Data Managment Unit 5 Flashcards
Numerical (Quantitative) Data
data that involves numbers
Continuous Data (Numerical)
Measurements of any data that can be any number in a range
Discrete Data (Numerical)
Can only have certain values
Categorical (Qualitative) Data
Information about something that sorted into groups
Ordinal Data (Categorical)
Numerical data which can be ranked
Nominal Data (Catergorical)
Data which cannot be ranked
Population
All the individuals in a group being studied
Sample
A portion of the population used to represent
Variability (in samples)
- how samples are different from each other
- The more similar the samples are to each other, the lower the variability
Simple Random Sample
Individuals are chosen at random
- Easy
- Might not be representative if the sample is too small
- Phone survey where #’s are randomly chosen
Systematic Random Sample
A mathematical rule used to generate a sample
- The rule ensures that people are chosen from the whole list
- the list must be complete
- Ex. every 5th person in line
Stratified Random Sample
A random sample is taken from groups that have been seperated
- If the stratification is representative then the sample can be good.
- If the groups are not representative then the results can be biased
- Choose 20 people per grade. Choose a representative sample of each grade based on the relative population
Cluster
Divide the population into groups, randomly choose a number of the groups, and sample each member of the chosen groups
- Good data if enough samples are taken
- Can exclude parts of a population grouped together
- Survey classes within a school board
Multistage Random Sample
1st divide the population evenly. 2nd randomly sample each group
- can be representative
- can amplify
- Divide the alphabet equally and choose a letter rom each group
Convenience
Sample those individuals easily accessible
- easy
- easy to have a non-representative sample
- ask people in line at a store
Voluntary
send a survey for response
- easy and cheap
- generally biased by responses of only people who care deeply
- send a survey to every house
Experimental study
a study conducted where an independent variable is changed and the dependent variable is measured
Observational study
observing the relationship between z variables. “examaning 2 sets of data”
Primary Data
Data which is collected to answer a specific question
secondary data
data used that was originally collected for another purpose
bias
the data representative of the population as a whole
primary data source
data generated based on a testable question
secondary data source
data used from a source which generated it for another purpose
microdata
statistics which are separated by individual or group
aggregate data
data which has been pooled so that individuals are not distinguishable
price index
measurement of the change in cost over time of an item
response bias
when respondents change their answers to influence the results, to avoid embarrassment, or to give answer they think the questioner wants
sampling bias
when the sample does not closely represent the population
measurment bias
when the collection method is such that the characteristics are consistently over or under represented
non response bias
when the opinions of respondents differ in meaningful ways from those of non-respondents