Study guide test 2 Book Online class notes Chapter 5 An experiment is a process of observation to be carried out in a situation expressly brought about for that purpose Experiments involve Taking action Observing the consequences of that action Especially suited for hypothesis testing The Experimental Model consequences Experiments minimally involve 1 taking action and 2 observing the Social science experiments also involve attempting to control the conditions under which the experiment is conducted Especially suited for hypothesis testing Scientific experiments have their own notation X treatment independent variable Y outcome dependent variable Z rival causal factor O observation measurement of dependent variable E equivalence randomization or matching 1 2 time points The Classical Experiment Involves three major pairs of components Independent and dependent variables Independent variable takes the form of an experimental stimulus that is either present or absent Alch abuse example how often subjects used alch is the dependent and exposure to a video about alch effects is the independent variable o It is possible for a variable to serve as an independent variable in one experiment and an dependent variable in another o The independent variable takes the form of a dichotomous stimulus that is either present or absent o It varies i e is independent in our experimental process o IV cause DV effect Dependent Variables The outcome the effect we expect to see Depends on the IV 1 Might be physical conditions social behavior attitudes feelings or beliefs KC several including crime fear of crime perceptions of the police traffic accidents etc Pretesting and post testing o Subjects are measured on a dependent variable pretested exposed to a stimulus that represents an independent variable post tested o Differences noted between the first and second measurements on the dependent variable are then attributed to the influence of the independent variable Subjects are initially measured in terms of the DV prior to association with the IV pretested Then they are exposed to the IV Then they are premeasured in terms of the DV post tested Differences noted between the measurements on the DV are attributed to influence of IV Experimental and control groups o The traditional way to offset the effects of the experiment itself is to use a control group testing exposed o Experimental group exposed to whatever treatment policy initiative we are o Control group very similar to experimental group except that they are NOT o If we see a difference we want to make sure it is due to the IV and not to a difference between the two groups What is the relationship between experimental designs and causal inference Experiments and Causal Inference Experimental design ensures Cause precedes effect via taking posttest Empirical correlation exists via comparing pretest to posttest No spurious 3rd variable influencing correlation via posttest comparison between experimental and control groups and via randomization Experiments potentially control for many threats to the validity of causal inference but researchers must remain aware of these threats The experimental design ensures that the cause precedes the effect in time by taking post test measurements of the dependent variable after introducing the experimental stimulus The second criterion for causation an empirical correlation between the cause and affect variables is determined by comparing the pretested in which the experimental stimulus is not present to the post test for the experimental group after the experimental 2 stimulus is administered A change in pretest to posttest measures demonstrates correlation The final requirement is to show that the observed correlation between cause and effect is not due to in the influence of a third variable The classical experiment makes it possible to satisfy this criterion for cause in two ways o 1 Posttest measures for the experimental group stimulus present are compared with those for the control group Stimulus not present If the observed correlation between the stimulus and the dependent variable is due to some other factor then the two posttest scores will be similar o 2 Random assignment produces experimental and control roups that are equivalent and will not differ on some other variable that could account for the empirical correlation between cause and effect Validity Threats Threats to internal validity The classical experiment is designed to satisfy the three requirements for demonstrating cause and effect relationships But what about threats to the validity of the causal inference The problem of threats to internal validity refers to the possibility that conclusions drawn from experimental results may not accurately reflect what went on in the experiment it self Conclusions about cause and effect may be biased in some systematic way o History historical events may occur during the course of the experiment that confound the experimental results Ex hospitalization of a popular athlete for acute alcohol poisoning during an experiment on reducing alcohol use is an example o Maturation people are continuously growing and changing whether in an experiment or not and those changes affect the results of the experiment In a long term experiment the fact that the subjects grow older may have an effect In shore experiments the may become tired sleepy bored hungry o change in other ways that affect their behavior o Testing the process of testing and retesting influences people s behavior and thereby confounds the experimental results o Instrumentation if the measurements are being made by the experimenters their procedures may change over the course of the experiment Problem of reliability In general testing refers to changes in how subjects respond to measurement If 3 different questionnaires about prejudice are used in pretest and posttest measurements instrumentation is a potential threat o Statistical Regression sometimes its appropriate to conduct experiments on subjects who start out with extreme scores on the dependent variable This is known as regression to the mean deals with extreme cases ex statisticians often point out that extremely tall people as a group are likely to have children shorter than themselves and extremely short people have children taller than themselves The danger is that change occurring by virtue of subjects starting out in extreme positions will be attributed erroneously to the effects of
View Full Document
Unlocking...