Research Methods Flashcards
Operational definitions
describes the actions that will be made to objectively measure or control a value
Paradigm
set of assumptions and ideas about what kind of research questions can be asked and how they can be answers
Parsimony
when there are two otherwise equally good explanations for a certain phenomenon, the simplest explanation is preferred; generally makes fewer assumptions
Natural order
the attribution of the same effects to the same causes
Generalizability
the same causes that produce our effects in the lab also produce those effects in everyday life situations
Conservatism
scientists tend to support the current explanation until new facts accumulate that the current explanation can’t explain
Empiricism
approach that emphasizes that knowledge should be based on actual observation and not reason alone
Inductive reasoning
move from a collection of specific observations (facts) to a theory that allows us to describe how the observations are related
Deductive reasoning
making specific predictions about situations or events that we have not yet observed directly
Process of scientific investigation
- adopt a theory
- generate hypothesis
- choose research method
- collect data
- analyze data
- report findings
- revise existing theories
Theory
general set of ideas on the way that the world works
Hypothesis
set of testable statements; makes a specific prediction about the relationship between variables involved in the theory
Reliability
ability of any test to give the same output when the same input is entered
Validitiy
ability of a test to measure what we intend to measure
Case studies
detailed examination of one particular individual; can provide some initial facts
Correlational studies
looking at existing relationships between pairs of variables
Correlation
measure of the direction and strength of the relationship; can be positive, negative, or zero
Line of best fit
straight line which comes as close as possible to all the points on the graph, and shows any positive or negative trends
Experiment
procedure of choice used to systematically study a problem
Within-subjects design
manipulating the independent variable within each participant to minimize the effect of external variables on the dependent measure
Practice effect
improved performance over the course of an experiment due to becoming more experienced
Binary variables
only two possible values; eg. on/off
Independent variable
variable that the researcher will manipulate
Dependent variable
measure by the researchers to see the effect of the independent variable
Confounding variables
researcher did not manipulate, but still affected the outcome of the experiment
Control group
receives no manipulation of the independent variable
Experimental group
receives a manipulation of the independent variable
Experiment research advantages
allows researchers to develop cause and effect explanations; gives the ability to say why something happened
Experiment research disadvantages
may be little resemblance between the controlled conditions in the laboratory and the real world
Direct observation
if done in natural environment, then there is reduced artificiality; can allow for long periods of data collection; useful when little is known about subject or phenomenon
Interviews
often one-on-one which allows for clarification questions; can gather information on behaviours otherwise difficult to observe
Questionnaire
can gather information on behaviours otherwise difficult to observe, usually relatively simple, allows for collection by someone else
Population
all of the individuals that meet your criteria
Sample
the subset of the population you’re interested in that you examine; must be randomly sampled
Random assignment
randomly deciding which group any particular participant is assigned; allows us to compare between different conditions of the experiment
Descriptive statistics
used to organize and summarize data, based entirely on the available data; uses measures of central tendency
Frequency distribution
type of graph illustrating the distribution of how frequently values appear in the data set
Normal distribution
distribution with a characteristic smooth, symmetrical, bell-shaped curve with one peak
Inferential statistics
assess how likely it is that the sample data are an accurate reflection of the population as a whole, require inferences to be made
Variability
the extent to which the scores in a data set tend to vary from each other and the mean; the lower it is, the more likely the difference is from independent variable manipulation
Standard deviation
measure of the variability of a set of data; the expected difference between any randomly selected datum and the mean of the set
Statistical significance
when the difference between two groups is due to some true difference between the properties of the two groups, and not simply due to random variation
T-test
statistical test that considers each data point from both groups to calculate the probability that two samples were drawn from the same population
P-value
value expressing the probability calculated by the T-test; > 0.05 then it is not significant
Replication
the repetition of a study to see whether the earlier results can be duplicated
Type I error
concluding that independent variable manipulation had an effect, when, in reality, any difference between groups is the result of sampling error
Type II error
concluding that independent variable manipulation had no effect, when, in reality, it did
Placebo effect
when an individual exhibits an effect to a perceived treatment when no treatment is actually given
Social desirability bias
a tendency to give socially approved answers to questions about oneself
Reponse sets
a tendency to respond to questions in a particular way regardless of the content
Blind
subject is unaware of the group condition to which they have been assigned
Double-blind
both the subject and the experimenter are unaware of group assignment