Question

what is a "null hypothesis"?

Answer 1

The null hypothesis is a hypothesis which the researcher tries to disprove, reject or nullify.

Answer 2

very good; is it:

1. the same as the original claim?
2. different from the original claim?
3. depends on how it is stated :)

Answer 3

different

Answer 4

ideally that would be a nice condition. But if the original claim contains an equality, the the null hypothesis is the original claim. If the original claim is an inequality, the null becomes the opposite.

Answer 5

agreed.....can you help me with something?

Answer 6

i can try

Answer 7

A large pond is stocked with fish. The fish population P is modeled by the formula
P = 2t + 8(sqrt of t)+ 140, where t is the number of days since the fish were first introduced into the pond. How many days will it take for the fish population to reach 500? (Round your answer to the nearest whole number.)

Answer 8

500 = 2t +8sqrt(t) +140

0 = 2t +8sqrt(t) +140-500

0 = 2t +8sqrt(t) -360

360 -2t
------- = sqrt(t) ; ^2 both sides
8

(45 - t/4)^2 = t

2025 + t^2/16 -90/4t = t

2025 + t^2/16 -86/4t = 0 ... this might go quicker with a wolframalpha :)

Answer 9

abt 133.741

Answer 10

134 perhaps; but lets dbl chk

Answer 11

134 is pretty good

Answer 12

I think a better way of putting it is, the null hypothesis holds when the data is not statistically significant.

Answer 13

It is the condition where the data doesn't show any scientifically interesting results.

Answer 14

right, the null can happen by chance then right?

Answer 15

Suppose you have a sample of smokers and a scientist wants to show that smoking is correlated to a rise in cancer rates. They need to show that there are more cases of cancer than can be explained by what would normally be expected in a randomly selected group of people.

Answer 16

They are disproving the null hypothesis, where the null hypothesis would be that there is no correlation and the rates are what would be expected from a randomly sampled group of people.

Answer 17

That makes sense if you are trying to support a claim that contains an inequality such as more than, greater than, less than ....

but what about a claim of equality?

Answer 18

Can you give me an example of what you mean?

Answer 19

hmm .... the mean body temperature of healthy adults is equal to 98.6.

Answer 20

Statistical significance comes from looking for meaningful deviations from the mean. That means greater or less than. Its silly to say that something is statistically significant if it is equal to or close to the mean.

Answer 21

ok ... which is prolly why you dont find alot of nulls that are equal to the claim.

Answer 22

we were going over the hypthesis testing stuff in stats and the null/alternative section seemed backwards to me :) its making better sense now tho

Answer 23

Its just the "fallback" so to speak if you can't prove anything interesting is happening in the data.