CADV 380
interrupted time series
a design in which treatment in an independent event, such as a historical event. -between subjects design
frequecy distribution
a graph of a distribution showing the frequency of each response in the distribution
standard deviation
a measure representing the average difference between scores and the mean of a distribution
Pre test-Post test
a measurement is taken before and after an event or treatment -within subjects design(same group of people).
distribution
a set of scores, likely to be a range between low and high values of the measurement
inferential statistics
a set of statistical procedures used by researchers to test hypotheses about the population
experimental designs
a type of research design that involves manipulation of an independent variable, and a measurement of a dependent variable, allowing control of extraneous variables that could affect results
median
middle score in a distribution such that half of the scores are above and half are below
data
numbers associated with the measurements from each individual in the study
informed consent
obtaining consent from participants for participation in research after they have been informed about the purpose, procedure, and risks
order effects
occur when the order in which participants experience conditions in an experiments affect the results of a study.
testing effects
occurs when participants are tested more than once in a study with early testing affecting later testing
central tendency
one way to summarize a data set; representation of a typical score in a distribution (mean, median, mode)
freedom of coercion
participants able to choose to participate; free to stop participating at any time with no consequences
random assignment
participants are randomly assigned to levels of the independent variable in an experiment to control for individual differences
subject mortality
people opting out of study
p-value
probability value associated with an inferential test that indicated the likelihood of obtaining the data in a study due to chance (the null hypothesis is true)
ethics
rules of conduct recognized in respect to a particular class of human actions or a particular group, culture, etc.
longitudinal design
same children tracked over time. -within subjects -developmental design considerations: subject mortality, history & testing effects
stratisfied sampling
sample chosen form the population such that proportion of individuals with a particular characteristic is equivalent in the population in the sample
cluster sampling
sample chosen randomly from clusters identified in a population
simple random sampling
samples chosen randomly from the population such that each individual has an equal chance of being selected
nuremberg code
set of guidelines developed for research with human subjects based on info gained during the nuremberg trials after WWII
counterbalancing
a control used within subjects experiment where equal number of participants are randomly assigned to different orders of conditions
Quasi-Experimental Designs
a type of research design where a comparison is made as in an experiment, but no random assignment occurs types: pretest posttest, interuppted time series, longitudinal and cross sectional
independent variables
a variable that is manipulated by the researcher such that the levels of a variable change across or within subjects
dependent variable
a variable that is measured for each level of the independent variable (expecting changes in values from one level of manipulation to another)
main effect
an effect in the independent variable on the dependent variable regardless of levels of other independent variables
interaction
an effect of one independent variable on the dependent variable which changes from one level of the independent variable to the other level
factorial design
an experiment that includes more than one independent variable
confounding variable
an extraneous variable present in a study that may affect results
extraneous variable
anything in a study not part of the manipulation or measurement (time of day, gender etc)
cross sectional
different children compared at different ages -between subjects considerations: cohort effects
history effects
events occur during the course of a study to all or individual participants that can result in bias
cohort effects
group effects
within subjects
independent variable where each participant experiences every level of the variable
between subjects
independent variable where each participant experiences only one level of the variable
benefit risk factor
information from study must outweigh the risks of harm that the participant incur as part of the study.
mean
is the calculated average of the scores in a distribution
Qualitative
levels of independent variable are different categories/ classes
quantitative
levels of independent variable are different values of measurement
analyses/statistics
mathematical methods for summarizing or interpreting data
marginal mean
means of independent variable one collapsed across levels of independent variable two
descriptive statistics
measures that help summarize the data set; describes the sample
range
the difference between the lowest and highest scores of a distribution
sampling error
the difference between the observations in a population and in the sample that represents that population in a study
internal validity
the extent to which changes in your dependent variable result from changes in levels of your independent variable (you can make causal conclusions)
mode
the most common score of the distribution
alpha level
the probability level used by researchers to indicate the cut off level (highest level) of error that will allow them to reject the null. (usually .05 or .01)
variability
the spread of scores of a distribution
variance
the standard deviation of a distribution squared
regression toward the mean
when participants score higher or lower than their average, they are likely to score near their average the next time they are tested i.e. wheaties effects
alternative hypothesis
your treatment has an effect on the dependent variable
null hypothesis
your treatment has no effect on the dependent variable