BUSN 3000 TEST 2 REVIEW

Type 1 Error

when you reject the null but the null is true

Type 2 error

when you fail to reject the null but the null is false

Standard error

the average error between the sample result (p-hat) and the assumed true population/proportion P

Ho (null hypothesis)

old value that is

Ha

alternative value, the result we want to show

Ha: p < hypothesized value

left tail test

Ha: p > hypothesized value

right tail test

Ha: p =/= hypothesized value

two sided test

Test statistic

Large test statistic

reject the Null

P Value

Probability of getting a sample result greater/less than the current P-hat is the null were true

Smaller p value 

reject null

Larger p value

fail to reject the null

If p-value < a

Reject the null, Ha is true

If p-value > a

fail to reject the null

If sample size increases then, standard error 

Decreases

If sample size increases than test statistic

Increases

If sample size increases than p-value

Decreases

As we increase the confidence level the width of the interval

increases

As the sample size increases there variability of P-hat DECREASES, thus the interval will be 

narrower

Wider intervals when p-hat is closer to

0.5

A larger standard error SE will result in the interval being

Wider

To decrease the margin of error what must decrease

confidence level

Unit 7 uses which kind of values

average values

Unit 6 uses which kind of values

proportion/population

Unit 5 is mainly about what

sampling and sampling distributions

The unknown fact you are trying to estimate is called

Parameter/estimand 

Estimator

the formula/equation used to compute an estimate based on the data

Estimate

specific value obtained from the sample data

Simple random sample

sample of 10

all have same chance of being selected

Systematic sample

randomly select a starting point

jump=population size/sample size

Stratified random sampling

classify population into similar individuals 

more precise

includes members from each group

Cluster sampling

population is divided into clusters and then chosen at random

cheap and easy