This

**preview**shows half of the first page. to view the full**2 pages of the document.**Confidence intervals & proportions

Margin of error: E = zc

√

p̂

1q̂

1

n1

+p̂

2q̂

2

n2

Hypothesis testing

Ex: A car manufacturer states that its new model gets 78mi/gal

Let µ be the mean gas mileage for this car. Manufacturer may overvalue car.

The claim µ = 47 is called the Null Hypothesis. (H0: µ = 47)

If I reject the null hypothesis, I need a claim to accept; the Alternate Hypothesis.

Alternate hypothesis is that µ < 47. (H1: µ < 47)

Types of tests

Left tailed: if H1 states that the parameter is less than the value claimed in H0.

Right tailed: if H1 states that the parameter is more than the value claimed in H0.

Two tailed: if H1 states that the parameter is different than the value claimed in H0.

Ex: Rosie the sheepdog. Vet fears her heart rate is slowing. For this breed:

µ = 115bpm σ = 12bpm

The vet takes Rosie’s pulse 6 times in 6 weeks.

x = 105bpm̄

H0: µ = 115bpm

H1: µ < 115bpm

How do we test this?

z =

̄

x−µ

σ

√

n

; z =

105−115

12

√

6

; z = -2.04

###### You're Reading a Preview

Unlock to view full version