Research Methods Exam 1

5 Ways of Knowing

Tenacity, intuition, authority, rationalism, empiricism

Tenacity

Knowing something is true because we have always known it to be true; accepted facts/superstitions; focus on confirming evidence, not correcting

Intuition

Information 'feels' right, not based on knowing/reason/logic; the way the brain processes information; ex. "gut reaction," "I know it in my bones"

Authority

Information is accepted from trusted sources (expert witnesses) due to status or expertise; subset: faith; ex. authority of scripture, expert in a field, textbooks

Rationalism

Following a logical process to test/explore claims; assumptions: facts accepted as a starting point; argument: set of assumptions linked through logic leading to a conclusion

Empiricism

Observation or direct sensory experience to obtain knowledge; assumes all things can be tested; assumes that the testing processes yield reliable results; assumes we can trust our senses (illusions); requires two witnesses of the same event

Characteristics of a good hypothesis

Logical, testable, refutable, positive (asserts a relationship/difference for a statistical analysis)

Elements of standard social science research articles

Introduction, methods, results, discussion

Introduction section of a standard social science research article

Consists of the research question, literature review, and hypothesis

Methods section of a standard social science research article

Describes participants and how they were recruited, discusses the step-by-step process of conducting the study

Results section of a standard social science research article

Consists of the statistical process (how the tests were analyzed), statistics, and any tables/charts

Discussion section of a standard social science research article

Evaluates whether the results support the hypothesis, describes the conclusions, applications, and limits of the study

Quantitative research

Research that provides data that can be expressed with numbers, such as ranks or scales.

Qualitative research

Research that relies on what is seen in field or naturalistic settings more than on statistical data

Steps of the scientific method

Observation, question, research, hypothesis, experiment, analysis, conclusion

Independent variable

Presumed to cause changes in another variable; manipulated by researcher

Dependent variable

The measurable effect, outcome, or response in which the research is interested; influenced by the IV

Extraneous (confounding) variable

Something unwanted or unexpected that might affect the dependent variable

Categorical variable

Varies by type or kind

Quantitative variable

Varies by degree or amount

Construct

A theoretical/conceptual idea/concept that cannot be directly measured; hypothetical attributes or mechanisms that help explain and predict behavior in a theory; ex. self-esteem, anxiety, shame, motivation

Operationalize

Indirectly measuring and defining a variable that cannot be directly measured (studying intelligence with intelligence tests)

Reliability

Measure of the consistency of results; affected by observer errors, environmental change, and participant changes; results are hardly ever on the "true score"

Ways to evaluate reliability

Successive measurement, simultaneous measurement, internal consistency

Successive measurement

A way of evaluating reliability that uses testing and retesting

Simultaneous measurement

A method that evaluates inter-rater reliability from multiple observers

Internal consistency

A way of evaluating reliability that compares the first half of the test to the second half (split-half)

Validity

The ability of a test to measure what it is intended to measure; it focuses on specific definitions of key terms

Face validity

On the surface, how a test appears to be measuring what it claims to measure

Concurrent validity

The degree to which the measures gathered from one tool agree with the measures gathered from other assessment techniques

Predictive validity

The degree to which the outcomes of the assessment correctly predict what it is supposed to predict

Construct validity

The extent to which variables measure what they are supposed to measure; how well the operational definition matches the theory

Convergent validity

When there is a positive correlation between two variables, as expected

Divergent validity

When there is either a negative correlation between two variables, as expected, or a weak correlation (not measuring the same thing)

Four types of measurement

Nominal, ordinal, interval, ratio

Nominal measurement

Has no direction and no magnitude; differences between variables are important but can't be measured; categories have no particular order; allows us to see if/how individuals are similar or different; can't see the direction of difference (higher/lower); can't see magnitude (size comparison)

Ordinal measurement

Has direction but no magnitude; the order matters, but the differences do not; categories form an ordered sequence; shows the direction of differences; (ex. finishers in a race: first, second, third); (ex. size of popcorn: medium, large, XL, family size)

Interval measurement

Has direction and magnitude; numeric values; shows both the order and the exact differences between the values; series of equal intervals; allows for measurement of central tendency (mean, median, standard deviation); doesn't have a 'true zero'

Ratio measurement

Has direction, magnitude, and true zero

Sensitivity/range

Evaluates if the instrument/assessment is sensitive enough to detect differences

Ceiling/floor effect

Statistics can't go any higher/lower for a particular group, so change isn't visible

Experimenter bias

Researchers influencing statistics to support a particular view (ex. altering the design of the study, affecting the behavior of participants)

Participant reactivity

Participants behaving in a certain way to influence the results of the study

Single-blind study

Participants don't know which experimental group they are in

Double-blind study

Neither the participants nor the experimenters know who is in each group

3 Ethical principles of the Belmont Report (1979)

Autonomy (informed, voluntary consent), beneficence (do good, minimize risk of harm), justice (balance who receives risks and benefits)

Highest ethical priority

The welfare and dignity of the participants

Informed consent

Complete information about the study prior to agreeing to participate, including procedures, risks, benefits, and confidentiality; individuals must be competent to make decisions regarding their well-being (free from undue influence, free to decline, free to stop) and must understand the conditions of the experiment; expressing written consent

Confidentiality

Information will be kept secret and private; those who have access to the data are specifically identified (usually only researchers); important because researchers are collecting potentially vulnerable/personal/private information

Anonymity

The participants' identity is not connected with the data

The use of deception in a study

Used to disguise the true purpose of the study to prevent participant reactivity

Passive deception

Omission; not telling the participants something

Active deception

Commission- intentionally misleading or providing misinformation

Confederates

People who pretend to be participants, but are really part of the study

Placebo

An inactive substitute for a treatment in an experiment

Requirements for deception in a study

Must be justified, must show that other options are not appropriate; cannot conceal risks of pain, harm, or emotional distress; must debrief, providing a complete explanation and necessary support/remediation

Institutional Review Board (IRB)

A committee of scientists who are responsible for examining/approving all studies involving animals and humans, including risks, equitable selection (justice), informed consent, data monitoring, privacy, and confidentiality