ST370 Prob & Statistics for Engineers NC State, complete
|
Population
The entire collection of subjects we wish to target
|
|
Sample
A subset of the population
|
|
Univariate
1 variable
|
|
Bivariate
2 variables from the same subject
|
|
Multivariate
2 or more variables from the same subject
|
|
Qualitative Data
Categorical, descriptive (yes/no, blue, etc)
|
|
Quanitative Data
Numeric (include discrete and continous)
|
|
Discrete Data
Primarily count data (the number of...)
|
|
Continuous Data
Data from measurements (can take on any value w/in some interval)n
|
|
Stratified Sample
|
helps avoid biased data (If there are 2X white people than Hispanics, then the sample should have 2X white people than Hispanics)
|
|
Convenience Sampling
|
Stay away from this, (Choosing to only sample from one assembly line on the shop floor)
|
|
Simple Random Sampling
|
(A name is drawn out of a hat)
|
|
Experiment
|
allows us to draw cause and effect b/c of the ways its designed (the best)
|
|
Survey
|
A questionnaire or observation
|
|
Descriptive Statistics
use of graphs, numeric computations to summarize the data
|
|
Inferential Statistics
Make and inference using sample statistics back to the population
|
|
Sample Mean (x ̅)
|
Population mean (μ)
|
|
Sample Median (x ̃)
|
Population Median(μ ̃)
|
|
Sample Relative Frequency (p ̂)
|
Population Proportion (p)
|
|
Sample Standard Deviation (s)
|
Population Standard Deviation (σ)
|
|
Sample Variance (s2)
|
Population Variance (σ2)
|
|
Trimmed Mean
|
trim a certain percentage of values from the ends of the data set, and then average whats left
|
|
Standard deviation (s)
|
The size of a typical deviation (calculator function)
|
|
Variance (s2)
|
How data points vary from the mean
|
|
n
|
sample size
|
|
N
|
population size
|
|
Center
tells us what a typical value in the data set should be (If data is fairly symetric use mean, otherwise, use median)
|
|
Spread
The range of data
|
|
Skew
If the bell curve is shifted left (negative skew) or right (positive skew)
|
|
Box Plots
|
They show us outliers visually, and are great for comparing multiple data sets
|
|
Quartiles
|
Values that divide the sorted data set into 4 equal parts.
|
|
Q1
|
The smallest 25% of data
|
|
Q2
|
The median
|
|
Q3
|
The 75% mark
|
|
Q4
|
The max value
|
|
percentiles
|
If a value is in the first quartile, then 75% of the values are grater than that, so your in the 75th percentile
|
|
Box Plots
|
Show us outliers visually and great for comparing multiple data sets
|
|
Dot Plot
|
Dots located above their value on the X-axis
|
|
Stem and Leaf
|
The stem of the number includes all but the last digit (so 38|3 would be 38.3)
|
|
Histogram
|
Like box graphs but there's no spaces between columns, can be used with discrete and continuous data
|
|
Histogram Shapes:
|
Symmetric, Right(positive) skew, Left (negative) skew, Bi-modal (2 peaks), and Multi-modal (many peaks)
|
No comments yet.
Cheatography n. The art of mapping complex subjects into clear, instantly navigable reference guides.
