In: Statistics and Probability
How do we know the answer for that? The answer is 6.
You perform a Q-test on a particular data point and obtain a Q value of 0.67. How many data points would you need to be able to reasonably discard this data point as erroneous?
The limit values of the two-tailed Dixon's Q test can be summarized using the following table
The number of values: | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
Q90%: | 0.941 | 0.765 | 0.642 | 0.560 | 0.507 | 0.468 | 0.437 | 0.412 |
Q95%: | 0.970 | 0.829 | 0.710 | 0.625 | 0.568 | 0.526 | 0.493 | 0.466 |
Q99%: | 0.994 | 0.926 | 0.821 | 0.740 | 0.680 | 0.634 | 0.598 | 0.568 |
So we basically compare the calculated Q value with the table value mentioned above.
Since you have not specified the level of confidence, I am assuming it to be 95%.
The data points we would need to be able to reasonably discard this data point as erroneous would be the data point at which Q < Qtable
At Q = 0.67 < Q6(table) = 0.625
At Q = 0.67 > Q7(table) = 0.710
Hence at 95% level of confidence the number of data points is 6
at which we would be able to reasonably discard this data point as
erroneous.
If satisfied, please
do upvote! Let me know in the comments if anything is unclear. I
will reply ASAP