Study text: "Essential Mathematics and Statistics for Science", 2nd Edition,

G Currell & A A Dowman, Wiley-Blackwell, 2009

G Currell & A A Dowman, Wiley-Blackwell, 2009

- Performing an Anderson-Darling (AD) test on 20 experimental data values produces a
*p*-value,*p*= 0.031, and the normal probability plot as below.

Which ONE of the follow sets of conclusions would be completely correct.- The data set is non-normal and shows a positive skewness.
- The data set is normal and shows a positive skewness
- The data set is normal and shows a positive kurtosis
- The data set is non-normal and shows a negative skewness

- A
*t*-test assumes that the data follows a normal distribution, and this can be checked by using a normality test such as the Anderson-Darling (AD) test.

Select ALL of the following statements that are true.

(Click here for the Video Answer) - Performing an Anderson-Darling (AD) test on 10 experimental data values produces a
*p*-value,*p*= 0.291, and the normal probability plot as below.

Which ONE of the follow sets of conclusions would be completely correct.- Accept the data as being normal, provided that there is no other reason to believe that the data is skewed
- Accept the data as being non-normal, because it is showing positive skewness
- The data appears to be normal showing a positive kurtosis
- The data appears to be normal showing a positive skewness

- You calculate the confidence interval, CI, for a set of experimental data (using an appropriate
*t*-value), but have reason to believe that the data source might not be normally distributed. You then perform an Anderson-Darling (AD) test to check the normality of the data.

Select ALL of the following statements that could be correct.

(Click here for the Video Answer) - What does the term ‘robust’ mean in relation to a statistical test?

Select ALL answers that are correct

(Click here for the Video Answer)