PSYC 302 Final Exam - Questions With Complete
Solutions
What are Quasi-experimental designs? Correct Answer - are research
studies in which participants are selected for *different* conditions from pre-
existing groups and self-selection into groups
Q designs are studies in which the IV are? Correct Answer - selected from
pre-existing values and not created through manipulation by the researcher
How are preexisting groups formed? Correct Answer - by self-selected
groups
ex. smokers vs nonsmokers
What is a central issue of quasi-experimental designs? Correct Answer -
research validity
What is the basic difference between true and quasi-experimental designs?
Correct Answer - random assignment
A quasi-experimental design DOES NOT permit the researcher to control
what? Correct Answer - the assignment of participants to conditions or
groups
How are Quasi-experimental designs characterized? Correct Answer -
*lower levels of control* over the WHO, WHAT, WHEN, WHERE, and HOW of
the study
What is a nonequivalent control groups design? Correct Answer - a
research design that has both experimental and control groups but the
participants are NOT randomly assigned to these groups
- most common type of Q design
What is the problem with nonequivalent control group designs? Correct
Answer - the problem is knowing how to compare the results between
groups when they are not equivalent to begin with
,- interpretability depends on whether the pattern of results obtained can be
accounted for by possible differences between the groups or by something
else in the study
-- ceiling effects
-- floor effects
What is a ceiling effect? Correct Answer - is the level at which an
independent variable no longer has an effect on a dependent variable, or the
level above which variance in an independent variable is no longer measured
or estimated
- example: 2 profs teaching the same class, students in one class constantly
was in the 98% on exams > while the other class started at 20% then moved
up to 98%. One would not be able to deem the first prof as better because
their teaching methods may have had nothing to do with the student's high
grades (could be that they're just smart and would get those high grades no
matter who the prof was)
What is a floor effect? Correct Answer - (aka, Basement Effect) is when
measurements of the dependent variable result in very low scores on the
measurement scale.
How can we further enhance or improve the interpret-ability of nonequivalent
control group designs? Correct Answer - 1. matching [limitation: only
controls for KNOWN factors]
2. identifying and building extraneous variables into the design or study as
moderator variables
3. pretesting—empirically documenting the degree of nonequivalence
4. if nonequivalent, as per pretest data, then can use a number of statistical
control procedures (as
previously discussed) to covary out or control for preexisting differences
What are the examples of nonequivalent control group designs? Correct
Answer - *delayed control group designs*: design in which the testing of one
group is deferred
- i.e., the two groups are tested sequentially with an appreciable time interval
between them]
- ex. testing impact of a natural disaster or London bombings (2005)
,*mixed factorial designs*: design in which there is one between-subjects
variable and one within-subjects variable
- at least one factor has to be naturally occurring or not RA (*between-
subjects variable = preexisting/naturally occurring*)
What are the designs without control groups? Correct Answer -
*Interrupted Time-Series Designs*: these designs allow the same group to be
compared over time by considering the trend of the data before and after the
treatment
- graph of uninsured rate diving in 2013 pg. 5
*Multiple Time-Series Design*: A variation of interrupted time-series design,
which is really NOT a design without a control group.
- used as a control for interrupted time-series {control and experimental
group are included to rule out HISTORY as a rival hypothesis}
- example: life satisfaction and marriage
*Repeated Treatment Design*: this research design allows the same group to
be compared by measuring the participants' responses before and after
repeated treatments
- ex. administering blood pressure meds, line on graph should go up and down
in a zig-zag
Can we make causal inferences based on quasi-experimental designs?
Correct Answer - no, because of absence of RA
- groups are nonequivalent which means there will always be 2 explanations
for differences:
1. treatment
2. nonequivalency
Which design is the best answer for which design can be experimental and
nonexperimental studies? Correct Answer - observational
What makes a Q design? Correct Answer - at least one IV is pre-existing
What is archival publication? Correct Answer - written record of scientific
progress
, What is invisible college? Correct Answer - informal communication
network of people having common scientific interests
What is discourse community? Correct Answer - a group of people who
share common goals, a public forum, common knowledge, and a specialized
language
What is an argument? Correct Answer - a set of reasons in support of a
proposition
What is a thesis? Correct Answer - the proposition that is supported by an
argument
What is a secondary citation? Correct Answer - documentation of an idea
from one work that is reported in another one
What is digital object identifiers (DOI)? Correct Answer - a unique
alphanumeric code that identifies and provides a persistent link to
information on the internet
What is gray literature? Correct Answer - a scientific literature that falls
outside the peer review process
Do you number every page and where does it go? Correct Answer - Yes,
top right
How many characters can the running head be and what should it look like?
Correct Answer - cannot exceed 50 characters
- looks like = Running head: TITLE OF PAPER
- only goes on 1st page
- all other pages look like = TITLE OF PAPER
The title outside of the header may be up to, how many word? Correct
Answer - 10-12
- put your name under
- under name put institution where research was conducted
Notes about over all paper Correct Answer - - 1 inch margins all the way
around
Solutions
What are Quasi-experimental designs? Correct Answer - are research
studies in which participants are selected for *different* conditions from pre-
existing groups and self-selection into groups
Q designs are studies in which the IV are? Correct Answer - selected from
pre-existing values and not created through manipulation by the researcher
How are preexisting groups formed? Correct Answer - by self-selected
groups
ex. smokers vs nonsmokers
What is a central issue of quasi-experimental designs? Correct Answer -
research validity
What is the basic difference between true and quasi-experimental designs?
Correct Answer - random assignment
A quasi-experimental design DOES NOT permit the researcher to control
what? Correct Answer - the assignment of participants to conditions or
groups
How are Quasi-experimental designs characterized? Correct Answer -
*lower levels of control* over the WHO, WHAT, WHEN, WHERE, and HOW of
the study
What is a nonequivalent control groups design? Correct Answer - a
research design that has both experimental and control groups but the
participants are NOT randomly assigned to these groups
- most common type of Q design
What is the problem with nonequivalent control group designs? Correct
Answer - the problem is knowing how to compare the results between
groups when they are not equivalent to begin with
,- interpretability depends on whether the pattern of results obtained can be
accounted for by possible differences between the groups or by something
else in the study
-- ceiling effects
-- floor effects
What is a ceiling effect? Correct Answer - is the level at which an
independent variable no longer has an effect on a dependent variable, or the
level above which variance in an independent variable is no longer measured
or estimated
- example: 2 profs teaching the same class, students in one class constantly
was in the 98% on exams > while the other class started at 20% then moved
up to 98%. One would not be able to deem the first prof as better because
their teaching methods may have had nothing to do with the student's high
grades (could be that they're just smart and would get those high grades no
matter who the prof was)
What is a floor effect? Correct Answer - (aka, Basement Effect) is when
measurements of the dependent variable result in very low scores on the
measurement scale.
How can we further enhance or improve the interpret-ability of nonequivalent
control group designs? Correct Answer - 1. matching [limitation: only
controls for KNOWN factors]
2. identifying and building extraneous variables into the design or study as
moderator variables
3. pretesting—empirically documenting the degree of nonequivalence
4. if nonequivalent, as per pretest data, then can use a number of statistical
control procedures (as
previously discussed) to covary out or control for preexisting differences
What are the examples of nonequivalent control group designs? Correct
Answer - *delayed control group designs*: design in which the testing of one
group is deferred
- i.e., the two groups are tested sequentially with an appreciable time interval
between them]
- ex. testing impact of a natural disaster or London bombings (2005)
,*mixed factorial designs*: design in which there is one between-subjects
variable and one within-subjects variable
- at least one factor has to be naturally occurring or not RA (*between-
subjects variable = preexisting/naturally occurring*)
What are the designs without control groups? Correct Answer -
*Interrupted Time-Series Designs*: these designs allow the same group to be
compared over time by considering the trend of the data before and after the
treatment
- graph of uninsured rate diving in 2013 pg. 5
*Multiple Time-Series Design*: A variation of interrupted time-series design,
which is really NOT a design without a control group.
- used as a control for interrupted time-series {control and experimental
group are included to rule out HISTORY as a rival hypothesis}
- example: life satisfaction and marriage
*Repeated Treatment Design*: this research design allows the same group to
be compared by measuring the participants' responses before and after
repeated treatments
- ex. administering blood pressure meds, line on graph should go up and down
in a zig-zag
Can we make causal inferences based on quasi-experimental designs?
Correct Answer - no, because of absence of RA
- groups are nonequivalent which means there will always be 2 explanations
for differences:
1. treatment
2. nonequivalency
Which design is the best answer for which design can be experimental and
nonexperimental studies? Correct Answer - observational
What makes a Q design? Correct Answer - at least one IV is pre-existing
What is archival publication? Correct Answer - written record of scientific
progress
, What is invisible college? Correct Answer - informal communication
network of people having common scientific interests
What is discourse community? Correct Answer - a group of people who
share common goals, a public forum, common knowledge, and a specialized
language
What is an argument? Correct Answer - a set of reasons in support of a
proposition
What is a thesis? Correct Answer - the proposition that is supported by an
argument
What is a secondary citation? Correct Answer - documentation of an idea
from one work that is reported in another one
What is digital object identifiers (DOI)? Correct Answer - a unique
alphanumeric code that identifies and provides a persistent link to
information on the internet
What is gray literature? Correct Answer - a scientific literature that falls
outside the peer review process
Do you number every page and where does it go? Correct Answer - Yes,
top right
How many characters can the running head be and what should it look like?
Correct Answer - cannot exceed 50 characters
- looks like = Running head: TITLE OF PAPER
- only goes on 1st page
- all other pages look like = TITLE OF PAPER
The title outside of the header may be up to, how many word? Correct
Answer - 10-12
- put your name under
- under name put institution where research was conducted
Notes about over all paper Correct Answer - - 1 inch margins all the way
around
