Chapter 1 Flashcards
random sample
ensures that each person in population has an equal chance of being selected
random assignment
assign subjects to treatment group with no prejudice, important for internal validity
population
the entire collection of events in which a researcher is interested
sample
a smaller grouping representative of the whole
external validity
the question of whether the sample reflects the population
internal validity
the results obtained because of differences in the way groups are treated and not because of who was placed in the groups
variable
property of an object or event that can take on different values
independent variable
controlled variable/s, either quantitative or qualitative and discrete or continuous
dependent variable
data obtained when an experiment happens, usually quantitative and continuous
discrete variables
take on a limited number of values
continuous variables
can assume, at least in theory, any value between the lowest and highest points on a scale
quantitative data
measurement data, results of measurement using an instrument, tells how much
categorical data
frequency data, qualitative data, data placed in categories with values for each category
raw data
collection of scores before being interpreted
descriptive statistics
when the purpose is to simply describe a set of data, by graphing, calculating means, looking for extreme scores or oddly shaped distributions
exploratory data analysis
EDA, John Turkey, necessity of paying close attention to data & analyzing them before invoking more technically involved procedures
inferential statistics
questions asked that the collected data can answer
parameter
a measure that refers to an entire population
statistic
a parameter, calculated from a collected data sample, that is a guess/inference at reality
S. S. Stevens
foremost leader of those who see measurement scales as crucial to the choice of statistical procedures, psychophysics as an attempt to turn psychology from “soft science” to “hard science”
nominal scales
label items, such as “gender” and “political party affiliation”, categorical data usually measured on nominal scale
ordinal scale
simplest true scale, orders people, objects, or events along a continuum
interval scale
measurement scale which legitimately speaks of differences between scale points b/c each interval has the same value
ratio scale
scale with a true zero point, pointing to the absence of a thing being measured (so that 10 seconds is twice as long as 5 seconds for example)