PSY1022 WEEK 8 DISC 4 Flashcards
MANIPULATION
The researcher manipulates one variable by changing its value from one level to another. A second variable is observed (measured) to determine whether the manipulation causes changes to occur.
- manipulated variable is the independent variable.
- observed variable is the dependent variable.
CONTROL
The researcher must exercise control over the research situation to ensure that other extraneous variables do not influence the relationship being examined.
- who is in the study and what happens.
PARTICIPANT VARIABLES
Characteristics such as age, gender, and intelligence that vary from one individual to another. Whenever an experiment compares different groups of participants (one group in treatment A and a different group in treatment B), researchers must ensure that participant variables do not differ from one group to another.
ENVIRONMENTAL VARIABLES
Characteristics of the environment such as lighting, time of day, and weather conditions. A researcher must ensure that the individuals in treatment A are tested in the same environment as the individuals in treatment B.
HOLDING VARIABLE CONSTANT
One way of controlling variables. eg. only using 10 year olds. Holds age constant.
ANTECEDENT CONDITIONS
Independent variable.
Conditions that were manipulated prior observing the independent variable.
CONTROL CONDITION
Individuals in a control condition do not receive the experimental treatment. Instead, they either receive no treatment or they receive a neutral, placebo treatment. The purpose of a control condition is to provide a baseline for comparison with the experimental condition.
- control group
EXPERIMENTAL CONDITION
Individuals in the experimental condition do receive the experimental treatment.
Receives some level of the independent variable.
- experimental group
BETWEEN-SUBJECTS DESIGN
An experiment in which different subjects are assigned to each group.
POSTTEST-ONLY CONTROL GROUP DESIGN
An experimental design in which the dependent variable is measured after the manipulation of the independent variable.
- half students taught studying device, then memory test performed.
PRETEST/POSTTEST CONTROL GROUP DESIGN
An experimental design in which the dependent variable is measured both before and after the manipulation of the independent variable.
CONFOUND
An uncontrolled extraneous variable or flaw in an experiment.
- harder in psych than other sciences due to human variability.
INTERNAL VALIDITY
The extent to which the results can be attributed to the manipulation of the independent variable rather than to some confounding variable.
NONEQUIVALENT CONTROL GROUP
Threat to internal validity.
When subjects in the control and experimental groups are not equivalent at the beginning of the study.
- can use random sampling and random assignment to minimise.
HISTORY EFFECT
Threat to internal validity.
When an outside event that is not part of the manipulation of the experiment could be responsible for the results.
- what else is going on in participants lives.
- can use equivalent control group to minimise
MATURATION EFFECT
Threat to internal validity.
When naturally occurring changes within the subjects are responsible for the observed results.
- can be overcome with a control group of equivalent subjects.
- can use equivalent control group to minimise
TESTING EFFECT
Threat to internal validity.
When repeated tests lead to better or worse scores.
- can use equivalent control group to minimise
REGRESSION TO THE MEAN
Threat to internal validity.
When extreme scores, upon retesting, tend to be less extreme, moving towards the mean.
- can use equivalent group with extreme scores to minimise
INSTRUMENTATION EFFECT
Threat to internal validity.
Fault in measuring device.
- measuring device can be a human. More likely to be inconsistent.
- can use equivalent control group to minimise
MORALITY (ATTRITION)
Threat to internal validity.
Most studies have dropouts or deaths. Usually even across groups.
- of concern when not equal.
DIFFUSION OF TREATMENT
Threat to internal validity.
When observed changes in the behaviors of subjects may be due to information received from other subjects.
- eg. Uni students might talk to other students about the experiment. These other students are now compromised.
EXPERIMENTER EFFECT (BIAS)
Threat to internal validity.
When the researcher consciously or unconsciously affects results of the study.
- Clever Hans the counting horse.
- use blind or double blind procedure
SUBJECT EFFECT
Threat to internal validity.
When the subject, consciously or unconsciously, affects the results of the study.
- people know they are being observed and may not act naturally.
- or try to be “good” subjects
- similar to reactivity.
FLOOR EFFECT
Threat to internal validity.
A limitation of the measuring instrument that decreases its capability to differentiate between scores at the bottom end of the scale.
eg. measuring in kg when difference is in grams.
CEILING EFFECT
Threat to internal validity.
A limitation of the measuring instrument that decreases its capability to differentiate between scores at the top end of the scale.
eg. measuring elephants on bathroom scales.
EXTERNAL VALIDITY
The extent to which the results can be generalized beyond the subjects used in the experiment and beyond the laboratory in which the experiment was conducted.
COLLEGE SOPHOMORE PROBLEM
An external validity problem that results from using mainly college sophomores as subjects in research studies.
- but doesn’t negate study.
ARTIFICIALITY CRITICISM
Caution when generalizing from the laboratory setting to the real world.
EXACT REPLICATION
Repeating a study using the same means of manipulating and measuring the
variables as in the original study.
Supports external validity.
CONCEPTUAL REPLICATION
A study based on another study that uses different methods, a different manipulation, or a different measure.
SYSTEMATIC REPLICATION
A study that varies from an original study in one systematic way— for example, by using a different number or type of subjects, a different setting, or more levels of the independent variable.
CORRELATED-GROUPS DESIGN
An experimental design in which the subjects in the experimental and control groups are related in some way.
- within-subjects design
- matched-subjects design
WITHIN-SUBJECTS DESIGN
A type of correlated-groups design in which the same subjects are used in each condition.
- need fewer subjects (no control group)
- less time
- same individuals mean less individual differences. Increases statistical power.
- but subject to order effects and demand characteristics, and carryover effect
ORDER EFFECTS
A problem for within-subjects designs in
which the order of the conditions has an effect on the dependent variable.
- same as testing effects
- can use counterbalancing
COUNTERBALANCING
A mechanism for controlling order effects either by including all orders of treatment presentation or by randomly determining the order for each subject.
LATIN SQUARE
A counterbalancing technique to control for order effects without using all possible orders.
- each condition should appear once in the ordinal position
- each condition should precede and follow every condition once.
MATCHED-SUBJECTS DESIGN
A type of correlated-groups design in which subjects are matched between conditions on variable(s) that the researcher believes is (are) relevant to the study.
- like between-subjects design different subjects in each condition
- but subjects are matched on a relevant variable (eg. weight, age)
- like within-subjects design but no carryover effect.
- high morality rate, matching is hard.
CARRYOVER EFFECT
When the subjects “carry” something with them from one condition to another.
- problem with within-subjects design
- also with drug trials, etc.
BETWEEN-SUBJECTS SUMMARY
Different subjects are randomly assigned to each condition
+ve - testing effects and demand characteristics are minimised.
-ve - more participants and time needed. Groups may not be equivalent. Less statistically powerful.
WITHIN-SUBJECTS SUMMARY
The same subjects are used in all conditions
+ve - fewer participants and less time needed. Equivalency of groups ensured. More powerful statistically.
-ve - testing effects and demand characteristics
MATCHED-SUBJECTS SUMMARY
Subjects are randomly assigned to each condition after they are matched on relevant variables.
+ve - testing effects and demand characteristics minimised. Groups fairly equivalent. More powerful statistically.
-ve - matching is very difficult. Need more participants.
NON MANIPULATED INDEPENDENT VARIABLE
The independent variable in a quasiexperimental design in which subjects are not randomly assigned to conditions but rather come to the study as members of each condition.
(eg. smokers or non smokers)
- subject variable.
- if this is what is being studied then by default is quasi-experimental.
- John Snow and cholera. NMIV is water company, dependent variable is cholera.
CORRELATIONAL METHOD SUMMARY
Two measured variables.
Conclusion: The variables may be related in some way. Can be used for prediction.
But: Cannot conclude that the relationship is causal.
QUASI EXPERIMENTAL METHOD SUMMARY
Typically one nonmanipulated independent variable and one measured dependent variable.
Conclusion: Systematic differences have been observed between two or more groups, but we cannot say that the nonmanipulated independent variable definitely caused the differences.
But: Due to confounds inherent in the use of nonmanipulated independent variables, there may be alternative explanations for the results.
DEVELOPMENTAL DESIGN
Type of quasi experimental design in which age is used as the non manipulated independent variable.
- cross sectional
- longitudinal.
CROSS SECTIONAL DESIGN
A type of developmental design in which subjects of different ages are studied at the same time.
- less attrition and expense than longitudinal
- problem is cohort effect
COHORT
A group of individuals born at about the same time.
- a generation.
COHORT EFFECT
A generational effect in a study that occurs when the era in which individuals are born affects how the respond in the study.
- old people and computers.
LONGITUDINAL DESIGN
A type of developmental design in which the same subjects are studied repeatedly over time as they age.
- no cohort effect
- but expensive and time consuming, attrition problems.
SEQUENTIAL DESIGN
A developmental design that is a combination of cross sectional and longitudinal design.
- more expensive and time consuming than either
- but can examine cohort effects.
SINGLE-CASE DESIGN
A design in which only one participant is used.
- version of within-subject experiment
- often used in clinical settings.
SMALL-N DESIGN
A design in which only a few subjects are studied.
- often used in clinical settings.
EXPERIMENTAL RESEARCH GOAL
Explanation; to establish a cause and effect relationship between two variables.
- manipulate
- measure
- compare
- control
REDUCING THREATS TO INTERNAL VALIDITY
- randomisation
- matching
- holding constant
GENERALISABILITY
- how well a sample generalises to the population
- how well the findings of one study generalise to another research study
- how well the findings generalise to the real world
POWER
The probability of detecting differences between
treatment conditions, if there are really differences to detect.
POWERFUL DESIGN
A powerful design is one that reduces variability
through good use of randomisation and controls, therefore:
- within-subjects most powerful
- matched-subjects come next
- between-subjects are the least powerful
