EXAM 2 research methods CJ

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/120

encourage image

There's no tags or description

Looks like no tags are added yet.

121 Terms

1
New cards
  • Conceptualization:.


  • The process of specifying exactly what we mean when we use particular abstract terms or concepts (e.g., defining what "recidivism" or "fear of crime" means for a study)


2
New cards
  • Operationalization:


  • Developing specific research procedures or operations that will result in empirical observations representing those concepts in the real world (i.e., turning an abstract concept into a measurable variable).


3
New cards
  • Measurement:


  • Careful, deliberate observation of the real world for the purpose of describing objects and events in terms of the attributes composing a variable.


4
New cards
  • Mutually exclusive:


  • A quality of variable attributes where every observation can be classified into only one category (categories do not overlap).


5
New cards
  • Exhaustive:



  • A quality of variable attributes where every observation must fit into at least one category (there is a place for every possible case).


6
New cards
  • Levels of measurement:


  • The four hierarchical ways variables can be categorized based on their mathematical properties: nominal, ordinal, interval, and ratio.


7
New cards
  • Nominal:


  • Variables whose attributes have only the characteristics of exhaustiveness and mutual exclusiveness; categories have no rank or order (e.g., gender, race, political party).


8
New cards
  • Ordinal:


  • Variables whose attributes can be logically rank-ordered from more to less, though the distance between ranks is unknown or unequal (e.g., socioeconomic status: low, medium, high).


9
New cards
  • Interval:


  • Variables whose attributes are rank-ordered and separated by equal, standardized distances, without a true, meaningful zero point (e.g., IQ scores, Fahrenheit temperature).


10
New cards
  • Ratio:


  • Variables that have all the qualities of interval variables plus a true, absolute zero point representing the complete absence of the variable (e.g., age, income, number of prior arrests).


11
New cards
  • Dispersion:


  • The spread or variability of scores in a distribution around the central tendency (e.g., range, variance, standard deviation).


12
New cards
  • Reliability:


  • Consistency or stability of a measurement; whether a particular technique, applied repeatedly to the same object, yields the same result each time.


13
New cards
  • Test-retest reliability:


  • Measuring reliability by administering the exact same test or measurement to the same group of people at two different points in time and comparing the scores.


14
New cards
  • Inter-rater reliability:


  • The degree of agreement or consistency among two or more independent observers/raters coding or scoring the same behavior or phenomenon.


15
New cards
  • Split-half method:


  • Assessing internal consistency by randomly dividing a set of items measuring the same concept into two halves and checking whether both halves produce similar scores.


16
New cards
  • Validity:


  • Accuracy of a measurement; the extent to which an empirical measure adequately reflects the real meaning of the concept under consideration.


17
New cards
  • Face validity:


  • The quality of an indicator that makes it seem a reasonable measure of some variable "on the face of it" (common-sense plausibility).


18
New cards
  • Criterion-related validity (a.k.a. Convergent/Predictive validity):


  • The degree to which a measure relates to or predicts an external criterion (e.g., LSAT scores predicting law school grades, or a new depression scale correlating strongly with an established clinical diagnosis).


19
New cards
  • Construct validity:


  • The degree to which a measure relates to other variables as expected within a system of theoretical relationships.


20
New cards
  • Content validity:


  • The degree to which a measure covers the full range of meanings or dimensions included within a concept.


21
New cards
  • Sample size:


  • The total number of units (e.g., individuals, cases) included in a sample; larger samples reduce sampling error and increase statistical power.


22
New cards
  • Replication:


  • Repeating an experiment or study (often with different subjects or settings) to see if the original findings hold up and are reliable.


23
New cards
  • No harm to participants:


  • The fundamental ethical rule that social research should never injure the people being studied, regardless of whether they volunteer.


24
New cards
  • Physical harm:


  • Bodily injury, pain, or health risks resulting from participation in a study.


25
New cards
  • Psychological harm:


  • Emotional distress, anxiety, trauma, loss of self-esteem, or embarrassment caused by research procedures.


26
New cards
  • Withholding desirable treatments:


  • An ethical dilemma in experimental research where a control group is denied a beneficial intervention or medical treatment.


27
New cards
  • Tuskegee Syphilis Study:


  • An infamous 40-year U.S. Public Health Service study where researchers deceived Black men with syphilis and intentionally withheld penicillin (even after it became the standard cure) to observe the untreated progression of the disease.


28
New cards
  • Milgram Experiment:


  • A famous obedience study in which participants were led to believe they were administering painful, potentially lethal electric shocks to a confederate, causing severe acute psychological distress.


29
New cards
  • Stanford Prison Experiment:


  • Philip Zimbardo’s 1971 simulation assigning college students to be "guards" or "prisoners," which had to be halted early due to rapid psychological abuse and emotional trauma.


30
New cards
  • Tearoom Trade Study:


  • Laud Humphreys’ covert sociological study of anonymous male homosexual encounters in public restrooms, notorious for deception, invasion of privacy, and tracking participants via license plates without consent.


31
New cards
  • Deception:


  • Misleading participants about the true purpose, procedures, or identity of the researcher in a study; requires strict justification and thorough debriefing.


32
New cards
  • Informed consent:


  • A norm in which subjects base their voluntary participation in research projects on a full understanding of the possible risks and benefits involved.


33
New cards
  • Elements of voluntary participation:


  • Participation must be completely free from force, fraud, deceit, duress, or coercion, and subjects must know they can withdraw at any time without penalty.


34
New cards
  • Special populations:


  • Vulnerable groups requiring extra ethical protections because of diminished autonomy or heightened risk of coercion (e.g., prisoners, children/minors, pregnant women, cognitively impaired individuals).


35
New cards
  • Confidentiality:


  • When the researcher can identify a given person’s responses, but essentially promises not to do so publicly.


36
New cards
  • Anonymity:


  • When neither the researchers nor the readers of the findings can identify a given response with a given respondent (no identifying link exists).


37
New cards
  • Deductive disclosure:


  • When an individual participant’s identity can be deduced or figured out by combining indirect demographic or contextual details in the published data, even if their name was removed.


38
New cards
  • Mandatory reporting:


  • Legal requirements compelling researchers (and certain professionals) to breach confidentiality and report specific disclosures, such as ongoing child abuse, elder abuse, or imminent harm to self or others.


39
New cards
  • Compensation vs. bribery/coercion:


  • Compensation fairly reimburses participants for their time and inconvenience, whereas bribery/coercion offers an excessive reward (especially to low-income or vulnerable people) that impairs free, rational judgment about risks.


40
New cards
  • Belmont Report:


  • The foundational 1979 ethical framework for human subjects research built on three core principles:


41
New cards
  • Respect for persons:


  • Treating individuals as autonomous agents (via informed consent) and protecting those with diminished autonomy.


42
New cards
  • Beneficence:


  • Maximizing possible benefits while minimizing possible harms ("do no harm").


43
New cards
  • Justice:


  • Ensuring fairness in who bears the burdens of research and who receives its benefits.


44
New cards
  • IRB (Institutional Review Board):


  • A committee at an institution (like a university) charged with reviewing research proposals involving human subjects to ensure ethical standards and participant protections are met.


45
New cards
  • Exempt review:


  • Minimal-risk research falling into federally defined low-risk categories (e.g., anonymous educational surveys or analysis of existing public data).


46
New cards
  • Expedited review: Minimal-risk research that does not qualify as exempt and is reviewed by the IRB chair or one/more experienced reviewers rather than the full board.


  • Minimal-risk research that does not qualify as exempt and is reviewed by the IRB chair or one/more experienced reviewers rather than the full board.


47
New cards
  • Full review:


  • Required for research involving more than minimal risk or vulnerable populations (like prisoners), reviewed and voted on by the entire convened IRB committee.


48
New cards
  • Ethical considerations for repeated studies:


  • Ensuring longitudinal or follow-up studies maintain ongoing informed consent, protect against cumulative psychological fatigue/harm, and safeguard longitudinal tracking data against deductive disclosure.


49
New cards
  • Experiments:


  • Research designs in which the researcher actively manipulates an independent variable, controls extraneous variables, and observes the effect on a dependent variable to establish causality.


50
New cards
  • Experiment vs. quasi-experiment:


  • A true experiment uses random assignment to place subjects into experimental and control groups, whereas a quasi-experiment compares non-equivalent groups without random assignment.


51
New cards
  • Elements of a true experiment:


  • (1) Manipulation of an independent variable, (2) presence of a control/comparison group, and (3) random assignment of subjects to groups.


52
New cards
  • (Random) assignment vs. (random) selection:


  • Random selection draws a sample from a population (for external validity/generalizability); random assignment places sample participants into experimental or control groups by chance (for internal validity/group equivalence).


53
New cards
  • Classical experiment:


  • The standard experimental design featuring random assignment to an experimental group and a control group, with both groups receiving a pre-test and a post-test, and only the experimental group receiving the stimulus.


54
New cards
  • Dichotomous variable:


  • A variable with only two possible attributes or categories (e.g., yes/no, experimental group/control group).


55
New cards
  • Independent variable (IV):


  • The presumed cause or treatment manipulated by the researcher.


56
New cards
  • Dependent variable (DV):


  • The presumed effect or outcome measured by the researcher.


57
New cards
  • Treatment/stimulus:


  • The specific intervention, program, or condition introduced to the experimental group.


58
New cards
  • Experimental group:


  • The group of subjects in an experiment to whom an experimental stimulus is administered.


59
New cards
  • Control group:


  • The group of subjects in an experiment to whom no experimental stimulus is administered (or who receive standard care/placebo), serving as a baseline for comparison.


60
New cards
  • Pre-test/post-test:


  • Measuring the dependent variable before the stimulus is introduced (pre-test) and again afterward (post-test) to measure change.


61
New cards
  • Placebo:


  • An inert or fake treatment given to the control group so they believe they are receiving the active intervention, isolating psychological expectation effects.


62
New cards
  • Hawthorne effect:


  • The phenomenon where research subjects alter their behavior simply because they know they are being observed or studied.


63
New cards
  • Double-blind experiment:


  • An experimental design in which neither the subjects nor the researchers/administrators know who is receiving the real treatment and who is receiving the placebo.


64
New cards
  • Internal threats to validity in experiment:


  • Factors other than the independent variable that might explain changes in the dependent variable:


65
New cards
  • Maturation:


  • Natural biological or psychological changes occurring in participants over time (e.g., growing older, tired, or wiser) independent of the treatment.


66
New cards
  • Selection bias:


  • Pre-existing differences between the experimental and control groups when random assignment fails or is absent.


67
New cards
  • Experimental mortality (attrition):


  • Differential dropout of participants from one group compared to another during the course of the experiment.


68
New cards
  • Testing:


  • The effect that taking a pre-test has on participants' scores on a subsequent post-test (e.g., learning from the first test).


69
New cards
  • Compensatory rivalry:


  • When control group members realize they are being compared to the experimental group and work extra hard to outperform them ("John Henry effect").


70
New cards
  • Demoralization:


  • When control group members feel resentful or discouraged about being left out of a desirable treatment and give up or perform worse.


71
New cards
  • Statistical conclusion validity threats in experiment:


  • Errors in drawing conclusions about whether variables are statistically related (e.g., low statistical power due to small sample size, violating statistical test assumptions, or unreliability of measures).


72
New cards
  • Construct validity threats in experiment:


  • Misidentifying or poorly operationalizing the cause or effect in an experiment (e.g., participants guessing the hypothesis, experimenter expectancy effects, or confounding treatment components).


73
New cards
  • External validity threats in experiment:


  • Factors that limit the ability to generalize experimental results beyond the specific study sample, setting, or time period (e.g., unrepresentative college student samples or artificial lab conditions).


74
New cards
  • What to include in an annotated bibliography:


  • A formal citation (e.g., APA) followed by a concise summary covering the study's overview/purpose, data/sample, methodology, key results, and major limitations.


75
New cards
  • What to look for in an academic article:


  • Peer-reviewed status, clear research questions/hypotheses, transparent sample and methods, empirical results, theoretical grounding, and acknowledged limitations.


76
New cards
  • Why emphasize results?:


  • In empirical research, the results section provides the actual evidence showing whether hypotheses were supported, allowing readers to evaluate the real-world magnitude and statistical significance of the findings rather than just relying on the authors' interpretation.


77
New cards
  • Meta-analysis:


  • A quantitative statistical technique that combines and analyzes data across multiple independent studies on the same topic to determine an overall effect size.


78
New cards
  • Census vs. sample:


  • A census collects data from every single member of a target population, whereas a sample collects data from a smaller subset selected to represent that population.


79
New cards
  • Why sample?:


  • Sampling saves time, money, and resources, and is often more accurate and feasible than attempting to reach an entire population.


80
New cards
  • Population:


  • The entire theoretically specified aggregation of study elements (the whole group you want to draw conclusions about).


81
New cards
  • Sample:


  • The subset of elements actually selected from a population to be observed in a study.


82
New cards
  • Representativeness:


  • The quality of a sample having the same aggregate distribution of characteristics as the population from which it was selected.


83
New cards
  • Sampling frame:


  • The actual list or quasi-list of elements from which a probability sample is selected (e.g., a university student directory or list of registered voters).


84
New cards
  • Sampling distribution:


  • The theoretical probability distribution of a statistic (like a sample mean) obtained from a large number of independent samples drawn from the same population.


85
New cards
  • Sampling bias (and why it exists):


  • A systematic error where some members of the population are less likely to be included than others, resulting in an unrepresentative sample; it exists due to flawed sampling frames, nonresponse, or nonprobability selection methods.


86
New cards
  • Sampling error (and the type of sampling required to calculate standard error):


  • The natural degree of error expected when estimating a population parameter from a sample rather than a census; probability sampling is required to calculate standard error and confidence intervals.


87
New cards
  • Probability sampling:


  • Any sampling technique in which elements are selected using random mechanisms so that every member of the population has a known, non-zero probability of selection.


88
New cards
  • Simple random sampling (SRS):


  • A basic probability sampling method in which every unit in the sampling frame is assigned a number and selected completely at random (like drawing names from a hat).


89
New cards
  • Equal probability of selection method (EPSM):


  • A sample design in which every member of a population has the exact same chance of being selected into the sample.


90
New cards
  • Systematic sampling:


  • A probability sampling method in which every element in the total list is chosen (after a random start) for inclusion in the sample.


91
New cards
  • Periodicity:


  • A cyclical pattern or hidden order in a sampling frame list that can coincide with the sampling interval in systematic sampling and create a biased sample.


92
New cards
  • Stratified sampling:


  • Grouping the population into homogeneous subsets (strata) based on key characteristics (e.g., age, race, gender) before sampling from each group to ensure proper representation.


93
New cards
  • Strata:


  • The distinct, homogeneous subgroups into which a population is divided prior to stratified sampling.


94
New cards
  • Disproportionate stratified sampling:


  • Sampling different strata at different rates (rather than in exact proportion to their size in the population) to ensure enough cases exist in smaller subgroups for reliable statistical analysis.


95
New cards
  • Oversampling:


  • Deliberately sampling a higher proportion of a smaller or underrepresented subgroup so that subgroup-specific analyses have sufficient statistical power.


96
New cards
  • Multistage cluster sampling (& NCVS method):


  • A probability sampling method involving repeated sampling of natural groups (clusters, such as census tracts or blocks) followed by sampling individuals within those selected clusters; used by the National Crime Victimization Survey (NCVS) to sample U.S. households nationwide without needing a single master list of every citizen.


97
New cards
  • Nonprobability sampling:


  • Any technique in which samples are selected in some way not suggested by probability theory (selection probabilities are unknown, so results cannot be statistically generalized to the whole population).


98
New cards
  • Purposive sampling:


  • A nonprobability method in which the researcher selects units based on their own judgment about which ones will be most useful or representative for a specific research purpose (e.g., interviewing experienced homicide detectives).


99
New cards
  • Quota sampling:


  • A nonprobability method that begins with a matrix describing target characteristics of the population and selects available participants until each demographic quota is filled.


100
New cards
  • Reliance on available subjects (vs. convenience sampling):


  • Selecting whoever happens to be easily accessible (e.g., stopping people on a street corner or surveying an intro criminology class); "reliance on available subjects" is the textbook term for what is commonly called "convenience sampling," highlighting its major risk of selection bias.