Question

Stats Question

A manufacturer receives parts from two suppliers. An SRS of 400 parts from supplier 1 finds 20 defective; an SRS of 100 parts from supplier 2 finds 10 defective. Let p1 and p2 be the proportion of all parts from suppliers 1 and 2, respectively, that are defective. Is there evidence of a difference in the proportion of defective parts produced by the two suppliers? To make this determination, you test the hypotheses H0 : p1 = p2 and Ha : p1 ≠ p2.The P-value of your test is
A. 0.1164.
B. 0.0602.
C. 0.0301.

Answer 1

I got
p1=.5
p2= .1
p=.0012
HO=30/500 I think... so now what?

Answer 2

do they expect you use a calculator? or a table?

for the p value

Answer 3

I can use a calculator and a table if necessary

Answer 4

ok because I'm getting something close to the answer, but wonder if they're using a table (instead of a calculator)

Answer 5

Oh I've only been using a calculator, but if there Is a table needed, then I have 5 to choose from, do you know which one is needed?

Answer 6

you would use the normal cdf table

Answer 7

or standard normal cdf table

Answer 8

ok I got that one, do you need me to attach it? Im not sure how I would use it in this problem

Answer 9

ok they are definitely used a table (I hate when they do that when you can easily use a calculator)

Answer 10

They're using something similar to this

http://homes.cs.washington.edu/~jrl/normal_cdf.pdf

Answer 11

sure attach yours so we can compare

Answer 12

its the same one, just that mine's cut in half, one is the negative values and the other the positive values, so when does the table come into play?

Answer 13

ok we'll get to that later (towards the end), so ignore the tables for now

Answer 14

alright

Answer 15

p1 = x1/n1

p1 = 20/400

p1 = 0.05

---------------

p2 = x2/n2

p2 = 10/100

p2 = 0.10

Answer 16

p = (x1 + x2)/(n1 + n2)


p = (20+10)/(400+100)


p = 0.06

Answer 17

next we find the standard error


SE = sqrt(p(1-p)(1/(n1)+1/(n2)))


SE = sqrt((0.06)*(1-0.06)*(1/(400)+1/(100)))


SE = 0.0265518360947035

Answer 18

then we find the test statistic


z=(p1-p2)/(SE)


z=(0.05-0.1)/(0.0265518360947035)


z = -1.88310894288677


z = -1.88

Answer 19

we then use this test statistic to find the area to the left of it under the curve

this is where the table or calculator will come in

Answer 20

ok ohhhh alright duh

Answer 21

so using the table I posted, what is that area?

Answer 22

.0301

Answer 23

now you double this to get 2*0.301 = 0.0602

Answer 24

you double this area because this is a two tailed test

Answer 25

ok, answered my question before I could ask it

Answer 26

they threw in the trap in C

a lot of people would have stopped at 0.0301

Answer 27

I would have, thankyou!

Answer 28

you're welcome