1
$\begingroup$

Suppose you want to test the null hypothesis:

H0: p1 = 0.65, p2 = 0.27, p3 = 0.01, p4 = 0.05, p5 = 0.02

to determine whether a population's distribution matches the proposed proportions. You acquire a random sample of 100 individuals. If the null hypothesis were true, what is the expected value of the test statistic?

I'm not sure I conceptually/intuitively understand how the chi-squared works. Can someone elaborate on why the answer is 4 here? If the null hypothesis is true, then the population does have proportions equal to 0.65, 0.27, 0.01, etc. So what does this tell us of the test statistic?

Improve this question
$\endgroup$
1
  • $\begingroup$ If this is related to some subject, could you add the self-study tag please? $\endgroup$
    – Glen_b
    Commented Apr 22, 2013 at 1:12

1 Answer 1

Reset to default
2
$\begingroup$

Intuitively, if the sample proportions exactly matched the proposed proportions, $\chi^2$ would be 0. But there will be random fluctuation.

e.g. 

set.seed(239920)
(testmult <- rmultinom(1, 100, c(0.65, 0.27, 0.01, 0.05, 0.02)))

does not yield exactly 65, 27, 1, 5, 2.

On repeated draws, the expected value of $\frac{(O-E)^2}{E}$ will be the degrees of freedom, which in this case is 4.

Improve this answer
$\endgroup$
1
  • 1
    $\begingroup$ there is a typo in your statistic, the square is on the top, not bottom $\endgroup$
    – colinfang
    Commented Apr 21, 2013 at 21:57

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.