In: Statistics and Probability
A computer random number generator was used to generate 950 random digits from 0 to 9. The observed frequencies of the digits are given in the table below.
0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
88 | 82 | 97 | 84 | 87 | 87 | 95 | 93 | 90 | 147 |
Using a 0.05significance level, test the claim that all of the
digits are equally likely.
(a) Find the rejection region.
Reject H0 if χ2>
(b) Find the test statistic. (Round your final answer to 2 decimal
places.)
χ2=
(c) Do these data provide significant evidence that the the digits
are not equally likely? (Type: Yes or
No )
Here we are to test that all the digits are equally likely or not.
Hence we compute the probabilities of the given digits and then see whether the distribution matches with uniform distribution or not.
Digit | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | Total |
Frequency | 88 | 82 | 97 | 84 | 87 | 87 | 95 | 93 | 90 | 147 | 950 |
(a)
The rejection region is given as:
Reject H0 when
The critical value of is obtained from the Biometrika table as 16.919
(b)
For the data to be equally likely, the probability of the 10 digits to occur must be 1/10=0.1
So the expected frequency for all the digits must be 0.1*950=95
Now we make a continuation of the table to compute the test statistics.
Digits | Observed Frequency(O) | Expected Frequency(E) | |
0 | 88 | 95 | 0.515789 |
1 | 82 | 95 | 1.778947 |
2 | 97 | 95 | 0.042105 |
3 | 84 | 95 | 1.273684 |
4 | 87 | 95 | 0.673684 |
5 | 87 | 95 | 0.673684 |
6 | 95 | 95 | 0 |
7 | 93 | 95 | 0.042105 |
8 | 90 | 95 | 0.263158 |
9 | 147 | 95 | 28.46316 |
Total | 950 | 950 | 33.72632 |
Hence the test statistic is =33.72632
(c)
As , we reject the null hypothesis at 5% level of significance and hence conclude that the digits are not equally likely at 5% level of significance.
Hopefully this will help you. In case of any query, do comment. If you are satisfied with the answer, give it a like. Thanks.