Null hypothesis is best described as:

• A. A statement predicting no significant difference between two groups or treatments studied.
• B. A statement predicting a significant difference between two groups or treatments studied.
• C. A statement about the sampling distribution of the statistic.
• D. A statement that there is always a significant result.

Answer: (A)

The main idea being tested is a null hypothesis, which is a statement of no difference or no effect between two groups or treatments. In practice, we set up the null as the default assumption about the population parameter—often that the means are equal or the proportions are the same. When data are collected, we see how likely it would be to observe what we did if this no-difference assumption were true. If that likelihood is very low (below our chosen significance level), we reject the null and conclude there is evidence of a difference or effect; if it isn’t, we don’t reject the null, meaning we don’t have strong evidence of a difference—though that doesn’t prove there isn’t one, only that we didn’t detect it given the sample and threshold.

This statement is about the population parameter, not about the sampling distribution itself, which is the model we use to understand how samples vary under the null. It’s also distinct from the alternative hypothesis, which is the claim that there is some difference or effect. Finally, the idea that there will always be a significant result is incorrect, since significance depends on the data, sample size, and chosen alpha level.