Statistics Momento Mistaki

How to write the discrete uniform distribution in function form

P(X=x) = a for Inequality of domain

Comment on the suitability

comparision of model’s prediction to actual value suggests good or not good

Refinement to a discrete uniform distribution for cloud cover

reason (varies with location and month) so non-uniform

Explainatory variable

independent variable

Response Variable

Dependent variable

How to state with a reason which is the explainatory variable

x will be the explainatory variable because it affects y

What words must you not use when talking about the explainatory variable in relation to the response variable

CAUSES or EXPLAINS no causation

How to Interpret a gradient of a regression equation

every UNIT rise in BLAH results in a (CHANGE) in blip of GRADIENT VALUE (CONTEXT!!!)

State assumptions that BLAH needs to make to use her binomial model

Binomial conditions hidden in CONTEXT

How to find the probability of the first success being after m trials from a binomial distribution of success of the successes in n trials

(probability of failure)^(n-1)(probability of success)

If two values from outside the IQR have moved to inside the IQR but above Q₁ which two values will change on a boxplot and why

Median and Q3 because there are more values below (VALUE OF Median) than below

Given a normal model, a sample of n and starting with X > a how do you find the probability that NONE of the sample will have X < b (b>a)

Find 1 - P( a < X < b)/P(X > a) and put to the power of n g idk why not 1-p then divide?

Given a normal model, sample where n have (X > a) and m have no data, what is the probability that none of the sample will have (X < b)

(1 - P(a<X<b)/P(x>a))to the power n x P(X>b)to the power m

Use the value calculated from the data and the value predicted by the model to comment on the suitability of the model

compare values and if not roughly same say ‘so model may not be suitable’

explain why a linear regression model based on these data is unreliable when (a value is out of the range)

It requires extrapolation so will be unreliable

state what is measured by the product moment correlation coefficient

Linear association between x and y

what does mean temperature of 27.2 suggest in july

Overseas not perth

what does windspeed mean of 3.5 suggest

not coastal

Accuracy for probabilities (awrt)

3 s.f.

when hypothesis testing for mean from sample mean what do you use for σ

sd/√n

How to hypothesis test for mean

assume h0, write distribution of xbar with sd/rootn , find p(xabr is more extreme than value) compare probability with sig level

What accuracy should you use for the p you get from a hypothesis test when comparing with significance level? awrt

3 s.f.

how to show that events are NOT independent

P(A)xP(B) = a DOES NOT EQUAL P(A intersection B) = b

What accuracy for p found for a binomial distribution?

anything?

She believes that a non linear model is better, the pmcc of the coded values (THIS VALUE) is greater than that of the uncoded. Explain how this value supports her belief

The value is close(r) to 1 or there is strong(er) (positive)

correlation

When using answers to comment on model can you just use the question part labels? (i think?)

yes

Should you calculate the standard deviation in the little box in distribution mode

NO!