What is a variable?
The thing(s) that are being counted/collected from a population or sample
What is a population?
The entire possible set of individuals from which data can be collected
What is a Sample?
A smaller portion of a population selected to collect data from
What is a population parameter? ***
Characteristic of a population
(EXAMPLE: Whether or not a video on youtube is a cat video)
What is a sample statistic? ***
Characteristic of a sample (usually calculated)
(EXAMPLE: Calculated average weight within a population)
What are the types of data?
(think 2 Q’s)
Quantitative: Data that can be counted and measured (numerical)
Qualitative: Data that cannot be counted, added, ect (think QUALITIES)
What are units of observation?
The individuals from which data is collected
What is statistical inference?
Conclusions that can be made using the data from a sample in regards to the whole population
What are the two main categories of sampling?
Probability and NON-probability
What is sampling?
Choosing a specific part of a population to collect data from while avoiding BIAS
What are the characteristics of nominal data?
Classifiable
No obvious ordering or ranking
No arithmetic
(EX: Race, gender)
What are the characteristics of ordinal data?
Categorizable, rankable
Ordered by significance
No arithmetic
(EX: subjective results, opinion polling, low, med, high)
What are the characteristics of interval data?
Can be categorized, ranked, spaced
Measured on a scale
Numerical values
Can Add / Subtract
No multiplication / division
No natural ZERO (0 is just a number on a scale - it doesn’t necessarily mean zero)
(EX: 20 F is twice as hot as 10 F, can be ranked but cannot be necessarily verified if it “feels” that way)
What are the characteristics of ratio data?
Can be categorized, ranked, spaced, evenly spaced
Has a natural ZERO (ZERO is a possible measurement - it MEANS something)
All arithmetic allowed
(EX: 0 K is absolute zero, a 20 yr old is older than a 19 yr old, HEIGHT)
What are some ways to visualize data? (5)
Bar graphs
Scatter plots
Histograms
Pareto charts
Box-and-whisker plot
What is a pareto chart?
A chart that combines both lines and bars
Bars record values
Lines record totals
What are the properties of a box-and-whisker plot?
- Contains 5 (or more) numbers: Quartiles, Minimum, Maximum, Outliers
Simple Random Sampling
All elements have equal chances of being selected
Stratified Sampling
Groups are made, random selections from ALL groups
Cluster Sampling
Groups are made, all members of RANDOM GROUPS are selected
Multistage Sampling
Groups are made, random members selected from random groups
Systematic Sampling
Selecting elements in a manner that follows a pattern/system (Every 3rd)
Convenience Sampling
Elements chosen based on ease of access
Which data types are QUALITATIVE?
Ordinal and Nominal
