Exam 2 - Ch 8 - 15 Flashcards
(294 cards)
1
Q
In a study by Ackerman & Goldsmith, one group of students were given laptops and the other paper for studying material, than were tested on the material. This is an example of a _______-______ design.
A
Between-subjects.
2
Q
In an experiment by Stephens, Atkins, and Kingston, participants were allowed to use swear words, then neutral words while holding their hand in icewater; this is an example of a ______-______ design.
A
within-subjects.
3
Q
The goal of between-subjects experiments is to demonstrate what kind of a relationship?
A
cause-and-effect relationships.
4
Q
The 4 main requirements of any research strategy include measurement of a DV and comparing scores; experiments include _____ of the IV and _____ over all potential confounds.
A
manipulation (of the IV); control (over confounds).
5
Q
A within-subjects experimental design is also known as a ______ measures design.
A
repeated.
6
Q
A between-subjects experimental design is also known as a/an ____ measures design. Why?
A
independent; because the groups of participants are independent of each other (one does not affect the other).
7
Q
A 70 degree room would feel cold coming from outside, or warm coming from a walk-in cooler (for the same person); this is an example of a ______ effect.
A
contrast
8
Q
A contrast effect is a type of ____-_____ effect.
A
carry-over
9
Q
Advantages of between-subjects designs are that participants are NOT influenced by _____ effects or ____-____ effects.
A
order effects; carry-over effects.
10
Q
One disadvantage of between-subjects designs is they require a large number of ______.
A
participants.
11
Q
Finding a large number of participants for a between-subjects design can be problematic when doing research on …?
A
special populations where the pool of participants is small.
12
Q
Individual differences can be a disadvantage in which design? Why (list 2 reasons)?
A
between-subjects because (1) differences can be confounding variables; (2) differences can cause high variability in the data which can obscure results.
13
Q
How can individual differences cause confounding in between-subjects?
A
Because the difference in scores between the groups may be due to a genuine treatment effect or to individual differences (confounding).
14
Q
Two major sources of confounding for between-subjects are ______ differences or ______ variables.
A
individual; environmental.
15
Q
The participant groups in between-subjects experimental designs must be ____ equally, _____ equally, and composed of _____ _____.
A
created equally, treated equally, and composed of equivalent individuals.
16
Q
The three main techniques for limiting confounding from individual differences are (1) ______ assignment; (2) _____ groups, and (3) ______ potentially confounding variables ________.
A
random assignment; matching groups, and holding potentially confounding variables constant.
17
Q
______ is the measure of variability obtained by computing the average squared distance from the mean.
A
Variance
18
Q
Variance measures the ____ of differences from one _____ to another.
A
size; score
19
Q
T or F: researchers should try to increase the differences between treatments.
A
True; if evaluating the effect of color on mood, chose the lightest and darkest shades of the color.
20
Q
Increasing sample size is a good way to control variance; however, it can be impractical because…?
A
It is only effective when the size is increased by a very large number.
21
Q
_____ is participant withdrawal before completion of the study/experiment.
A
Attrition.
22
Q
_____ attrition is the worst kind of attrition because withdrawal is _______ between groups.
A
Differential; unbalanced/unequal.
23
Q
This threat to internal validity is defined as spreading of treatment effect from the treatment group to the control group (gossip and use elements of the treatment).
A
Diffusion.
24
Q
This threat to internal validity is defined as the demands of untreated groups to receive a treatment.
A
compensatory equalization
25
This threat to internal validity is defined as untreated group's compensation for lack of treatment through extra work (gossip then control group tries to outcompete).
compensatory rivalry
26
This threat to internal validity is defined as untreated group's loss of productivity after learning of another group's special treatment (gossip then demoralized).
resentful demoralization.
27
Two-group mean difference (aka single-factor two-group design or two-group design) is a strategy comparing two groups of scores that represent two _______ of a ________.
levels of a factor.
28
For the two-group mean difference (aka single-factor two-group design or two-group design) how many IVs are there? How many levels?
One IV, two levels.
29
In the two-group mean difference (aka single-factor two-group design or two-group design), the ______-______ _____ test is used to show if there is a significant difference between the means.
independent-measures t test
30
The ___-____ _____ ____ design is a between-subjects design that compares the means of two groups of participants using the independent-measures t test.
two-group mean difference (or single-factor two-group)
31
One of the advantages of a two-group mean difference (aka single-factor two-group design or two-group design) is its _______; but the downside is that it provides...?
simplicity; provides little information.
32
For the two-group mean difference (aka single-factor two-group design or two-group design), one of the disadvantages is that is provides little information - explain (2 main points).
(1) You can only have two groups which means forgoing a control and placebo plus treatment; (2) if the relationship is curvilinear, you might miss a treatment effect if the two levels chosen are on a level or negative portion of the curve.
33
Unlike the two-group mean difference (aka single-factor two-group design or two-group design), the single-factor ______-______ design can compare...?
multiple-group can compare multiple groups for multiple levels of the IV.
34
Unlike the two-group mean difference (aka single-factor two-group design or two-group design), the single-factor multiple-group design is analyzed using what statistical analysis?
single-factor ANOVA
35
The single-factor multiple-group design provides ___ evidence for cause-and-effect than the two-group design.
stronger/more/greater
36
When analyzing data for more than two groups in a single-factor design, the _____ is computed for each group of participants, and an ____ is used to determine whether there are any significant differences among the means.
mean; ANOVA
37
T or F: when an ANOVA concludes that a significant difference exists between the means of a single-factor design with more than two groups, you're done.
False - you must perform a post hoc test (aka post test) to determine which means are significant.
38
The ____ ____ test is a follow up hypothesis test done after an ANOVA to determine exactly which mean differences are significant.
post hoc test.
39
When comparing proportions for two or more groups measured on a nominal or ordinal scale, data can be analyzed with a ___-____ test for independence.
chi-square
40
The chi-square test for independence compares _____ between groups.
proportions.
41
An example of when a chi-square test for independence is used is when the DV is what kind of question being asked?
A yes/no question.
42
In a ___-____ design, treatments can be administered sequentially or all together in one experimental session.
Within-subjects.
43
The two major confounds in within-subjects designs are ____ variables and ___-_____ variables.
environmental and time-related variables.
44
In this time-related threat to internal validity, ____ is an event that influences participants' scores differently in one treatment than in another treatment.
History
45
In this time-related threat to internal validity, ____ is any systematic change in participants' physiology or psychology that affects scores (esp. problematic in young or elderly participants).
Maturation.
46
In this time-related threat to internal validity, ____ is changes in the measuring instrument (or in an observer's ratings) over time.
instrumentation
47
In this time-related threat to internal validity, ____ towards the mean (aka statistical ______) is a tendency for extreme scores to regress when the measurement procedure is repeated.
regression (x2)
48
In this time-related threat to internal validity, ____ ____ is any change in performance caused by participation in a previous treatment.
order effect.
49
Two examples of order effects are...?
fatigue and practice.
50
Statistical regression can be especially problematic if participants with the ___ or ___ scores were chosen for specific treatments.
highest or lowest
51
____ error is a change in performance related to experience in a research study, but not in a specific treatment.
progressive error.
52
___-____ effects are changes in the scores of one treatment that are due to the lingering aftereffects of an earlier treatment.
Carry-over effects.
53
____ effect is a type of carry-over effect wherein perception of one treatment is influenced by the contrast of another treatment.
contrast effect.
54
Shortening the time between treatments can ____ the likelihood that _____ effects will confound; however, shortening the time can reduce _____-____ threats.
increases the likelihood that order effects will confound; can reduced time-related threats (e.g. maturation)
55
Increasing the time between treatments increases the risk of ___-___ threats; but increasing the time can reduce _____ effects from confounding.
time-related threats; order effects.
56
_____-_____ design is better for research conditions that are prone to order effects.
Between-subjects (fatigue and practice are not an issue when the groups are different).
57
Changing the order in which treatment conditions are applied from one participant to another is known as _______.
counterbalancing.
58
The goal of counterbalancing is to use every possible ____ of treatments with an equal # of participants in each.
order
59
The purpose of counterbalancing is to eliminate the potential for confounding by disrupting any _____ relationship between the order of treatments and ___-____ factors.
disrupt any systematic relationship; time-related factors (maturation, history, etc).
60
This procedure is used to minimize threats from order-effects and time-related factors by changing the order of treatment conditions.
Counterbalancing.
61
Counterbalancing spreads _____ _____ evenly across all the different conditions, but it does not eliminate them.
order effects
62
Counterbalancing can increase within-treatment ______.
variance
63
The use of a separate group of participants for every possible order of the treatment conditions is known as (calculated via a permutation n!)
complete counterbalancing.
64
_______ counterbalancing uses some aspects of counterbalancing, but not every possible sequence, and is accomplished by using a ____ ____.
'partial' counterbalancing; Latin square
65
An n x n matrix wherein each different item appears once in each column and row.
Latin square.
66
Two advantages of within-subjects designs is they require fewer ____ and eliminate problems associated with _____ ______.
participants; individual differences.
67
The problem with participant attrition as it pertains to within-subjects design is that it can lead to exaggerated ____ _____?
It can lead to exaggerated volunteer bias.
68
A study by Seery, Holman, and Silver (2010) evaluated participants' lifetime exposure to adverse events, and found that participants with some adversity were more well adjusted than those with no or too much adversity. This is an example of a ________ research strategy.
nonexperimental (more specifically, differential - a nonexperimental design with nonequivalent groups).
69
In this research strategy, researchers compare groups of scores without manipulating an IV and with no control of participant assignment.
Nonexperimental
70
A ________ research strategy attempts to demonstrate a relationship between two variables by comparing scores from two or more groups (no cause and effect).
nonexperimental
71
Correlational vs. nonexperimental? Goal of each?
Correlational uses one group with two scores (within-subjects); nonexperimental uses two or more groups with two or more scores (one set of scores per group). Both seek to establish a relationship.
72
This research strategy 'attempts' to limit threats to internal validity and produce cause and effect conclusions.
quasi-experimental.
73
A ________-_______ variable is one that differentiates the group conditions (or scores) being compared.
quasi-experimental.
74
What does it mean when a strategy has 'nonequivalent' participants?
The participants are pre-existing, so the groups weren't 'created equally'.
75
T or F: a nonequivalent group design is a within-subjects design?
False: a nonequivalent group design is a between-subjects.
76
A pre-post design is between- or within-subjects?
It's a within-subjects design -- all participants are tested before and after a treatment.
77
A study were the researchers uses a group of college grads and participants with no college is a ______-______ design, and the participants are considered _______.
between-subjects design; they are nonequivalent.
78
In this research design, the first variable, time of measurement, is the variable that differentiates the groups' two scores; the second variable is measured before and after a therapy or treatment (received by all participants). This is an example of a ______-______ design.
Pre-post design. (within-subjects)
79
The differential research, posttest-only nonequivalent control group design, pretest-posttest nonequivalent control group design, and cross-sectional developmental design are all examples of ______ group designs because they all compare preexisting groups of individuals.
Nonequivalent.
80
The pretest-posttest design, time-series design, and interrupted time-series design are all examples of _____-______ designs because they compare _____ or more scores for one group (within-subjects) of participants.
pre-post; two or more scores
81
In a nonequivalent group design, groups are differentiated by a specific ______.
Factor / variable
82
The purpose of this design is to show that a specific factor (used to separate groups) is responsible for differences in scores.
Nonequivalent group design.
83
The biggest threat to internal validity in the nonequivalent group design is that _____ bias prevents a clear cause and effect explanation; ultimately, there is no assurance of _______ groups.
assignment; equivalent.
84
This example of a nonequivalent group design is a nonexperimental method that compares preexisting groups (usually race, gender, etc.) with the goal of determining whether scores from one group are 'different' from the other group.
Differential research design.
85
Correlational vs. differential?
Correlational = two variables measured per individual; differential = one variable used to differentiate groups, the second variable is measured.
86
A nonequivalent control group design uses preexisting groups in the _________ and _________ group conditions.
Treatment and control
87
This research design is often called ex post facto research because it looks at differences after they've already taken place (preexisting).
Differential research.
88
A posttest-only nonequivalent control group design is also known as a ____ group comparison (because you're not measuring change in behavior after a treatment, or something like that).
static.
89
An example of a ________-_______ nonequivalent control group design could be measuring the well being of 2 groups of children: one with a neighborhood park, and one without.
posttest-only
90
Why is the pretest-posttest nonequivalent control group design considered quasi-experimental?
Because some of the threats to internal validity are limited due to the measuring / comparing of a control group; this enables some time-related factors to be detected.
91
The ____-____ design is a quasi-experimental or nonexperimental method consisting of a series of observations made over time, and the goal is to evaluate the effect of an intervening treatment by comparing observations made before vs. after the treatment.
Time-series design
92
T or F: a pre-post design is a between subjects design.
False: it is a within-subjects.
93
Because of the length of time of pre-post designs, what are the possible drawbacks?
The length of time can make them susceptible to time-related threats.
94
A political analyst evaluating the effectiveness of an ad campaign might use the ____-_____ design, which is a "single-group" method involving two measurements (one before and after treatment).
pretest-posttest design
95
A time-series design is a quasi-experimental research strategy consisting of a series of observations before a after treatment OR and EVENT - treatment vs. event?
treatment is manipulated by the researcher; event is beyond the researcher's control (e.g., a change in the law [known ahead of time] or a natural disaster [unknown])
96
A ___-____ design is a quasi-experimental research strategy consisting of a 'series of observations' before and after treatment.
time-series
97
A(n) _____ time-series design is a strategy consisting of a series of observations before and after an "event".
Interrupted
98
Time-series design vs. interrupted time-series design
time-series the treatment is planned, or the event is known in advance; interrupted time-series is exactly that - the event is not manipulated.
99
Why are time-series designs quasi-experimental?
observations can reveal trends or other threats, and the researcher can take steps to mitigate (some control).
100
A therapist monitoring instances of compulsive behavior in one client for 3 weeks before and after therapy is an example of a _____-_____ ___-______ design.
single-case time-series design (often called single-case or single subject designs).
101
The ______ _____ design is a nonexperimental research design used to examine the relationship between age and other variables and are used to examine changes in behavior related to age.
developmental research design
102
Cross-sectional and longitudinal designs are both examples of ______ _____ design.
developmental research design.
103
In this developmental research design, groups of participants represent a different age are compared.
Cross-sectional developmental research design
104
The advantage of a cross-sectional developmental research design is that...?
they're quick and easy to conduct, unlike longitudinal designs.
105
A _____ is one of multiple individuals who are of similar age and grew up under similar circumstances.
Cohort
106
The _____ effect, AKA generational effect, is the difference between age groups that is caused by characteristics or experiences other than the aging process (e.g., life experiences).
cohort effect
107
One weakness for the cross-sectional developmental design is...?
cohort effects (generation effects) can threaten internal validity.
108
The _____ _______ research design is a developmental strategy that makes a series of observations or measurements over time.
Longitudinal developmental research design.
109
In the longitudinal developmental research design, differences amongst participants is more likely due to _______ rather than _____ _____.
aging; cohort effects.
110
In a 2002 study by Bartholow and Anderson, the relationship between aggressive behavior and violent video games was studied, but it included another variable: gender; this is an example of a _______ design.
factorial
111
An ______ ______ design includes two or more IVs, otherwise known as ______, which are manipulated.
experimental factorial design; factors
112
Advantages of experimental factorial designs are that they create a more _____ situation than examining a single factor in isolation; and they can evaluate how individual factors and/or groups of factors _____ behavior.
more realistic; influence behavior
113
IV AKA ____ in factorial designs.
factor
114
A ___-___ design is factorial research strategy involving two IVs (or quasi-independent variables).
two-factor design.
115
A ___-___ design is factorial research strategy involving one IV or quasi-independent variable.
one-factor design
116
2 x 2 is an example of the notation system that id's the number of _______ and the number of _____ of each factor in a factorial design.
factors; levels
117
The total number of treatment conditions in a factorial design can be determined by...?
Multiplying the levels of each factor.
118
A 3 x 2 x 3 factorial design has how many factors? Treatment conditions?
3 factors; 18 treatment conditions.
119
In factorial designs, the _____ _____ are the mean differences among the levels of one factor, and neither factor has a direct _____ on the other.
main effects; influence
120
_____ _____ factors = the effects of one factor depends on different levels of another factor (answer to the hypothesis is "it depends").
Interaction between factors.
121
In a factorial design, ______ ______ factors is whenever one factor modifies the effects of a second factor.
interaction between factors
122
When graphing factorial designs, ____ or _____ lines indicate an interaction, _____ lines indicates no interaction
crossing or converging; parallel
123
When identifying an interaction in a data matrix, the size and direction of the difference in one row are the same as the the corresponding differences in the other rows, then there is/is not evidence of an interaction.
No interaction.
124
When identifying an interaction in a data matrix, the size and direction of the difference in one ____ changes in the other ______, then there is/is not evidence of an interaction.
row (x2) - there is an interaction
125
A two-factor [factorial] study allows researchers to evaluate three separate sets of means - which are they?
(1) mean differences from the main effect for factor A; (2) mean differences from the main effect for factor B; (3) mean differences from the interactions between factors.
126
A ____ ___ is a factorial strategy that blends/combines 2 different research designs, such as between-subjects and within-subjects, in the same factorial design.
mixed design
127
Disadvantages of a purely between-subjects factorial design include ____ participants, and individual ______.
many participants and individual differences.
128
Advantages of a purely between-subjects factorial design include no _____ effects such as ____ or _____.
order effects; fatigue or practice.
129
Disadvantages of a purely within-subjects factorial design include participant _____, _____ effects, and inability to properly ______ treatments due to too many treatments.
participant attrition; order effects, and inability to counterbalance.
130
Advantages of a purely within-subjects factorial design include _____ participants and reduce/eliminate individual ______.
fewer participants; individual differences.
131
A study by Durso, Luttrell, and Way (2015) to study Tylenol's effect on pleasure and pain gave 1/2 participants acetaminophen, and 1/2 a placebo, then showed them all positive and negative images. This is an example of a ____ design where one factor, the medication, was a ___-___ design, and the other factor, the images, was a ___-____ design.
mixed; between-subjects; within-subjects
132
T or F: A factorial design that is purely experimental is one where both factors are true independent variables that are manipulated by the researcher.
true
133
A factorial design that combines 2 different research 'techniques' such as experimental and non-experimental is called a ______ ______.
Combined strategy
134
The ____ strategy utilizes one non-experimental factor, such as gender, and one quasi-experimental or experimental factor, such as treatment effect over time.
combined
135
A study by Bartholow and Anderson (2002) measured aggressive behavior after playing violent or non-violent video games for males and females. The video games are ______ factors, and gender is a _____ factor. This is an example of a _____ strategy.
experimental; non-experimental; combined.
136
The _____-______ control group design is an example of a two-factor mixed design involving one measurement before and one measurement after treatment where one factor is between-subjects, and the other is within-subjects.
pretest-posttest control group design.
137
Pretest-posttest control group design vs. pretest-posttest nonequivalent group design
Pretest-posttest control group design is a factorial design
138
In the pretest-posttest control group design, the pretest-posttest factor is a ____-subjects factor, the experimental factor is a _____-subjects design.
within-[subjects] (both measurements are given to each subject, so it's "within"); between-[subjects] (one group gets the treatment, the other is the control, so it's "between".
139
The pretest-posttest control group design is classified as quasi-experimental because...?
It uses nonequivalent groups.
140
T or F: the pretest-posttest control group design can use random assignment of participants in some cases.
True.
141
The main applications for factorial designs is to _____ a previous study by using the same factor of IV exactly as it was used in a previous study, and to _____ on a previous study by adding a second factor in the form of new conditions or new participant characteristics to ascertain whether previous findings can be generalized to new situations/populations.
replicate; expand
142
In a 2015 study by Lederer, Autr, Day, and Oswalt, research showed that as work hours increased, sleep decreased. This is an example of a _______ research strategy.
Correlational
143
In the _____ research strategy, 2 or more DV's are measured per participant to find relationship patterns and to measure the strength of the relationship.
correlational
144
In a correlational research strategy, the goal is to establish the existence of a _______, and to describe the _______ of the relationship.
relationship; strength
145
T or F: only one variable can be manipulated in a correlational research strategy.
False - there can be NO manipulation.
146
A _______ study measures two DV's and examines the relationship between them; a ______ study uses one of the variables to define (or differentiate) two groups of participants, then measures the second variable.
correlational; differential
147
A graph that shows the data collected from a correlational study is known as a _____ _____.
scatter plot.
148
In correlational studies, data can be presented in a _____ _____ or in a _____ that shows the two scores per individual.
scatter plot or list
149
The _____ ______ is a statical value that measures and describes 3 characteristics of a relationship: the direction, the form, and the consistency or strength of a relationship.
correlation coefficient
150
When referencing the direction of a relationship in a correlation calculation (r), it is either _____ or ______.
Positive or negative.
151
When referencing the form of a relationship in a correlation coefficient, it is said to be either ________ or ________.
Linear or monotonic
152
A linear correlation coefficient (r) with interval or ratio data is evaluated using the _____ correlation.
Pearson
153
A correlation using ordinal data to evaluate monotonic relationships is the _______ correlation.
Spearman
154
T or F: monotonic relationships are strictly curvilinear.
False: they can be linear or curvilinear; monotonic simply refers to ordinal data and utilization of the Spearman statistic.
155
In a correlation coefficient (r), the numerical value (-1.0 - 1.0) indicates the ________ or _______ of the relationship.
strength or consistency.
156
The type of correlation, Pearson or Spearman, indicates the _______ of the relationship.
form
157
When evaluating correlational relationships for non-numerical data from nominal scales, use the non-numerical variable to create ________; and compare the two groups using an ______-______ __ ______ (for two groups), or an _____ of _____ (for > 2 groups).
categories; independent-measures t test; analysis of variance
158
When evaluating correlational relationships for non-numerical data from nominal scales, if the non-numerical variable consists of 2 categories, they can be coded as 0 and 1, and a ____-______ correlation (correlation between binary and numeric data) can be calculated.
point-biseral
159
When both variables in a correlational study are from nominal scales, we evaluate the data by organizing it into a ________.
matrix
160
When both variables in a correlational study are from nominal scales, and both nominal variables are coded (binary data consisting of yes/no, on/off, etc.), a ______ correlation is calculated, and the result is known as a ____-_____.
Pearson; phi-coefficient.
161
The ____ of _____, (r2) is the squared value of the correlation that measures the percentage of variability in one variable which is determined or predicted by its relationship with the other variable.
coefficient of determination
162
The statistical _____ of a _____ is the relationship that is unlikely to have occurred by chance (it's reasonable to assume that the correlation represents a real relationship in the population).
statistical significance of a correlation.
163
Two factors that must be considered when interpreting the strength of a correlational relationship is the ______ of ______ (percentage of variability) and the _______ of the correlation.
coefficient of determination; significance
164
A coefficient of determination = 0.01 is ____; = 0.09 is _____, and 0.25 is ______
small; medium; large
165
Applications of the correlational strategy include ______ one variable from another variable.
predicting
166
In a correlational strategy, the ______ variable is the independent component in a correlational study; AKA the first variable (X).
predictor
167
In a correlational strategy, the ______ variable is the outcome construct in a correlational study; AKA the second variable (Y) being explained or predicted.
criterion
168
In a correlational strategy, _____ is the statistical technique used for predicting one variable from another.
Regression
169
In a correlational strategy, the goal of regression is to find the ______ that produces the most accurate _____ of Y (the criterion variable) for each vale of X (the predictor variable)
equation; predictions
170
The _______ variable is usually relatively simple and well defined. The _______ variable is usually complex and unknown.
predictor; criterion
171
______ evaluates the consistency or stability of the measurements; _______ evaluates the extent to which the measurement procedure actually measures what it claims to be measuring.
Reliability; validity
172
Both _____ and ______ are commonly defined by relationships that are established using the correlational research design.
reliability and validity
173
_____-_____ reliability compares scores of 2 successive measurements of the same individuals and correlates the scores (i.e., one measurement procedure used twice).
Test-retest reliability
174
________ validity of the test can be established by demonstration that the scores from the test are strongly related to scores from established tests (i.e., new measurement vs. old/established measurement).
Concurrent
175
Strengths of the correlational research strategy include high _____ validity, they are __________ (natural behaviors can be readily observed), they are good for preliminary research, and they are good for investigating variables that are _____ or _____ to investigate.
external; nonintrusive; unethical or impossible
176
Weaknesses of the correlational research strategy include low _______ validity (due to the ______-variable problem and _______ problem [AKA chicken or egg]), and they can't assess ________.
internal; third-variable problem; directionality problem; causality.
177
________ ______ is a statistical procedure used in correlational studies for studying multivariate relationships.
Multiple regression
178
In correlational research, an example of where ______ ______ would be applied is predicting academic performance using IQ -AND- motivation.
multiple regression
179
"1/3 of Americans get < 6 hrs of sleep per night"; "A survey of > 2K adults found that 63% of Americans would have trouble meeting basic needs if they lost income for 3 months" are both examples of the _____ research strategy.
descriptive.
180
The goal of descriptive research is to obtain separate ____ for each ______.
descriptions for each variable.
181
In descriptive research, variable(s) is/are measured as they exist _____.
naturally
182
In descriptive research, there is no concern for the _____ between variables, just the descriptions of each.
relationship.
183
There are 3 categories of the descriptive research design: (1) _________ research design where the researcher observes and systematically records behavior of individuals to describe the behavior; (2) ________ research design where a researcher uses surveys to obtain a description of a particular group; and (3) _______ study design where an in-depth study and detailed description of an individual is obtained.
Observational; survey; case study
184
Regarding the descriptive research categories, there are two potential problems with observational research: the behaviors CANNOT be _____ or _____ by the observer; and observations are partly based on the observer's _______ ______.
disrupted or influenced; subjective judgement
185
________ ______ is the direct observation and systematic recording of behaviors.
Behavioral observation.
186
In observational research, participants can be _____ to the observer's presence, or the observer can be ______.
habituated; concealed
187
In observational research (a category of descriptive research), a set of observable actions placed into groups, known as _______ ________, should be established beforehand to reduce subjectivity.
behavior categories
188
One way to address subjectivity in observational research is to use multiple, well trained observers to assess ____-____ reliability, and develop a list of well-defined ______ categories.
inter-rater; behavioral
189
To establish reliability in an observational research study (a category of descriptive research), what is required?
2 or more individuals record simultaneously during some portion of the observations.
190
The frequency method, duration method, and interval method are the 3 techniques used to _______ observations in observational research.
quantify
191
The _____ method of quantifying observations involves counting the instances of specific behaviors that occur during a fixed time period.
frequency (how 'frequent' did they do x in z amount of time?)
192
The ____ method of quantifying observations involves recording how much time an individual spends engaged in a specific behavior.
duration (what was the duration spent doing x in z amount of time?)
193
The ______ method of quantifying observations establishes whether a behavior has occurred within units of a specific time period.
interval (did behavior x occur during z number of intervals?)
194
Methods of quantifying observations: a child committed "3 aggressive acts" during a 30 min period... which method?
frequency
195
Methods of quantifying observations: a child spent "18 mins playing alone" during a 30 min period.
Duration
196
Methods of quantifying observations: a 30 min observation period was divided into 30, 1-min units. The child was observed in "group play during 12 of the units" (not necessarily consecutive).
Interval
197
Using the techniques of behavioral observation to measure the occurrence of specific events in media that present replicas of behavior is known as ______ _______.
Content analysis.
198
_______ research looks at historical records to measure behaviors or events that occurred in the past.
Archival.
199
_______ analysis and _______ research do not involve the direct observation of behaviors, but they follow the same rules for behavioral observations: they establish behavioral _______, they use the 3 methods of ______ observation (frequency, duration, and interval) to obtain numerical scores, and they employ multiple ________ for at least part of the measurement process to obtain a measure of ______-______ reliability.
content; archival; categories; behavioral; observers; inter-rater
200
In an observational research study (a category of descriptive research), there are 3 kinds of observation: (1) _______ observation where a researcher unobtrusively records behavior in a non-lab setting (AKA nonparticipant observation); (2) ________ observation where the researcher engages in the same activities as the participants in order to observe and record their behavior; and (3) ___________ observation where recordings are made in settings arranged specifically to facilitate the occurrence of specific behaviors (lab setting).
naturalistic; participant; contrived
201
In an observational research study (a category of descriptive research), _______ observation has high degrees of external validity and is useful for examining behaviors that can't be manipulated for practical or ethical reasons.
naturalistic.
202
In an observational research study (a category of descriptive research), ______ observation has high external validity and enables researchers to observe behavior that may not normally be accessible; but it is extremely time-consuming and potentially dangerous.
participant
203
In an observational research study (a category of descriptive research), ______ observation may affect external validity due to the less natural environment; however, the researcher doesn't have to wait for the behavior to occur naturally.
contrived.
204
In an observational research study (a category of descriptive research), a researcher can observe parent-child interactions in their home, or they can employ the use of ______ observation (AKA structured observation).
contrived.
205
Both _____ observation and ______ observation include weaknesses for being time-consuming; however, ______ observation has the potential for loss of objectivity, while _____ observation has the potential for observer influence if discovered.
naturalistic and participant; participant; naturalistic.
206
The ________ research design (a category of descriptive research) uses a self-report to obtain a description of a particular group of individuals.
survey
207
The goal of the _____ research design is to get a 'snapshot' of the group of interest at a particular time.
survey
208
One strength of the survey research design is it is an efficient way to....?
gather large amounts of information.
209
Regarding the survey research design (a category of descriptive research), there are 4 issues that need to be addressed in order for the results to be meaningful and accurate: (1) survey questions must be ______; (2) questions must be ________ to produced a well-constructed survey; (3) a ______ process must be developed to determine who will participate; (4) it must be determined how the survey will be ______.
developed; organized; selection; administered
210
Regarding the survey research design (a category of descriptive research), _____-______ questions allow participants to respond in their own words granting them the greatest flexibility; however, they are often difficult to ______ or ______ with conventional statistical methods.
Open-ended; summarize or analyze
211
Regarding the survey research design (a category of descriptive research), _________ questions present a limited number of responses, are easy to analyze/summarize, and allow for an element of open-endedness by including an "other, explain:" selection.
restrictive
212
Regarding the survey research design (a category of descriptive research), ______-_____ questions require selection of a numerical value on a predetermined scale.
rating-scale
213
Regarding the survey research design (a category of descriptive research), one type of rating-scale questions are ______ scale where ratings are presented as a horizontal line; however, participants may tend to answer most questions the same way, which is know as a _____ set.
Likert; response set
214
Regarding the survey research design (a category of descriptive research), there are 5 guidelines for constructing a survey: (1) _______ should appear at the end (recently challenged, tho); (2) sensitive questions should appear in the ______; (3) group questions by ______; (4) the ____ should be simple; (5) language should be ______ to ______.
demographic; middle; topic; format; easy to understand
215
Regarding the survey research design (a category of descriptive research), participants selected should _______ the group of interest, and questions should be ______ to them.
represent; relevant
216
Regarding the survey research design (a category of descriptive research), internet surveys are ________, ______ at reaching a large number of participants at once, and ______ in presenting questions based on previous responses.
economical; efficient; flexible
217
Regarding the survey research design (a category of descriptive research), ______ bias in internet surveys is a threat to external validity because the respondents are usually not representative of the population.
nonresponse
218
Regarding the survey research design (a category of descriptive research), ____ surveys are convenient and nonthreatening in that participants can be confident their responses are ______; but they can be expensive, time-consuming, and response rates tend to be low.
mail; anonymous
219
Regarding mail surveys, response rates can be improved if they are accompanied by a good _____ _____, include a ______, give participants ______ _____ to expect the survey, and ______ _____ after surveys have been mailed.
cover letters; gift; advanced warning; follow up
220
Regarding the survey research design (a category of descriptive research), ______ surveys can be conducted from anywhere, and a large number of participants can be reached; however, ______ bias can influence respondents' answers, it can be expensive, and it can be time consuming.
telephone; interviewer bias
221
Regarding the survey research design (a category of descriptive research), ___-_____ surveys (AKA _______) are very efficient for administering surveys to groups, and info can be gathered from the illiterate, but it can be very time consuming, and is subject to ____ bias.
in-person AKA interviews; interviewer bias
222
The ______ ______ design (a category of descriptive research), is an in-depth study and detailed description of a single individual or very small group (may or may not include intervention/treatment).
case study
223
A _____ ______ (a category of descriptive research) is the study of an individual that does not include a treatment or intervention.
case history
224
The ______ approach to the case study design strictly studies individuals, not groups; whereas the _______ approach strictly studies groups, not individuals.
idiographic; nomothetic
225
Applications of the case study design (a category of descriptive research) include _____ phenomena, such as dissociative identity disorder, and ____ to the rule, such as savants.
rare; exceptions
226
Strengths of the case study design (a category of descriptive research) include ______ and ______ studies that can be better visualized and impactful for the reader. Weaknesses include no attempt to ID ______, potential for _____ bias (which cases are reported vs. which aren't), and limited ________.
vivid and convincing/powerful; causation; selective bias; generalization.
227
In a study by McHugh, Tinstrom, Radley, Barry, and Walker (2016), disruptive behavior by a student was notably reduced when other students engaged in tootling (tattling), but resumed to previous levels when tootling stopped, then reduced again when tootling was reintroduced. This is an example of a ______-______ experimental design.
single-case
228
____-______ designs use the results from one participant to establish causality (cause-and-effect) by including a manipulated IV and controls for potential confounds.
Single-subject
229
While similar to descriptive case studies and quasi-experimental time-series studies, _____-_____ studies are capable of demonstrating true ___-____-___.
single-subject; cause-and-effect
230
The _____-_____ designs (AKA single-case designs) were developed by _________ (most famous being Skinner and his operant conditioning of a rat in a box).
single-subject; behaviorists
231
In ______-______ designs, control of other variables is achieved by: (1) measuring a _______, (2) making _____ observations to ensure no confounding, and (3) _____ of phases to ensure changes are due to the treatment rather than confounds.
single-case (or single-subject); (1) baseline; (2) repeated; (3) replication
232
When evaluating the results from a single-case study, it is essential that the data be ________ because the study relies solely on the appearance of graphs to provide evidence.
clear/unambiguous
233
Two reasons to be skeptical when evaluating finds from a single-case studies is potential ________ and pure _______.
confounding; chance
234
In a single-case study, a single _____ consists of a series of observations of the same individual "under the same conditions"; a ______ _____ is an observation/measurement made while no treatment is being administered ("A"); and a ______ ______ is an intervention observation (i.e. observations during treatment denoted by "B").
phase; baseline phase; treatment phase
235
The ______ design is a single-subject/case experimental method consisting of baseline, treatment, return to baseline, and a second treatment phase.
ABAB
236
In A-B-B1-A-BC-C, what is B1? C?
B1 is a treatment that was modified from B; C is a new treatment
237
In a single-case study, even/consistent magnitude for a series of observations is called ______; a consistent difference in direction and magnitude from one measurement to the next is a _______; and the degree to which a series of observations show a 'consistent' magnitude or direction is ________.
level; trend; stability
238
In a single-case study, a change in the conditions from one phase to another usually involving manipulation of the IV (start/stop treatment) is called a ______ ______.
phase change
239
In a single-case study, what's the goal of a phase change?
To demonstrate that manipulating the IV (treatment phase or baseline phase) causes changes in the DV (behavior).
240
In a single-case study, visual inspection techniques (graphs) include 4 characteristics to help determine meaningful change between phases: (1) change in the ______ _____ between phase means; (2) ______ change in level where the last data point in one phase is notably different from the first data point in the next phase; (3) change in ______ (baseline is level or steadily increasing, treatment phase is steadily increasing or decreasing in opposition to baseline); and (4) ______ of change where a delay between phase change behavior undermines the experiment.
average level; immediate; trend; latency
241
In a single-case study, ______ of change affects interpretation of the graph (undesirable but a good indication that the treatment needs work!).
latency
242
In a single-case study, the ________ design is an experiment where a baseline phase is followed by a treatment phase, followed by at least one return to baseline, and then repetition of treatment.
reversal design
243
In a single-case study, the goal of ABAB design is to demonstrate that the treatment....?
Causes the change in behavior.
244
An _____ design is an example of reversal design with 4 phases.
ABAB
245
In an _____ design, the graph must show clear change in the overall ______ of behavior, and then the researcher must be able to show _____ of the results (for each phase) in order to prove that the treatment is the cause for the change.
ABAB; level; replication
246
In a single-case study, researchers sometimes have an ______ dilemma when the return-to-baseline may have a detrimental effect on the participant; one solution is to employ the use of a _____-______ strategy.
ethical; multiple-baseline
247
A _______-______ strategy begins with 2 simultaneous baseline phases and then initiates the treatment for the second baseline at a later time.
multiple-baseline
248
A multiple-baseline across _______ is a study which the initial phases correspond to the same behavior for two participants.
subjects
249
A multiple-baseline across ______ is a study in which the initial phases correspond to 2 separate behaviors for the same patient.
behaviors
250
A multiple-baseline across _______ is a study in which the initial phases correspond to the same behavior in 2 separate situations.
situations.
251
A researcher using desensitization techniques to treat arachnophobia, and then employing the same technique sometime later to treat fear of flying in the same patient is employing a multiple-baseline across ______ design.
behaviors
252
A researcher using a treatment for a disruptive child at school notes the treatment is working, and implements the same treatment at a later time in the home is employing multiple-baseline across _______.
situations.
253
Some of the strengths of the multiple-baseline design: it can be used for participants with more than one ______ ______; it can be used for a participant with problems in more than one _________, and it can be used when treatment effect is expected to be _________ (and repetition of phases unlikely).
problem behavior; location/situation; lasting
254
Single-case designs tend to be more _______ than traditional group studies, but they require _______ assessment.
flexible; continuous
255
Advantages of single-case designs include evidence of _______, ______ to integrate experimental research with clinical research, and ability to create ________ treatments.
causation; flexibility; individualized
256
Disadvantages of single-case designs include low _____ and _____ validity, _______ observations, and reliance on ______ to demonstrate real efficacy of treatments due to the absence of statistical controls.
internal and external; continuous; graphs
257
Practical significance vs. statistical significance?
practical = result or treatment effect is large enough to have value in the "real world"; statistical = a result/treatment effect is large enough to be extremely unlikely to have occurred by chance.
258
Statistical methods serve 2 principle purposes: to _____ and ____ the data in order to communicate the results to others; and help answer the questions that initiated the research by determining what ________ are justified.
organize and summarize; conclusions
259
_____ statistics are methods that help "organize, summarize, and simplify" the results obtained from research studies; whereas _______ statistics enable researchers to use the results to help make "generalizations about populations" via hypothesis testing and prediction.
Descriptive; inferential
260
A _______ is a summary value that describes a sample or an entire set of scores in the sample, and provides information about the corresponding summary values for the entire population.
statistic
261
A ________ is a summary value that describes the population.
parameter
262
The goal of descriptive statistics (not to be confused with descriptive research) is to organize scores (e.g., creating a _______) or _______ summary values that describe the entire group.
graph; computing
263
A _______ _______ ________ is a table or graph that describes how many scores are located in each category by displaying the set of categories that make up the scale of measurement, and by listing the number of individuals w/ scores in each category.
frequency distribution table.
264
A frequency distribution table consists of _____ columns of information; one column for the ______ of ______, the other for the ________.
two; scale of measurement; frequency
265
Frequency distribution graphs for interval or ratio scales utilize one of two graphs: a _________ where vertical bars indicate the frequency of each score; or a ________ showing a point above each score corresponding to the frequency, and who's points are connected by straight lines.
histogram; polygon
266
Histograms and polygons show the scale of measurement (categories) along the ______ axis and the frequency along the ______ axis.
horizontal (x); vertical (y)
267
Frequency distribution graphs for nominal or ordinal data are _____ graphs with the vertical bar indicating frequency of each score, and the horizontal bar indicating the category.
bar graph
268
A bar graph measures data from _____ or _____ scales; a histogram or polygon measures data from ______ or _____ scales.
nominal or ordinal; interval or ratio
269
_____ _______ is a statistical measure that identifies a single score that defines the center of a distribution, and the goal is to ID the value that is most representative of the entire ________.
Central tendency; group
270
The _____ _____ is a measure of variability that describes the "average distance" from the mean, and is obtained by taking the square root of variance.
standard deviation
271
The distance of "each sample score" from the mean is called the ________; squaring each of these distances and computing the average (minus 1) is called __________.
deviation; variance
272
When describing non-numerical data (nominal and ordinal), one way to do so is to report the ________ or ________ of each category; additionally, for nominal scales, report the ________ - it will ID the most typical member of the sample.
proportion or percentage; mode
273
Line graph vs. polygon?
Polygon is connected to the X axis and displays frequency distribution for interval and ratio data; line graph does not connect to the X axis and displays summary statistics.
274
Factorial studies use _______ and _______ graphs to depict data.
matrices and line graphs
275
Correlational studies use ______ _____ or _______ to depict data
scatter plots or tables
276
The statistical process of finding the linear equation is called _______.
regression
277
Tables and graphs allow you to see all of the _______.
data
278
Correlations measure and describe 3 aspects of the relationship between 2 variables: (1) the _______ of the relationship (+ or -); (2) the ____ of the relationship (linear or monotonic); and (3) the consistency or strength of the relationship.
direction; form
279
What is the mathematical statement for the line of best fit between a criterion and predictors?
regression equation
280
Using IQ and SAT scores to predict college GPA is and example of a ______-______ equation.
multiple-regression
281
______ _______ is the naturally occurring difference between a sample statistic and the corresponding population parameter.
Sampling error.
282
In ________ statistics, researchers need to differentiate between results that represent real patterns/relationships vs sampling error.
Inferential
283
A ______ test uses simple data to evaluate the credibility of a hypothesis about a population; it ensures the _____ validity of the study, and its goal is to rule out chance/______ error as the explanation for the result.
hypothesis; internal; sampling
284
There are 5 basic elements to a hypothesis test: the ____ hypothesis (no change), the sample statistic, the standard ______, the ______ statistic, and the alpha level.
null; error; test
285
The _____ hypothesis states that any patters in the sample are due to nothing other than chance / sampling error.
null
286
The ________ statistic is the statistic used to reject or fail to reject the null hypothesis.
Sample statistic
287
The ______ ______ is the measure of the average / standard distance between a statistic and the parameter. It provides a measure of how much difference is reasonable to expect between a statistic and a parameter (how much discrepancy to expect).
standard error
288
The _______ statistic is a mathematical technique for comparing the sample statistic with the null hypothesis (a large value indicates a large discrepancy and usually leads to rejecting the null hypothesis).
test
289
The ______ level (AKA level of significance) is the criterion for statistical significance that defines the maximum probability that the result can be obtained by chance alone.
alpha
290
A ______ ____ error is a false report (report of a significant result when there wasn't one); they occur when the sample is an _______ sample.
A Type I error; extreme
291
A ______ _______ error is a conclusion that the result isn't statistically significant, when in fact, it was (just really small). That can be fixed by ______ the experiment and using stronger ________.
Type II error; repeating; treatments
292
Factors that influence the outcome of a hypothesis test are the ________ of scores (i.e. the law of ______ _____); and the size of the _______.
number; (law of large numbers); variance.
293
Three techniques used for sampling observations are (1) _____ sampling [observation interval, recording interval, 2nd observational interval, 2nd recording interval, etc.]; (2) _____ sampling [observe behavior A, record, observe behavior B, record, etc]; and (3) ______ sampling [1st interval, 1st participant observed; 2nd interval, 2nd participant observed, etc.].
Time; event; individual
294
OxO vs. OOOOxOOOO
pretest-posttest vs. time-series
