement of an outcome (dependent variable) after an experimental intervention or after a presumed independent variable has changed for some reason. The same as the prettiest but is administered at different time

TTIV : Endogenous Change

occur when natural developments in the subjects, independent of the experimental treatment itself, account for some or all of the observed change between pretest and posttest

What is causality?

occurs if variation in the independent variable is followed by variation in the dependent variable, when all other things are equal. 3 criteria to establish

TTIV: Contamination

occurs in experiment when the comparison and treatment groups somehow affect each other. If comparison groups know they are being compared, they might increase efforts just to be competitive.

TTIV : Mortality/ Attrition

occurs when comparison groups become different because subjects in one group are more likely to drop out for various reasons compared to subjects in the other group

TTIV & T.M: Hawthorne Effect

occurs when subjects of the treatment group change because of their participation in the study makes them feel special.

TTIV & T.M: Placebo Effect

occurs when subjects receive a treatment they expect to be beneficial and improve as a result of that self expectation rather than the treatment itself.

TTIV: Regression to the mean

occurs when subjects were chosen because of their extreme scores. Whenever you pick people for being on an extreme end of the scale, odds are that next time on the posttest they'll be more average, due to mathematical necessity, not treatment

Threats to Internal Validity: Non- comparable groups

occurs when the experimental group and the control group are not really comparable. That is when something interferes with the 2 groups being essentially the same at the beginning/end of a study

Criteria of causality: Association

sometimes call correlation. Am empirical or observed association between the independent and dependent variables. They must vary together such as when one goes up/down, the other goes up/down

TTIV: Treatment Misidentification

subjects experience a "treatment" that was not intended by the researcher. Some unknown or unidentified interviewing process is causing the outcome. 3 possible