Research methods Flashcards
Variable
Any phenomenon that can take on more than one value.
Continuous variable
Has a continuum of possible values.
Categorical variable
Can only take on fixed values in groupings or categories.
Extraneous variable
An external variable not being investigated that may affect IV or DV and cause inaccurate conclusions.
Confounding variable
Produces effects that might be confused with the effects of the independent variable.
Independent variable
The variable manipulated by the experimenter.
Dependent variable
The response measured by the experimenter.
Experimental research
Researcher manipulates aspects of a situation and examines the response to assess cause and effect. May have external validity issues but provides strong evidence to establish causation.
Generalisability
If research results from the sample can be applied to the entire population of interest. findings must be valid.
Measure
Way of assessing a variable, must be reliable and valid.
Reliability
Measure’s ability to produce consistent results.
Validity
Measure’s ability to assess the variable of interest or assess what it is intended to measure.
The scientific approach
Uses empirical methodologies such as observation and experimentation to gain knowledge. Three main goals are description, prediction and understanding.
Quantitative research
Experiments or surveys that provide quantified data.
Qualitative research
Interviews, observations and case studies to understand phenomena. Has holistic view, inductive approach. Has three key perspectives: positivism (objective research that assumes a universal truth), interpretivism (subjective research in natural setting) and critical theory (taking a moral-political approach to examine how power is expressed in society).
Theory
Systematic way of organising and explaining observations.
Hypothesis
Prediction of relationship between two or more variables.
Random sampling
Every member of the population has equal probability of being selected.
Stratified random sampling
Sample selected that proportionately represents all subpopulations. Selection is only random within groups.
Correlation coefficient
measures/ quantifies the association between two variables and ranges from -1.0 to +1.0. A correlation of 0 means two variables are unrelated. High correlation positive or negative means scores on one variable is a good predictor of the other variable. Measured with Pearson’s r = co-efficiency.
Positive correlation
The higher the score is on one variable, the higher the other variable will score.
Negative correlation
The lower the score is on one variable, the higher the other variable will score.
Informed consent
Participants must be informed of the purpose of the study and the nature of the treatments before they agree or refuse to participate.
Deception
Some experiments need deception but participants must be debriefed, can withdraw at any time, and the research is important and cannot be conducted without deception.
Operationalising
Turn abstract concept into a variable that can be measured.
Control group
Not exposed to treatment or 0 level of IV.
Experimental group
Receives treatment or an active level of IV.
Blind studies and double-blind
Participants are unaware of aspects of the research. Researchers are also unaware of aspects in double-blind study.
Quasi-experiment
Experiments that have variables that are impractical or unethical to manipulate.
Test-retest reliability
Test gives similar results if the participant takes it two or more times.
Internal consistency
Different ways to measure the same variable should produce similar answers.
Inter-rater reliability
Two testers who rate the same person on the same variable should give similar ratings.
Internal validity
The extent to which a study is methodologically adequate.
External validity
The extent to which the findings can be generalised outside the laboratory.
Sampling bias
When a sample does not represent the population as a whole.
Evaluating empirical psychological study
Does the theory make sense, do the hypotheses flow from it?
Is the sample adequate and appropriate?
Are the measures and procedures valid and reliable?
Is the data conclusive?
Are the broader conclusions warranted?
Does the study say anything meaningful?
Is the study ethical?
Common fallacies in arguments
Strawman, appeals to popularity, appeals to authority, and arguments directed to the person.
Crisis of replicability
An experiment or study must produce the same results when repeated.
Benefits and limitations of psychology research through the internet
Assess, automate and process data quickly and easily. However, can have sampling bias, uncontrolled data collection procedures, issues protecting the welfare of participants, and the right to confidentiality.
Critical thinking principles
Scepticism, objectivity, open-mindedness
Descriptive research
Cannot establish causation. Describes phenomena as they exist without manipulating variables.
Case studies
In-depth observation of one person or a small group. Useful for generating hypotheses and exploring complex phenomena.
Naturalistic observation
In-depth observation of a phenomenon in its natural setting. Useful for observing complex phenomena outside of the lab.
Survey research
Asking a large sample questions about their attributes or behaviours.
Correlational research
Assesses the degree to which two variables are related, to see if knowing the value of one can predict the value of the other. Correlation does not demonstrate causation.
Epistemology
Examines the nature of knowledge itself using three approaches: Objectivism (phenomena exists independently of consciousness, one universal/ objective meaning), Subjectivism (phenomena is subjective and meaning is individual, no universal truth), and Constructionism (not one objective or universal meaning but the result of social and intellectual constructions).
