Week 4 Flashcards
1
Q
correlation (2)
A
- there is a relationship between two or more variables
- relationship does not necessarily imply cause and effect
2
Q
What does it mean when two variables are correlated?
A
- as one variable changes, so does the other
3
Q
correlation coefficient (3)
A
- number from -1 to +1 that indicates strength and direction of relationship between variables
- represented by letter r
- a statistic that is calculated to measure correlation
4
Q
What does the number portion of correlation coefficient indicate?
A
- strength of the relationship
5
Q
What does it mean when the correlation coefficient is closer to one (positive or negative)? (2)
A
- the more strongly related the variables
- the more predictable changes in one variable will be as the other variable changes
6
Q
What does it mean when the correlation coefficient is closer to zero? (2)
A
- the weaker the relationship
- the less predictable the relationships between the variables become
7
Q
What does a correlation coefficient value of zero indicate?
A
- no correlation
8
Q
What does the sign (positive or negative) of the correlation coefficient indicate?
A
- direction of the relationship
9
Q
What does a positive correlation coefficient indicate? (2)
A
- variables move in the same direction
- when one variable increases, the other variable increases
10
Q
What does a negative correlation indicate? (2)
A
- variables move in opposite direction
- decrease in one variable is associated with a increase in the other variable
11
Q
What are examples of positive correlation? (2)
A
- relationship between an individual’s height and weight
- relationship between person’s age and number of wrinkles
12
Q
What is an example of a negative correlation?
A
- relationship between one’s tiredness during the day and the number of hours they slept the previous night
13
Q
Why is correlational research useful?
A
- allows us to discover strength and direction of relationships that exist between 2 variables
14
Q
Why is correlation limited?
A
- establishing existence of a relationship tells us little about cause and effect (causation)
15
Q
confounding variable (2)
A
- unanticipated outside factor that affects both variables of interest
- often giving the false impression that changes in one variable causes changes in the other variables, when the outside factor causes changes in both variables
16
Q
cause and effect relationship
A
- changes in one variable cause the changes in the other variable; can be determined only through an experimental research design
17
Q
Where are claims of causation as a function of correlations common?
A
- advertisements and news stories
18
Q
illusory/false correlations
A
- occur when people believe that relationships exist between two things when no such relationship exists
19
Q
Why are we so apt to believe in illusory correlations? (3)
A
- often we read or hear about them and simply accept information as valid
- we may have a hunch and look for evidence to support the hunch, ignoring evidence that would tell us our hunch is false
- what we believe based on information that comes easily to mind, even if severely limited
20
Q
confirmation bias
A
- highlighting evidence that supports our belief and ignoring contradictory evidence
21
Q
What are the drawbacks of illusory correlations? (2)
A
- certain behaviours inaccurately attributed to certain groups
- involved in formation of prejudicial attitudes that can lead to discriminatory behaviour
22
Q
What is the only way to establish a cause-and-effect relationship between 2 variables?
A
- conduct a scientific experiment
23
Q
How is a hypothesis formulated?
A
- formulated through direct observation of the real world or after careful review of previous research
24
Q
What two groups does the most basic experimental design involve?
A
- experimental group and control group
25
experimental group
- receives experimental manipulation, the treatment or variable being tested
26
control group
- does not receive experimental manipulation
27
operational definition (2)
- description of how we will measure our variables
| - important in allowing others to understand exactly how and what a researcher measures in a particular experiment
28
Why are operational definitions important to an experiment?
- aids peoples' ability to interpret our data as well as their capacity to repeat our experiment
29
experimenter bias
- possibility that researcher's expectations might skew the results of the study as they observe behaviour
30
single-blind study
- one of the groups (participants) are unaware as to which group they are in (experiment or control) while the researcher who developed experiment knows which participants are in each group
31
double-blind study (3)
- both researchers and participants are blind to group assignments
- control for both experimenter and participant expectations
- method for avoiding confounded variable
32
placebo effect
- people's expectations or beliefs influence or determine their experience in a given situation; expecting something to happen can actually make it happen
33
independent variable (2)
- manipulated or controlled by experimenter
| - only important difference between experimental and control groups
34
dependent variable
- what researcher measures to see how much effect the independent variable had
35
What do we expect when looking and the independent and dependent variable?
- we expect the dependent variable to change as a function of the independent variable
36
participants
- subjects/individuals involved in psychological research
37
Which group is used often for psychological research?
- college students
38
What characteristics define college students relative to the general population? (4)
- younger
- more educated
- more liberal
- less diverse
39
Why can just using college students for psychological research be problematic?
- relying on such a limited pool of research participants can be problematic because it is difficult to generalize findings to larger population
40
random sample
subset of larger population where every member of the populations has an equal change of being selected
41
Why are random samples preferred?
- sample is large enough to reasonably be sure that participating individuals are representative of the larger population
- percentages of characteristics in the sample (sex, ethnicity, socioeconomic level, etc) are close to percentages in the larger population
42
How do we find a random sample for an experiment?
- we find a group of about 200 that reflects composition of that city and then we can generalize findings to the larger population without fear of our sample being biased in some way
43
random assignment (3)
- split of participants into experiment and control groups where all participants have equal chance of being assigned to either group
- statistical software will randomly assign each individual into the experimental or control group
- critical for sound experimental design
44
What does random assignment help with? (2)
- in sufficiently large samples, random assignment makes it unlikely for systematic differences to exist between groups
- allows us to assume that any difference observed between experimental and control groups result from manipulation of independent variable
45
quasi-experimental (2)
- type of research where we recognize we cannot make a cause-and-effect claim
- occurs when you cannot directly control the independent variable (eg: person's sex)
46
What is a constraint for experimenters?
- ethical constraints
47
statistical analysis
- analysis conducted after data is collected to find out if there are meaningful differences between the experimental and control groups
48
What does a statistical analysis determine?
- how likely any difference found is due to chance (meaningless)
49
In psychology, what differences are considered meaningful?
- if the odds that these differences occurred by chance alone are 5% or less (if we repeated this experiment 100 times, we would expect to find the same results at least 95/100 of the times)
50
What is the greatest strength of experiments? (2)
- ability to assert any significant differences in the findings are caused by independent variable
- random selection, random assignment, and a design limits effects of both experimenter bias an participant expectancy creates groups that are similar in composition and treatment
51
Who publishes a manual detailing how to write a paper for submission to scientific journals?
- The American Psychological Association (APA)
52
What type of article would be published in a magazine like "Psychology Today"
- targets a general audience with an interest in psychology
53
What is the aim of a scientific jounral?
- aimed at an audience of professionals and scholars who are actively involved in research themselves
54
peer-reviewed journal articles (2)
- article is read by several other scientists with expertise in the subject matter
- peer reviewers provide feedback, to both author and journal editor, regarding the quality of the draft
55
What are peer reviewers looking for? (3)
- strong rationale for research being described, clear description of how research was conducted, and evidence that research was conducted in an ethical manner
- look for flaws in study's design, methods, and statistical analyses
- check that conclusions drawn by author seems reasonable given observations made during research
56
What do peer reviewers comment on and how does it help?
- comment on hoe valuable research is in advancing discipline's knowledge
- helps prevent unnecessary duplication of research findings in scientific literature and ensures that each research articles provides new information
57
What does the journal editor do?
-compile all peer reviewer feedback and determine whether the article will be published in its current state (rare occurrence), published with revisions, or not accepted for publication
58
What does peer review provide for psychological research?
- some degree of quality control; poorly conceived or executed studies are weeded out and even well-designed research can be improved by revisions suggested
- ensures that research is described clearly enough to allow other scientists to replicate it to determine reliability
59
What is the purpose of replication? (2)
- serves to provide evidence to support original research findings
- sometimes replications involve additional measures that expand on original findings
60
What do successful replications do?
- make scientists more apt to adopt those findings from original research
61
What do failed replications do?
- tend to cast doubt on legitimacy of original article and lead scientists to look elsewhere
62
When can a published piece of work be rescinded? (2)
- when data is called into question because of falsification, fabrication, or serious research design problems
- once rescinded, scientific community is informed of serious problems with original publication
63
Who can retract a published journal? (4)
- researcher who led the study
- research collaborators
- institution that employed researcher
- editorial board of the journal where article was originally published
64
What are 2 important considerations that must be made in any type of data collection?
- reliability and validity
65
reliability (2)
- ability to consistently produce given results
| - any instrument or tool used to collect data does so in consistent, reproducible ways
66
validity
- extent to which given instrument or tool accurately measures what it's suppose to measure
67
What are experiments? (2)
- method used by scientists to find out what causes what
| - basically a method of determining causality
68
In general, what does an experimenter design?
- two or more conditions under which the subject will be tested
69
between-subjects design
- different group of subjects is tested under each condition (eg, experimental vs control group)
70
within-subject design
- same group of subjects is tested under each condition
71
counterbalance
- in a within-subject design, splitting the group into two to ensure that the results are correct
72
experimenter expectancy effect
- effects on subjects due to the beliefs or expectations of experimenters
73
non-experimental studies (3)
- descriptive/correlational methods
- case studies
- quasi-experiments
74
Why are quasi-experiments used?
- it is not always possible for psychologists to use experimental method to answer questions of interests, often for ethical reasons
75
confounding variable
- extra variable you did not account for which can ruin an experiment and give useless results
76
descriptive statistics
statistics used to help organize/summarize data
77
inferential statistics (2)
- statistics that allow researcher to make inferences about characteristics of a population, based on the characteristics of a representative sample taken from that population
- used to interpret data and draw conclusions
78
What are three types of descriptive statistics?
1. measures of central tendency
2. measures of variability
3. measures of correlation
79
measures of central tendency
- what is the number that tends to summarize the centre of this group of numbers?
- defined by mean, median, mode
80
mean
- total of all the scores divided by the total number of scores
81
median
-"centre" score once we rank the score, centre-most score
82
mode
- most frequent score
83
bimodal distribution
- two values represent the mode
84
unimodal distribution
- one mode value
85
average
- could be mean, median, or mode
86
What are 3 ways to describe variability?
1. range
2. variance
3. standard deviation
87
range
- difference between the smallest observation and the largest observation
88
variance (3)
- calculate mean
- calculate deviation scores (value from mean) and square these numbers
- variance = sum of squared deviations/number of scores
89
standard deviation
- square root of the variance
90
correlation, video definition (2)
- interested in correlation when you have scores on 2 variables measured on the same participants
- make it possible to use the value of one variable to predict the value of another
91
coefficient of determination (2)
- correlation coefficient squared
| - allows us to determine percentage of variance in the distribution accounted for in the regression line
92
What best describes the distribution of a dataset in a meaningful way?
- standard deviation
93
How do you make a scatter plot on excel?
- highlight data, click insert, click scatter, choose desired plot
94
How do you calculate the correlation coefficient in excel?
- input "correl(date,date)"
95
When does statistical significance exist? (2)
- when probability that observed results are due to chance is below some level
- usually that level is below 5 in 100, referred to as the 0.5 significance level (p = >0.05 = significance
96
t-tests
- written as t(# of subjects minus 1) = t-value, p<0.5
97
can the lab tell us about everyday life? (3)
- might be good at predicting behaviour of groups of individuals, but they are not good at predicting behaviour of an individual
- lab is simplified version of the real world
- psychologists are more interested in testing general principles of behaviour rather than specific behaviours
98
WEIRD
- western, educated, industrialized, rich, democratic
99
Do gender and culture matter for psychological studies?
- YES, but there are still some commonalities in the underlying processes that allow generalization
100
What do ethical guidelines typically urge researchers to do? (4)
1. obtain informed consent from participants
2. protect participants from harm
3. Preserve confidentiality of participant data
4. Debrief participants once an experiment is complete
