1/79
Looks like no tags are added yet.
Why Numbers?
they describe and predict, there’s accurate discrimination, generalization, and the ease of collection
Numbers
assign value and relativity
Numerals
labels
concept
thing under study; abstract thinking to distinguish a phenomenon from other elements
construct
theoretical definition of a concept; must be observable or measurable; linked to other concepts
Variable
element that is identified in research and hypotheses
operationalization
specifically how the variable is observed or measured
independent variable
changing this variable causes change in other variables
dependent variable
the primary interest of a study
extraneous variable: confounding
hidden cause
extraneous variable: mediating
the “how” or “why” in the middle; explains how the independent variable leads to the dependent variable
extraneous variable: moderating
impacts the strength of relationship (magnifies or lessons)
Nominal
data is categorized with no inherent order or ranking, simply labeled for distinct categories
Ordinal
data can be ranked or ordered, but the difference between categories isn’t necessarily equal
Ratio
data has equal intervals and a true zero point, allowing for meaningful ratios between values
Interval
data has equal intervals between categories, but there’s no true equal point
discrete variables
the presence or absence of some characteristic, counted, not measured, and no decimals
continuous variables
reveals intensity or magnitude, values that differ in a degree or frequency can be ordered on a continuum, measured and decimals are okay
hypothesis
tentative, testable explanation for an observed phenomenon or research question
null hypothesis
no relationship between variables
alternate hypothesis
opposite of null, significant relationship exists
population
contains every unit the researcher wants to study
sample
selected segment of the population presumed to represent that population
why sample?
resources (time, money) and workload
probability sampling
method of selecting a sample from a population where every member has an equal chance of being included in the sample
sample frame
the list from which the potential respondent are drawn
N
total population size
n
sample size
sampling unit
unit actually selected for the study
sampling error
the degree to which the sample differs from population characteristics on some measurement; always exists when sampling
simple random sampling
every individual has an equal chance of being selected
advantages of simple random sampling
unbiased, easy to analyze
disadvantages of simple random sampling
requires a complete list of population, can be impractical for larger populations
process of simple random sampling
define the population
determine a sample size
assign number to each individual
use a random number generator to select participants
stratified random sampling
population divided into subgroups based on shared characteristics
process of stratified random sampling
divide a population into strata
take a simple random sample from each stratum
systematic sampling
selecting every nth individual from the population after a random start
advantages of systematic sampling
easy to implement, can be more precise than simple random sampling
disadvantages of of systematic sampling
potential for bias if there’s a hidden pattern in the population
process of of systematic sampling
calculate sampling interval
choose a random starting point
select every nth individual
multistage closer sampling
sampling done in stages, typically moving from larger to smaller units
advantages of multistage cluster sampling
cost effective for geographically dispersed populations
disadvantages of multistage cluster sampling
higher sampling error, more complex analysis
process of multistage cluster sampling
divide population into large clusters
randomly select some clusters
some individuals within chosen clusters
non probability sampling
samples are not randomly selected; grounded in researchers judgement
validity
am i measuring what i intend to measure?
content validity
covers all aspects of what i want to measure
face validity
measure makes sense on the surface
construct validity
measures what it claims to theoretically
reliability
will i get the same results every time i measure?
test-retest reliability
measures the consistency of results when the same test is given to the same sample at different points in time
inter-coder reliability
measures the degree of agreement between different people observing or assessing the same thing
intern-item reliability
assesses the “closeness” between multiple items in a test that are intended to measure the same phenomenon
established measures reliability
takes advantage of the reliability testing conducted on wildly-accepted measures in the field
survey
a system for collecting information that relied on questionnaires; often used to collect comparative data and draw generalizations about a population
fixed design survey
each participant answers the same questions
large magnitude survey
researchers can collect data from a large number of peopler
representative sample survey
a sample for an identified population is used to dram inferences
cross-sectional data
data collected around the same time period (a days or weeks)
internal reliability
are the items measuring the same phenomenon
social desirability bias
respondents answer in a way that makes them look favorable or socially acceptable instead of their own opinion
codebook
reference guide that explains how data is structured coded or classified
composite variable
variable made of two or more survey items the are highly related to each other conceptually
statistics
the collection, analysis, interpretation, and presentation of numerical data
descriptive statistics
summarizes and describes data, used to organize and present data
mean
average, most sensitive to outliers and extreme scores
median
middle of all scores on one variable
mode
score or scores that appear most often
measures of dispersion
describes variability or spread of scores, should be reported with mean
range
highest to lowest score
standard deviation
when sd= 0 all scores are the same, the larger the sd the more the scores differ from the mean
inferential statistics
uses a small sample to make predictions, test hypotheses or draw conclusions about a larger population
correlations
statistical test to measure the strength and direction of the relationship between true variables, ranges from -1 to 1.
experiment
a research method used to test whether one variable causes a change in another variable
control group
group that doesn’t receive the experiment treatment
random assignment
randomly placed in groups to prevent bias
source credibility bias
people are more likely to believe a message when they think the source is trustworthy and knowledgeable
elaboration liklihood method
explains how people are persuaded through two different routes of thinking
central route
focuses on facts, evidence and arguments
peripheral route
influenced by celebrities, attractiveness, popularity or music