2017-09-21 01 Exam Flashcards
primary research article
(A & L, 32)
- author(s) report original research they conducted
steps in the research process
(A & L, 11-25)
Aka the scientific method
1) identify your topic: interests you and others based on an established opinion/belief, no special/specific participants, have q’s but read past research to develop a strong hypothesis/design
2) find, read, and evaluate past research to develop hypothesis/research q: constantly look at past research
3) further refine topic and develop a hypothesis/research q: testable hypothesis
4) choose research design: feasible with resources and time, ethical
5) carry out your study: approval from professor, IRB
6) analyze the data: chose analysis based on hypothesis
7) communicate results: fit/don’t fit with past research, limitations
correct format for research article
(A & L, 48-58) (in-class 8/31)
1) Abstract
2) Introduction
3) Method
3) a) Participants
3) b) Procedure
3) c) Measures
4) Results
5) Discussion
abstract
(A & L, 51) (in-class 8/31)
- 150-200 words
- like a movie trailer (but spoils the end)
- always first, but created last
introduction
(A & L, 53) (in-class 8/31)
- introduces topic, why it’s important (why people should care)
- build case for study: describe past research, gaps in it, and limitations (organize broad to narrow)
- introduce new study, how it’s addressing past limitations/gaps
- state hypothesis/research questions
method
(A & L, 54) (in-class 8/31)
a) Participants
- how many, who are they, consent?, was anyone excluded
b) Procedures
- what did you do step-by-step, data collection process, include anything relevant for replication
c) Measures
- what were key variables?, how were they measured?, example items, scale scoring
results
(A & L, 56) (in-class 8/31)
- “just the facts”
- objective description of the results
EX: X correlated with Y
discussion
(A & L, 57) (in-class 8/31)
- restate hypothesis: if findings supported past research, relate to previous research
- describe limitations
- why results are interesting/useful
correct APA format and references format
(in-class 8/31) Dutton, H., & Shen, H. (2017). Title: No more uppercase letters. Just Journal in Italics: 40(5), 223-225. dio:00000
steps to ensure a study is ethical
(A & L, 3-11) (in-class 8/29)
- informed consent: explain study purpose, can withdraw at any time, risks
- confidentiality: only researchers and participants know defining characteristics (anonymity: only participant knows)
- incentive: nothing unreasonable (a million dollars)
- deception: none or ethical
- debriefing, answering questions: asap after the study
- approval from IRB
descriptive research design
(A & L, 106, 117)
- Survey
- Interview
- Questionnaires
- Observational
- Archival
correlational research design
(in-class 8/29) (A & L, 20)
- looks for relationship of 2 observed variables
- all about causation
experimental research design
(A & L, 19)
- determines causal relationship by manipulating IV, measuring DV, and random assignment
independent variable (and levels)
(A & L, 21) (in-class 8/29) - variable that's manipulated in an experiment Levels: a control group and then 1 or more other assignments/groups
dependent variables
(A & L, ) (in-class 8/29)
- variable that’s measured in an experiment
- expected to change based on IV
study reliability and replication
(A & L, 69-71, 76) (in-class 9/4)
- how generalizable is the study?
- extent to which a set of findings is reproducible
- does the measure have similar results in many trials
- are there relatively low levels of measurement error?
internal validity
(in-class 9/4, 9/7) (A & L, 71) (in-class 9/4: 351)
- all about causation
- allows researchers to state that they’ve identified causal associations
- was the IV the sole cause of changes in the DV
EX:
- high: well controlled experiment (ideally with random assignment)
- medium: correlational study with statistical controls
- low: did not rule out potential third-variable explanations
scales of measurement
(in-class 9/4) (A & L, 79-83)
- nominal
- ratio
- interval
- ordinal
nominal scale
(in-class 9/4) (A & L, 80)
- identity (each number has a specific meaning)
- used to measure categories
ratio scale
(in-class 9/4) (A & L, 80)
- identity (each number has a specific meaning), order (numbers on a scale, in ordered sequence), equal intervals (distance between numbers on the scale is equal), true zero (fixed-point)
- used to measure quantities
interval scale
(in-class 9/4) (A & L, 80)
- identity (each number has a specific meaning), order (numbers on a scale, in ordered sequence), equal intervals (distance between numbers on the scale is equal)
- used to measure ratings
ordinal scale
(in-class 9/4) (A & L, 80)
- identity (each number has a specific meaning), order (numbers on a scale, in ordered sequence)
- used to measure rankings
operational definition
(in-class 9/4) (A & L, 77)
- specifics of how the variable is measured
- so it can be exactly replicated
construct validity
(in-class 9/4: 351)
- abstract psychological phenomenon
- inferred from observable behavior
EX: love, attraction, engagement
– need to be specific in how you’re going to measure (unlike a ruler)
- did the authors measure or manipulate ~all facets of the concept~ that they claim to be measuring or manipulating?
- can’t measure directly
measurement validity
(A & L, 76)
Measurement is accurate and measure’s what it’s supposed to
- Construct validity (content, divergent, criterion[predictive, concurrent])
content validity
(in-prac 9/11) (A & L, 93)
construct validity
- have to measure all aspects of the construct
EX: only measuring one part, but now the full range of what’s being measured
divergent validity
(in-prac 9/11) (A & L, 94)
construct validity
- negative or no relationship between 2 scales measuring different constructs
- 2 measures that only really measure one thing
criterion validity
(in-prac 9/11) (A & L, 94)
construct validity
- positive correlation between scale scores and a behavioral mesaure
measurement reliability
(in-class 9/4) (A & L, 90) - internal consistency (Cronbach's Alpha, split-half reliability), test-retest reliability, alternate forms reliability, inter-rater reliability
internal consistency
(in-class 9/4) (in-prac 9/11) (A & L, 91)
Consistency of participants responses to all items in a scale
- Cronbach’s Alpha, split-half reliability
Cronbach’s alpha
(in-prac 9/11) (A & L, 91)
measures internal consistency
- computes inter-correlations of scale items
- values >0.7 are acceptable internal consistency
- when alpha is <0.7, sometimes items deleted to reach 0.7 standard
split-half reliability
(in-prac 9/11) (A & L, )
measurement reliability
- correlations between 2 halves of the items on a scale (ex: even number items correlated with odd-numbered items
- values >0.7 are considered acceptable reliability
test-retest reliability
(in-class 9/7) (in-prac 9/11) (A & L, 91)
measurement reliability
- check again if the measurement could be unstable
- same question, different answer (means question is picking up something else)
interrater reliability
(in-class 9/7) (in-prac 9/11) (A & L, 91)
measurement reliability
- for when people are being observed, field work with complicated behaviors (not relevant for survey data [questionnaire])
- multiple people coding
3 criteria of an experiment
(A & L, 19)
1) random assignment
2) manipulation of IV
3) measurement of DV
descriptive study
(A & L, 19)
- describe variables, but don’t examine relationship or causation
Survey research
(A & L, 106)
Descriptive research design
- interviews or questionnaires where participants report attitudes or behaviors
- Advantages: insight into how participants see themselves, can be administered easily (online, a lot at a time)
- Disadvantages: social desirability bias, interviews time consuming, interviewer bias, questionnaire don’t get as much in depth info
interview
(A & L, 106, 117)
Descriptive research design, survey
- 1-1 conversations directed by researcher
- phone, in person, email
- can’t be anonymous, but can be confidential
questionaire
(A & L, 85, 108, 117)
Descriptive research design, survey
type of measurement
- allow for anonymity (reduce social desirability bias)
- can be administered easily (online, a lot at a time)
- asses one or more construct
observational study
(A & L, 109)
Descriptive research design
- recording behavior
- can be in addition to other research methods
- Advantages: reduce social desirability bias, time consuming to record and code data, potential observer bias)
social desirability bias
(A & L, 106)
- in self-reports, people responding in what they thing is the most desirable or ideal
Convert observation
(A & L, 111)
Descriptive, observational
- observations made without participants knowing
- to capture participants natural and spontaneous reactions
- can be unethical (can be in a public place)
overt observation
(A & L, 111)
Descriptive, observational
- no attempts made to hide observation
- participants could change behavior if they know they’re being watched
- researchers usually give time for participants to acclimate to situation
naturalistic observation
(A & L, 112)
Descriptive, observational
- observations that occur in natural environments/situations
- don’t involve interference by any researcher
contrived observation
(A & L, 112)
Descriptive, observational
- researcher sets up situation and watches how participants respond
- can be event, physical stimulus, asking participants to complete a task, etc
nonparticipant observation
(A & L, 112)
Descriptive, observational
- researcher/observer isn’t directly involved in the situation
participant observation
(A & L, 112)
Descriptive, observational
- researcher/observer is actively involved in the situation
external validity
(in-class 9/4: PSY 351) - ~generalizablilty~ to population of interest (not always everyone) - are the results true for other: participants? settings? times? EX: - high: large, random selection of participants from population of interest; procedure similar to situation of interest - low: small convenience sample with major differences from population of interest; procedure different frem situation of interest
convergent validity
(in-class prac 9/11) (A & L, 93-95) construct validity - positive relationship between 2 scales measuring the same or similar items
concurrent validity
(A & L, 95)
construct validity, criterion validity
- positive correlation between scale scores and a current behaviors that’s related to the assessed construct
predictive validity
(A & L, 95)
construct validity, criterion validity
- positive relationship between scale scores and future behaviors that’s related to the assessed construct
reliability
(in-class 9/7) - extent a set of findings is reproducable
types of measures
(A & L, 84-89)
- Questionnaire
- response format (open-ended response, closed-ended, forced-choice)
response formats
(A & L, 86-89)
- open ended response
- closed-ended
- forced choice
open-ended response format
(A & L, 86-89)
- item on a scale that has respondents generate their own answers
closed-ended response format
(A & L, 86-89)
- items that have limited number of choices for respondents to choose from (multiple choice)
forced-choice response format
(A & L, 86-89)
- response format where respondents cannot be neutral (yes/no, true/false)
(nominal)
population
(A & L, 118)
- group researchers are interested in
- defined by specific characteristics
subpopulation
(A & L, 118)
- portion/subgroup of the population
sample
(A & L, 119)
- subset of population the data is collected from
sampling
(A & L, 119)
- process of how the sample is selected
sampling bias
(A & L, 119)
- when some members of the population are overrepresented
probability sampling (random sampling)
(A & L, 121)
- sampling procedure that uses random selection
- ideal, (external validity/generalizable)
- simple random, stratified random, cluster sampling
random selection
(A & L, 121)
- all individual members of a population or sub-population have an equal chance of selection
random selection with placement
(A & L, 121)
- selected members of the population are returned to the pool of possible participants
- any member can be selected into the sample more than once
random selection without placement
(A & L, 121)
- selected members of the population are removed to the pool of possible participants
- member can be selected only once
simple random sampling
(A & L, 122)
probability sampling
- every member as equal chance of being selected
stratified random sampling
(A & L, 122)
probability sampling
- key populations are represented based on characteristics (age, gender, ethnicity)
cluster sampling
(A & L, 122)
probability sampling
- groups (or clusters) are randomly selected, instead of individuals based on categorization (ex: specific schools when target pop is middle schoolers)
non-probability sampling (non-random sampling)
(A & L, 123)
- sampling procedure that doesn’t use random selection
- less time (no need to identify all participants [members, clusters] in a population)
- if researcher can’t identify all members/clusters, appropriate sample size, and/or minimize non-response data
- convenience, quota, maximum stratification, snowball,
convenience sampling
(A & L, 129)
non-probability sampling
- sample is volunteers who are readily available and willing to participate
- typically have an over-represented group
- easiest (feasable)
quota sampling
(A & L, 130)
non-probability sampling
- results in the sample represent key sub-populations based on characteristics (age, gender, race)
maximum variation sampling
(A & L, 131)
non-probability sampling
- researcher seeks out full range of extremes in the population
snowball sampling
(A & L, 132)
non-probability sampling
- participants recruit others into the sample
non-response bias
(A & L, 122)
- when participants don’t answer all questions, or data differs from participants who did participate
descriptive statistics
(A & L, 142)
- used to analyze quantitative and qualitative data
- quantitative analysis used to summarize characteristics of a sample
- frequency, percentage
frequency
(A & L, 143)
descriptive statistic
- how many times a score is in a sample
percentage
(A & L, 143)
descriptive statistic
- proportion of a score in a sample
central tendency
(A & L, 147)
- central score
- summarizes center of distribution
- mode, median, mean
mode
(A & L, 149)
measures central tendency
- most frequent score in a distribution
median
(A & L, 149)
measures central tendency
- halfway point of distribution
mean
(A & L, 149)
measures central tendency
- arithmetic average
variability
(A & L, 150)
- how much scores are different from each other in a sample
- observed minimum, observed maximum, range, standard deviation
observed minimum
(A & L, 150)
measures variability
- lowest score in the sample
observed maximum
(A & L, 150)
measures variability
- highest score in the sample
range
(A & L, 150)
measures variability
- distance between observed minimum and maximum
standard deviation
(A & L, 150)
measures variability
- how much in general the scores in a sample differ from the mean
descriptive statistics for nominal data
(A & L, 170)
- frequencies and/or percentages
- CT: (sometimes mode)
- variability: –
descriptive statistics for ordinal data
(A & L, 170)
- (sometimes: frequencies and/or percentages)
- CT: median
- variability: observed min and max
descriptive statistics for interval or ratio (normal distribution)
(A & L, 170)
- (sometimes: percentages for each score on an interval scale)
- CT: mean
- variability: standard deviation (sometimes: possible min/max for interval, observed min/max for interval and ratio)
descriptive statistics for interval or ratio (skewed)
(A & L, 170)
- (sometimes: cumulative percentage)
- CT: median
- variability: observed min/max or range
archival research
(A & L, 113)
- analysis of existing data/records
- Advantages: no direct data collection, large time frame, fewer ethical decision, can study some behaviors/attitudes that can’t be obtained through survey/observation
- Disadvantages: obtaining data, could need to adjust hypothesis, time consuming to collect and code data
bar graph
(A & L, 158)
- for nominal or ordinal data
- y axis: frequency of scores
- x axis: data or ranks
graphing nominal data
(A & L, 158)
- bar graph
graphing ordinal data
(A & L, 158)
- bar graph
histogram
(A & L, 161) - graph showing interval or ratio data - y axis: frequency of scores - x axis: interval ratings or ratio scores (shown like a bar graph)
frequency polygon
(A & L, 161)
- graph showing interval or ratio data
- y axis: frequency of scores
- x axis: interval ratings or ratio scores
(dots represent points, connected with straight lines, connect to 0 on x axis on both ends)
uniform distribution
(A & L, 163)
- non-normal distribution
- where all scores are the same
bimodal distribution
(A & L, 163)
- non-normal distribution
- has 2 peaks
skewed distribution
(A & L, 163)
- non-normal distribution
- scores on one side with a tail on the other
positively skewed distribution
(A & L, 163) (in-class 9/14)
- non-normal distribution
- tail on positive side (where it pulls the data), peak on negative side
EX: income, number of sexual partners)
negatively skewed distribtion
(A & L, 163) (in-class 9/14)
- non-normal distribution
- tail on negative side (where it pulls the data), peak on positive side
EX: number of fingers on adults
outliers
(A & L, 163)
- responses/observations that are different from the rest of the data
validity
(in-prac 9/18)
accuracy
reliability
(in-prac 9/18)
consistency
pilot study
(in-prac 9/18)
- still with target population
- test before spending money
- work on any possible changes
accuracy
(in-prac 9/18)
validity
consistency
(in-prac 9/18)
reliability