Biostats exam II conceptual questions

A type 2 statistical error:

Fail to reject the null (Ho) hypothesis when the null is false

If you lower the significance level (alpha) from 0.05 to 0.01

You are lowering the probability of a type 1 error but you are increasing the probability of a type 2 error.

A p-value is:

The probability of observing an outcome that is at least as extreme as what we got if the null hypothesis (Ho) is true.

Which one of the following is incorrect about the statistical hypotheses (Ho and Ha):

The null hypothesis has the same probability of being true as alpha

Which one of the listed below is not a valid approach to conduct a paired experimental design. 

Individuals from the same geographic area are randomly allocated to one out of two treatments.

Nonparametric statistical techniques do not assume the normal distribution for continuous variables.

True

Which answer is true about the multiple comparisons problem in statistics:

The more statistical comparisons are made the higher the probability of committing at least one type 1 error.

Confidence intervals and statistical hypotheses tests are mathematically equivalent and generally allow you to reach the same conclusion about statistical significance.  

True

As discussed in class, which of the following is an advantage of paired designs compared to unpaired (=independent) design studies?

 

You have more control over extraneous variables that might have a confounding effect on the data.

When conducting the Wilcoxon rank-sum test we start by calculating the averages of the two groups being compared. 

False