Ch 10 Experimental Research Flashcards
experiment
a controlled method of observation in which the value of one or more independent variables is changed to assess the casual effect on one or more dependent variables
laboratory experiments
conducted in artificial settings that are constructed in such a way that selected elements of the natural environment are simulated and features of the investigation are controlled
field experiments
are conducted in natural settings as people go about their everyday affairs
experimental stimulus (or experimental treatment)
an independent variable that is directly manipulated by the experimenter to assess its effect on behavior
experimental group
a group of subjects exposed to the experimental stimulus
experimental condition
describes the group of people who receive the experimental stimulus
symbols in logic of experimentation
O = observation or measurement of dependent variable X = exposure of people to the experimental stimulus or independent variable R = random assignment to conditions
experimental variability
variation in the dependent variable produced by the independent variable and is the focus of interest in experiments
extraneous variability
variation in the dependent variable from any source other than the experimental stimulus and it makes inferences about change in the dependent variable difficult
control variables
variables whose value is held constant in all conditions of the experiment
control group
group of research subjects who are provided the same experiences as those in the experimental condition with a single exception: the control group receives no exposure to the experimental stimulus
control condition
refers to the state of being in a group that receives no experimental stimuli
matching
involves matching individuals in the experimental group with similar subjects for a control group
random assignment
uses chance to reduce the variation between experimental and control groups
blocking
combination of matching and randomization. the subjects are first matched on one or more key variables to form blocks of similar subjects. members of each block then are randomly assigned to the experimental and control conditions
internal validity
refers to whether the independent variable actually produces the effect that it appears to have had on the dependent variable ; it is concerned with ruling out extraneous sources of variability to the point where we have confidence that changes in the dependent variable are caused by independent variable
history
is more of a problem for field experiments
concerns events other than the experimental stimulus that occur during the course of experiment and that could affect dependent variable
maturation
refers to change occurring within experimental subjects as a result of the passage of time
testing
may occur whenever subjects are exposed to a measurement device more than once
instrumentation
refers to the fact that the way in which variables are measured may change in systematic ways during the course of an experiment, resulting in observations being measured differently at the end of an experiment than they were at beginning
statistical regression
arises any time subjects are placed in experimental or control groups on the bias of extremely high or low scores on a measure in comparison to the average score for the whole group
selection
a threat to internal validity when the kinds of people who are selected for one experimental condition differ from those who are selected for other conditions
experimental attrition
occurs when there is a differential dropout of subjects from the experimental and control groups
pre experimental designs
lack both the random assignment to conditions and the control groups that are such a central part of good experimental designs
true experimental designs
more complex and use randomization and other techniques to control the threats to internal validity
quasi-experimental designs
special designs that are used to approximate experimental control in non experimental settings
external validity
concerns the extent to which casual inferences made in an experiment can be generalized to other times, settings, or groups of people
demand characteristics
subtle, unprogrammed cues that communicate to subjects something about how they should behave
experimenter’s expectations
can be communicated to subjects in such a subtle way that neither the experimenter nor the subjects are aware that the communication has taken place
double blind experiment
neither the subjects nor the experimenter knows which people are in the experimental condition and which are in the control condition