4: Sampling, Measurement and Hypothesis Testing Flashcards
Random sampling
each member of the population has an equal chance of being selected to be a member of the sample
stratified sampling
Proportions of important subgroups in the population are represented precisely
Probability sampling is and includes
Each member of the population has a definable probability of being selected for the sample
Random sampling
stratified sampling
cluster sampling
Non probability sampling
selects samples based on the subjective judgment of the researcher rather than random selection
convenience sampling
purposive sampling
quota sampling
snowball sampling
Cluster sampling
Researcher randomly selects a cluster of people all having the same feature in common
Helps for big populations
Purposive sampling
A specific type of person is recruited for the sample
Convenience sampling
A group of individuals who meet the general requirements for the study and are recruited in a variety of non-random ways
§ From the subject pool
Quota sampling
The researcher attempts to accomplish the same goal as stratified sampling but does so in a non-random fashion
Snowball sampling
Once a member of a particular group has been surveyed, the researcher asks that person to help recruit additional subjects through a network of friends
Developing measures from constructs
Researchers define the constructs as precisely as possible - operational definitions
how do we evaluate measures
with reliability and validity
Content validity
Is the test fully representative of what it aims to measure
Criterion validity
predictive validity: refers to whether a test can successfully predict some future behaviour.
Concurrent validity: meaningfully relates to some other measure of behaviour
Interval Scale
Each unit increase in the scale is assumed to reflect the same change in the underlying measure.
Construct validity
Accurately measures some construct - the operational definition
Convergent validity - yes to other scores related to the construct
Discriminant validity - not to scores unrelated to the construct
Ordinal scale
Measurement scale in which the ordering of numbers is meaningful, but the metric (amount) is not.
rankings showing the relative standing of objects or individuals
Ratio scales
The concepts of order and equal interval are carried over from ordinal and interval scales, but in addition the ratio scale has a zero point
Descriptive statistics
summarize the data collected from the sample
mean, median (N+1)/2, and mode
variance: range, IQR (Q3-Q1)
standard deviation
better to use median than mean when there are
outliers
Variation is reported when the data represents ______ the standard deviation is reported when the data represents ______
the entire population of scores; a sample of scores from the population
Type I Error
Rejecting the null hypothesis when it is true
chance of this happening are equal to alpha
Type II Error
You fail to reject H0 but are wrong (there is a statistically significant difference)
Can occur when the measurements are not reliable or aren’t sensitive enough to detect true differences between groups, or you have a small sample size
Alpha
want to be at least 95% confident that your results are NOT due to chance
Effect size
reports the size of the differences between groups
Power
One hopes to be able to reject H0
The chance of this happening is referred to as the power of the statistical test
Inverse relationship with Type II error
