-
Population
The entire collection of objects or outcomes about which information is sought
-
Sample
A subset of a population containing the objects or outcomes that are actually observed.
-
Simple Random Sample
of size n is a sample chosen by a method in which each collection of n population items is equally likely to comprise the sample, just as in a lottery
-
Bias
difference between sample and population
-
Conceptual Population
A population that consists of all values that could possibly be observed, from which a simple random sample comes
-
Experiment
An experiment is any procedure that can be infinitely repeated and has a well defined set of outcomes
-
Sampling Variation
variation due to performing the experiment
-
Response Variable
- Outcome (Dependent Variabel)
- example: mpg
-
Factor
- quantity changed (Independent Variable)
- example: driving style
-
Levels
- exact value of the factor
- example: windows up/down
-
sample mean
Xbar = 1/n { summation (x1 , x2 , ..xn) }
-
Sampling Variance
S2= 1/(n-1) { sum 1 to n (xi - xbar) } 2
-
Sample Standard Deviation
s= { sqrt (s2) }
-
Sample Median
Middle of ORDERED data
-
Dotplot
- . .
- . . . ... . .. . .
- ________________
-
Histogram
the thing with lots of bars and each represents a spread of values like 6-10 or 11-15
-
box plot
learn how to make these.. IQR?
-
Barplot
do instead of piechart each bar is a percent of total observed, so all are < 1
-
Sample Space
Lits of all possible values
-
Event
A subset of the Sample Space
-
-
-
-
Mutually Exclusive
Nothing in Common
-
Axioms of Probability
- i P(Sample space) = 1
- ii P(A) ≥ 0
- iii if A and B are Mutually Exclusive, P(A U B) = P(A) + P(B)
-
Additive Rule
P(A U B) = P(A) + P(B) - P( A ∏ B)
-
Number of ways to perform k tasks
n1, n2, .....nk
-
Permutation
- number of ways to choose within group where order matters
- n! / (n-k)!
-
Combination
n! / (k!(n-k)!)
-
Conditional Probability
- P(A l B)
- which is P(A "given" B)
-
Independence
P(A l B) = P(A)
-
Multiplicative Rule
P( A ∏ B) = P(B) x P(A l B)
-
Definition of a Random Variable
quantity that takes on different values with different possibilities numerical
-
Characteristics of a discrete random variable
discrete, countably infinite possible values
-
Probability Mass FUnction
P(x) = P(X=x) = P(X= specific thing)
-
Mean of a discrete random variable
µx = { sum all poss (X x p(x)) }
-
Variance of a Discrete Random Variable
sigma2 = {sum. all possible (x-µ)2 x p(x)
-
Standard Deviation of a Discrete Random Variable
- sigma = {sqrt (sigma2)}
- standev disc rand var = sqrt variace disc rand var
-
Characteristics of a Continuous Random Variable
Takes on different possible values with different possible probabilities (on the interval)
-
Probability Density Function
Probability is Area under P(a < x < b) = {integral a to b ( f(t) dt) }
-
Mean of a Continuous Random Variable
µx = integral -infinity to infinity (x f(x)
-
Variance of Continuous Random Variable
sigma2 = {integral -inf to +inf [ (x-µ)2 x f(x) dx] }
-
Standard dev of a cont random variable
sigma = {sqrt (sigma2)}
-
Probability Mass Function of Bernoulli (p)
- P(x) = (1-p if x=0)
- ( p if x=1)
-
-
Variance of Bernoulli
p(1-p)
-
Characteristics of Binomial (n,p)
x ~ Binomial (n,p)
-
Probability Mass Function of Binomial (n,p)
- P(x) = (nx) px(1-p)n-x if x = 0,1,2....n
- 0 otherwise
-
Mean of Binomial (n,p)
µx = np
-
variance of Binomial(n,p)
sigma2x = np(1-p)
-
Probability mass function of Poisson (lambda)
- P(x) = e-lambda (lambdax/x!) if x = 0,1,2,....
- 0 otherwise
-
mean of Poisson (lambda)
µx = lambda
-
Variance of Poisson (lambda)
sigma2x= lambda
-
Charactersitics of N (µ,sigma2)
N is normal, µx = µ ..... sigma2 = sigma2
-
empirical rule
- 68% will fall within 1 standev
- 95% will fall within 2 standev
- 99.7% will fall within 3 standev
-
-
compute probabilities of Lognormal (µ, sigma2)
if take log of lognormal you get normal
|
|