Study Guide Exam 2 updated Flashcards
What is internal validity?
Answers the research question and provides evidence by controlling variance enough to provide a clear picture of the relationship between the IV and DV
Must eliminate alternate explanations.
Results must reflect object reality.
Must be certain the change in the DV is caused by the experimental treatment and not by factors that could mimic the effect of treatment.
What is external validity?
degree that generalizations can be made or transferred outside of the confines of the study
The research design serves to unite the ________, _________, and _____________
the research questions, the supporting evidence, and conclusions of the study.
Define research design and what are the two main branches?
Specific set of tactics to carry out the strategy
they can be quantitative and qualitative
what are types major types quantitative design?
group and single subject design
(1st Major type of quantitative) Explain group design
1 or more groups of participants are exposed to 1 or more levels of the IV
Average performance of the group of participants on the DV is examined to determine the relationship between the IV and DV
gathers quantitative data from a group of subjects to determine a cause-effect relationship or descriptive association between variables
What are some group research designs?
between-subjects design
within-subjects design
mixed design
Explain Between-subject Design
“The performances of separate groups of subjects are measured and comparisons are made between the groups”
Ex. Comparison of the
‘average’ behavior of one group of subjects to the
‘average’ of another group.
IV applied to experimental group but not control group
Need equivalence of both groups
may be bivalent
Random assignment to groups (best for large groups)
Subject matching (match members of two groups)
Explain within-subjects design
The performance of the same subjects is compared in different conditions
compare the average behavior of a group of subjects in two different conditions.
Performance of the same subjects is compared in different conditions i.e. longitudinal studies.
All conditions should be equivalent except for application of the various levels of IVs.
Have to assure that changes in DV are attributed to IV rather than extraneous variables.
(SAME STUDY AND GROUP OF PEOPLE; TREATMENT X AND Y AND GIVE IT TO BOTH PEOPLE)
Explain Mixed design
includes both types of comparisons in the same study
Study one IV with a between subjects comparison and the other IV with a within-subjects comparison.
Study the effect of an IV on a DV with two different types of subjects.
i.e. Experimental Group receives Tx1 and Tx2
Control groups get no tx.
Comparison between groups (Treatment and control groups) and within (between Tx1 and Tx2 Experimental group).
T/F between subjects can be bivalent, multivalent, or parametric
True
What is an aside design?
not uncommon: purported “mixed design” includes quantitative design and anecdotal information
(2nd Major type of quantitative) Explain single subject design
individual participants, rather than the average group performance
Analyze the factors that contribute to their success of failure of the treatment
May examine the behavior of more than 1 participants, but the data obtained from each participant is examined individually
What are the various types of single subject design?
Withdrawal design ABA design ABAB design Reversal Design Multiple Baseline design Changing-Criterion Designs
Explain withdrawal design/reversal design
Compares subjects behavior at times when the IV is present with the behavior observes when the IV is absent or withdrawn
Include at least two time segments:
- Baseline segment (A) = nonintervention.
- Treatment segment (B)= intervention
- Treatment-reinstatement segment (B again)
the magnitude of the DV is measured by the duration, frequency, and magnitude of occurrence
T/F ABA design controls for confounding variables; because a “well controlled design”; experiment ends w/ reinstatement of treatment
True
Explain ABA design
The simplest form of a single-subject experiment
A: baseline
B: second/treatment segment
A: the measurement of the DV at specific intervals is continued once the treatment has been terminated or withdrawn (treatment withdrawal segment)
Explain ABAB
another common withdrawal exp in which the withdrawal segment is followed by a second treatment segment (treatment-reinstatement segment)
advantage: it shows that intervention was responsible for the change by ending with a reinstatement of treatment
Explain reversal design
similar to withdrawal designs but instead of simply withdrawing treatment the researcher returns the behavior toward baseline by reinforcing another or alternative behavior that is incompatible with the target behavior trained previously
they can be: ABA, ABAB, ABACA
in each case a segment that follows treatment is ass with an active reversal rather than mere intervention withdrawal
Multiple Baseline Design
By initiating intervention following different baselines
sustained for different time lengths the relationship
between the DV (target behavior) and IV (intervention)
can be established. = study the effects of one intervention on several dependent variables
Applied across subjects and behaviors so that one intervention is provided and the same target behavior is measured across several subjects who share common relevant characteristics
* Overcomes effects of maturation, timing of training, and amount of training (e.g., threats to internal validity) * No withdrawal or reversal of treatment is necessary (no ethical concerns with stopping an intervention)
Why would I want a study with multiple baseline?
It’s generalizable because they did it in 3 different settings, across subjects and behaviors, and no withdrawal or reversal treatment is necessary
Explain changing-criterion designs
The effect of the IV is shown by successive changes in the DV to match a stepwise performance criterion.
the effect of changing the criterion for reinforcement establishes the functional relationship between the DV and IV
After baseline, treatment is introduced in consecutive segments, each one with a a higher criterion for behavioral improvement than the treatment that precedes it.
Subject are expected to become more proficient at the target behavior with each successive segment.
Each segment serves as a baseline for the following treatment segment.
What are examples of quanlitative studies?
A.Participatory Designs B.Non participatory designs C.Sequential exploratory Design D.Explanatory design E.Concurrent triangulation design F.Concurrent nested design G.Mixed methods **
Explain participatory
investigators participate on some level with participants.
“Conducting research with them and not on them.”
Explain non participatory
Researcher does not interact with participants.
Explain Mixed-methods design
both quantitative and qualitative.
Explain sequential exploRatory design
qualitative data are collected and analyzed first then quantitative data are then obtained, primarily to supplement the qualitative data
Explain sequential exploNatory design
quantitative data are collected and analyzed first, augmented by qualitative data
-implemented to explain relationships and help make since of research results when unexpected
What is a concurrent triangulation design?
quantitative and qualitative data are given equal priority
What is concurrent nested design?
priority is given to either the quantitative or qualitative components
What are factors that threaten internal validity?
History, maturation, pretesting, instrumentation, statistical regression, differential subject selection, and attrition.
Why is a pilot research done?
To protect internal and external validity, the design, methods and procedures used in a quantitative study are fixed and invariable.
- Participants are recruited using preset criteria
- Receive same instructions
- Research protocol is kept as consistent as possible
- Small number of participants
What is the methods section?
i. Subjects/participants
ii. Materials
iii. Procedure
What are subjects/participants
Refers to the individuals who are tested, evaluated, and described in a research study
Define population?
any group of individuals in which the researcher is ultimately interested.
Define Sample size
a subset of the population of interest–Usually we only look at a sample and generalize to the whole group by inference.
What are factors that impact sample size
- purpose of the study
- previous research
- concerns about generalization
- variability of attributes being investigated
- research design.
Define subject selection
guideline: description of the subjects, materials, procedures and need sufficient description to replicate it.
Subject selection can utilize what 2 things?
inclusion and exclusion criteria
Protection of Subjects/Participants–What are three basic “ethical” principles
i. Respect for persons – honor individual’s decisions.
ii. Beneficence – maximize benefit and minimize harm.
iii. Justice – selection of individuals be fair and unbiased.
Who is IRB?
Institutional Review Board (IRB).
=Studies must gain approval of IRB.
=Sometimes referred to as “Human Subjects” but
=Includes animals as well
=Include 5 or more members with diverse backgrounds, both within and outside the research community
=Approval from the IRB that the study protocol adheres to the ethical principles
What 3 things are crucial to remember in regards to subjects?
- Informed consent: to participate in a research study is the cornerstone of ethical research conduct
- Privacy: Individuals ability to control when and under what conditions others will have access to personal information–preventing unwanted intrusion
- Confidentiality: ability of other people to connect back to individual, protection of identity
In materials what two basic eval questions need to be answered?
- Was there adequate selection and measurement of the independent (classification, predictor) variable?
- Was there adequate selection and measurement of the dependent (criterion, predicted) variable?
When acquiring data what do you need to use?
measurement
instrumentation
measurement devices
behavioral instruments
Define measurement
consists of rules for assigning numbers to objects in such a way as to represent quantities of attributes.
Define instrumentation
hardware, electronic equipment, and transducers.
Deine measurement devices
calipers, rulers, and timing instruments.
Define behavioral instruments
calipers, rulers, and timing instruments.
What are the levels of measurement?
Nominal: mutually exclusive
•i.e. pass/fail
Ordinal: mutually exclusive and ranking
•i.e. mild, moderate and severe.
Interval: all of the above and equivalence of units
•i.e. standard scores on tests.
Ratio: All of the above and equivalence of units and a true zero point.
Define Validity
Defined as the ‘degree’ to which is measures what it purports to measure
What are the three types of validity that = holy trinity
- Content validity
Logical examination of the content of the test items to see how well they sample the behavior or characteristic to be measured
2.Construct validity
The degree the instrument measures reflect a trait or construct
Statistical means help define constructs
- Criterion validity
Established by empirical examination of how well the measure correlates with some outside validating criteria – cut off score
•I.E. GPA for graduate school
Define procedures
•Describe what is done to the subjects with the materials
What are the tasks and protocols in the procedures section
Researcher protocol is the sequence of tasks performed by the subjects, manipulations of the IVs, & the subsequent measurement of change in the DV
- Step-by-step description
- Test environment → needs to be controlled
What are some other important things to consider in the procedures?
1.Subject instructions → clear and concise
oFree of ambiguity
2.Observer bias
oVariability among individuals/researchers acting as judges or raters
3.Non-interactional:
oOccurs when the researcher’s behavior affects recording of subject responses. Think of testing, too.
4. Interactional:
oInteractions with the subject affect changes the subjects behavior.
5. Appropriateness of measurements
oAssuming the instruments used to provide reliable and valid measurements of the variables, the reader should be concerned about the appropriateness of the measurements.
What is data analysis as part of procedures?
A statement on how the data are organized and analyzed (statistical processing, etc).
What are the common measures of Central Tendency?
Mean: The averageof the numbers.
It is easy to calculate:add upall the numbers, thendivide by how manynumbers there are.
Median: The Middle number.
Place the numbers invalue orderand find themiddle number.
Mode: The mode is simply the number which appearsmost often.
What is the null hypothesis?
Statistical analyses can only disprove hypotheses by showing the unlikelihood of occurrence of
chance relationships or differences.
is presumed to be valid until the researcher
can prove otherwise.
Null hypothesis states there is no difference between groups or no relationship among variables.
Null Hypothesis assumes any difference or covariance
observed in the data set is due to chance.
“I failed to reject the null hypothesis.”
What are the irregular shapes of the bell curve?
Negatively skewed
-when most scores cluster around a high value but a small number of scores spread out into the very low score end at the left of the distribution
Positive Skew
-most scores cluster around a low value but a small number of scores spread out into the very high score end at the right of the distribution
What is type 1 error?
sampling error give the research samples that represent unusual (but randomly occurring) events and incorrectly rejects the null hypothesis
To reject the null hypothesis of no differences when it is true; to conclude falsely that a difference exists in the data when in fact is does not
What is type 2 error?
Researcher failed to detect a relationship that is present
To accept the null hypothesis of no differences when it is false; to conclude falsely that a difference does not exist in the data when in fact is does
T/F The null hypothesis can never be accepted—it can only be rejected or fail to be rejected
True
