Statistic Year 2 Flashcards
Bivariate
Two variables
product moment variable coefficient
gives type (positve or negative) and strength of linear correlation between x and y
Regression calculation
- assin one to x and y
- put all values in (stats, 2 var)
- shift EXE
- regular results
- choose depending on relationship
- r= regrssion
P(AUB)
P(A) + P(B) - P(AnB)
P(AnB)
P(B) times P(AIB)
P(AIB)
P(AnB) / P(B)
P(B’UB)
1
difference between P(AUB) and P(AnB)
random variable
represented by capita X Y Z takes on values that are outcomes of an experiment
e.g. let X be the number of heads you get when tossing two fair coins
X= 0,1,2
Continuous random variable that follows a normal distribution
X~N(μ,σ^2)
μ- poluation mean
σ^2 population variance
σ population standard deviation
normal distribution properties
- has a bell-shaped curve
- symetrical about the mean
mean = mode= median - the area under the bell-shaped curve represents probability
- total area = 1
key percentages for a normal distribjution
1 σ 68%
2 σ 95%
3 σ 99.7%
68% of the data is within one standard deviation of the mean
if P(X>a) = 0.4
do the normal distribution of P(X<a) = 0.6
normal distribtion condition
mean = median = mode
μ
centre of bell shaped curve
when to use a one tailed test
if you want to trst if population PMCC is greater or smaller than zero
when to use a two tailed test
when checking if population is not/ equal to zero
PMCC
regular results, r
critical value
question states the type of correlattion
approximating the binomial distribution
if n is large
if p is close to 0.5
the bionomial distribution X~N(n,p) can be aproximated by the normal distribution
aproximating the binomial distribution formulae
λ=np
σ= square root of (np(1-p))
when finding probabilities for normal distribution e.g.
P(X<33)
normal cd function
for normal distribution to be used the variable has to be
continuous
with discrete/ continuous variable all the propbs had add up to
1
the curve has points of inflection
one standard deviation from deviation from the mean i.e.
lamda - sigma
(where curve changes concavity)
normal distribution is symetical
mean= mode = median