Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
73 Cards in this Set
- Front
- Back
|
what is basic research?
|
research completed to learn about relationships among variables regardless of any immediate commercial product. driven by scientist curiosity, expand knowledge
poor! |
|
|
What is applied research?
|
grant research heavily funded. to invent something and further the consumer. solve problems
|
|
|
what is qualitative research?
|
seeks detailed knowledge of specific cases, with the goal to find out “how” things happen
|
|
|
what is Quanitative research?
|
inquires in which observations are observed predominately in numerical terms. To develop and employ mathematical models
|
|
|
nomothetic research?
|
scholarships designed to find general laws that apply to many
|
|
|
idiographic?
|
: scholarships design to develop a full understanding of an event/indiv
|
|
|
Unobtrusive Measures
|
A method of studying social behavior without affecting it, they may be qualitative or quantitative, ex. Content analysis
|
|
|
Triangulation
|
cross examination, two or more methods are used in a study. To increase credibility and validity of the results. “cross checking data for multiple sources”
|
|
|
Intersubjectivity
|
Diff researchers, with diff beliefs draw the same interpretations of the meaning of observations. “shared meanings
|
|
|
Empirical
|
Observable research, test statements against an observable data
|
|
|
Dichotomization
|
to divide into parts such as groups and classes
|
|
|
Falsification?
|
any theory must be testable, must deal with statements that can be falsifed
|
|
|
Conceptualization
|
The process of specifying what is meant by the term. Ex. “what is meant by “X” in this research
|
|
|
Operationalization
|
taking specific conceptualized constructs and translating them into specific measures that can be used to collect data. Ex. How was “X” measured
|
|
|
Reliability
|
consistency. over time repeated
|
|
|
Validity
|
Judge results, measuring tools. A valid result is one that accurately measures what it claims to be measuring
|
|
|
External
|
: Accuracy of scientific results, refers to the generalizability of the treatment/condition outcome
|
|
|
Internal Validity
|
criteria against which research results are judged. Ex. To be internally valid, the results of an experiment are considered to be accurate indications of the manipulation of an IV. refers specifically to whether an experimental treatment/condition makes a difference or not, and whether there is sufficient evidence to support the claim
|
|
|
Experimenter Effect
|
experimenter acts in a way to influence the participant to act in favor of the study)
|
|
|
Observer Bias
|
preset bias of the situation by the observer.
|
|
|
Researcher attribute Effect
|
(what the researcher is doing/wearing/looks like influences the results
|
|
|
Participant related
|
History:events in the participants’ environment (other than the manipulated ind.var.) occur during the course of the experiment that may affect the outcome
Maturation:any psych. or phys. changes taking place within participants that occur over time (regardless of the exp. manipulation): short & long term effects - Testing:= taking the pretest may affect how participants do on the posttest – Instrumentation:unwanted changes in characteristics of the measuring instrument/measurement procedure Statistical Regression:= tendency for extreme score on a test to move (regress) closer to the mean on a 2nd administration of the test Selection:sampling biases in selecting/assigning subjects to conditions Experimental Mortality:= losing participants (drop outs Social Interaction:Diffusion or imitation of treatment Compensatory rivalry, Resentful demoralization, Compensatory equalization of treatment |
|
|
Threats to External Validity
|
1 – Effects of Testing = interaction testing & exp. var. (“pretest sensitization”)
2 – Effects of Selection = interaction selection & exp. var. 3 – Reactive Arrangements = reactions toward arrangement vs. variable 4 – Multiple Treatment Interference= reactions in non-generalizable ways |
|
|
Deductive Approach
|
Gives primacy to theory- how people talk to each other
|
|
|
Inductive Approach
|
Gives primacy to observation- instead of having theory tell us, we observe how people interact, based on our observation we say wether something applies to a theory
|
|
|
Sampling bias
|
tendency for the sample to err so that it fails to represent the population
|
|
|
Sampling error
|
degree to which a sample differs from the population (on some measure)
|
|
|
Nonrandom Sampling
|
1.1. Convenience Sampling
1.2. Quota Sampling 1.3. Known Group Sampling 1.4. Snowball Sampling |
|
|
Advantages/Disadvantages of Nonrandom-Sampling
|
+ sampling naturally occurring events
+ getting samples that would otherwise be unavailable - sampling bias - sampling error cannot be computed - findings cannot be generalized |
|
|
. Random Sampling
|
2.1. Simple Random Sampling
2.2. Systematic Sampling 2.3. Stratified Random Sampling 2.4. Cluster Sampling |
|
|
causation
|
1. Association - Both variables are correlated.
2. Time Order - The cause precedes the effect. 3. Nonspuriousness - Alternative explanations can be ruled out |
|
|
Experimental Design
|
X = treatment condition
O = observation/measurement of DV R = random assignment (if no R, then no random assignment) each line = a group |
|
|
Likert scale
|
Scales composed of Statements that reflect clear positions on an issue, for which subjects indicate their agreement on typically five-point scales
|
|
|
Semantic Differential
|
Scales (often seven-point intervals) bounded by pairs of bipolar adjectives. “How people assign meaning to words
|
|
|
Types of Variables
|
DV= Variables whose values or activities are presumed to be conditioned on the independent variable in the hypothesis. (Predicted Variable)
IV= Variables that predict outcomes (DV) posited in hypothesis. Exogenous= Outside factors Endogenous= “Within” factors |
|
|
Moderator
|
affects the direction and or strength of the relation between the (IV&DV)
|
|
|
• Mediator
|
the intervening variable between stimuli & response
|
|
|
4 levels of measurment?
|
Nominal: names categories
Ordinal: well ordered set Ration: has a zero point interval: evenly spaced numbers |
|
|
• One-tailed
|
(directional): prediction a trend of a difference or relationship (pos/neg) all alpha risk on one side
|
|
|
two tailed:
|
non directional,predicting a diff/relationship w/o indicating a trend. Alpha risk on 2 tails
|
|
|
skewness:
|
negative skew: The left tail is longer; the mass of the distribution is concentrated on the right of the figure
positive skew: The right tail is longer; the mass of the distribution is concentrated on the left of the figure |
|
|
kurktois
|
high peak!
|
|
|
central tendency!
|
mean, median mode
|
|
|
manifest anylsis
|
concrete terms directly visible
|
|
|
latent anaylsis
|
underlying meaning contained within text
|
|
|
Threats to Reliability with content anaylsis
|
Bad coding shceme, inadquite coder training, coder fatigue,presence of a rogue coder
|
|
|
Advantages to content analysis
|
Unobtrusive, inexpensive, longitudinal analysis, historical analysis, transparency & replication, access to valuable information, variety of media channels
|
|
|
Disadvantges to content analysis
|
time-consuming, interpreting coding manuals → intra-reliability & inter-reliability, analysis only as good as a) the documents b) their sampling, no causality, latent (implicit) content: misleading inferences, explanatory function (“atheoretical” research), external validity
|
|
|
Steps in conducting content analysis
|
1.Identifying Topic Domain
2.Identifying Data Sources 3.Defining + Limiting the Population 4.Selecting Coding Units + Classification Systems 1.exhaustive categories 2.mutually exclusive 3.coding rules in place 5.Sampling Messages 1.random 1.stratification 2.cluster / multi-stage 6.Coding Message Content 1.coder training (outsider) 2.determining consistency 7.Analyzing Data 1.Descriptive stats 2.χ² 3.Mean differences 4.Correlational data 8.Interpreting Results |
|
|
Coding units
|
categories used to count or rate the communication forms in the examples chosen
|
|
|
coding scheme
|
categorizing content can be difficult
|
|
|
Theoretical Function (i.e., Description, Explanation)
|
1.Description (behavior characterized into different forms)
2.Explanation (event as an instance of a larger system of things) 3.Prediction (what can be expected in subsequent tests to be made) 4.Control (power to direct things) |
|
|
Content Analysis - A Scientific Method
|
Objectivity-Intersubjectivity
-avoid biases -objectivity is the ultimate goal, but human inquiry is ultimately intersubjective 2) A priori design -deductive: coding rules must be made before observation begins -inductive: revising coding scheme 3) Reliability -intercoder reliability -level of agreement among 2 or more coders 4) Validity (“Does the measure really identify the variables alleged?” - face - content 5) Generalizability -usefulness 6) Replicability -accurate + independent reproducibility 7) Hypothesis Testing -exploratory research → confirmatory research |
|
|
Textual Analysis
Neo-Aristotelian Criticism |
Arrangement: concering organization
Style: use of language Delivery: voice and gestures Memory: ablitiy to recall passages Invention: types and sources of ideas. |
|
|
Discourse analysis
|
examines naturally occurring messages for the purpose of determining “how talk/texts are used to perform actions
|
|
|
conversational analysis
|
attempts to explore the structure + sequencing of turn-taking exchanges
|
|
|
Ethnography
|
Speech communities :not individuals
|
|
|
Emic
|
from group member’s perspective
-“culturally relative approaches” -using local language + terminology |
|
|
etic
|
from outsider observer’s perspective
-material (rather than cultural) explanations -questions cannot be easily duplicated |
|
|
forms of participant observation
|
complete participant
- participants’ lack of awareness that they are being observed - active involvement of the researcher - complete observer - participants NOT aware that they are being observed - NO active involvement of the researcher |
|
|
Urban Archaeology
|
examination of modern artifacts of urban life
|
|
|
Accretions”/“Deposits
|
material left by some action
|
|
|
“Erosions
|
wear or the use of objects
|
|
|
Grounded Theory
|
a set of explnations that has immediate relevance to a specfic field setting under investigation.
|
|
|
Meta-Analysis
|
Primary,
original data analysis Sec data re-analysis |
|
|
Assumptions of meta analysis
|
1) Only empirical studies
- incl. sample sizes + effect sizes → comparing effect sizes, not statistical significances 2) Studies are independent = groups/samples/studies are unaffected by each other 3) Studies must be comparable - Do the studies follow similar design and procedures? - independence vs. comparability |
|
|
Steps in Conducting Meta-Analysis Research
|
1) Sampling Studies
- quantitative - representativeness - time-consuming process - published vs. unpublished results - ‘publication bias’ - ‘file-drawer-effect’ 2) Computing Relationship Sizes - effects in correlation form - standardized difference scores 3) Identifying Essential Differences - coding research study characteristics (e.g., year, study design, # of IV, moderators, etc.) - study quality (rated by group of experts) – intersubjectivity! 4) Assessing Mean Relationship Sizes - weighing studies based on N (larger sample size = more stable effect sizes) 5) Making ‘Diffuse’ Comparisons - tests of homogeneity of effect sizes - to see whether there is another variable that contributes to the variance associated w/ different study outcomes 6) Making ‘Focused’ Comparisons - tests to determine whether differences in other variables are related to differences in the sizes of study effects on primary variables - examining moderators via correlations w/ effect sizes |
|
|
Publication bias
|
Tenendcy for research publications to favor empirical studies.
|
|
|
File Drawer Effect
|
Tendency for studies that fail to find signifigant relationships to remain unpiblished
|
|
|
Diffuse
|
Measures of the homogeneity of effect sizes in mea-analyses
|
|
|
Focused Comparisons
|
assessments in meta anaylyses to determine whether differences in other variables are related to differences in the sizes of study effects on primary variables.
|
|
|
Major Advantages to meta
|
+ concrete outcome
+ distance from personal biases + capable of replication (statistically) + greatest representation of studies w/ least sampling error |
|
|
Disadvantages to meta
|
-only quantitative research
-moderators must be previously studied -secondary analyses only -no assessment of conceptual issues |
