How does Null Hypothesis Significance Testing (NHST) differ from the estimation approach to analyzing data?

NHST is actually the exact same thing as the estimation approach, but it is called estimation in the U.S. and NHST in Europe and Australia.

NHST is different, but it is based on the same foundations as the estimation approach, and one can usually translate results back and forth between these approaches.

NHST and estimation approaches are completely incompatible, so using one means you must avoid the other.

NHST is the approach used for experimental research, and estimation is used for all other types of research.

2.

In the NHST approach, what is the null hypothesis?

an open-minded approach, where one has no hypotheses prior to conducting research

a statement giving a specific value of the parameter one is studying, a value that one will test to determine if that value is plausible

a hypothesis that has already been rejected by previous researchers but still appears promising because of subsequently identified mistakes in their procedures

the assumption that one's data will be flawed

3.

What doespindicate?

the probability of rejecting the null hypothesis

the probability of a false positive

the probability of obtaining results similar to the one's own or more extreme IF the null hypothesis is true

the probability that a data analysis will be conducted without having to correct the results

4.

Which statement is correct?

P-values can range from 0 to 1.

P-values can range from 1 to 1.

P-values can range from 0 to infinity.

The definition of p-value is deliberately ambiguous.

5.

When a p-value is near zero, this indicates

the data obtained are very unlikely if the null hypothesis is true.

the data obtained are very likely if the null hypothesis is true.

the data obtained were not sufficient to tell us anything about the null hypothesis.

the probability that further research should be conducted.

6.

You read in the results section of a research article, "We found that the two groups were significantly different in terms of depression scores (t(25) = 2.1,p= .046)." Based on this statement, you know that

the p-value reported by the researchers is based in the assumption that the null hypothesis is true.

the two groups being compared had the same levels of depression.

had an estimation approach been used, the 95% confidence interval would have included 0.

the researchers will not reject the null hypothesis.

7.

A researcher measures learning in 12 students who were randomly assigned to take Psychology 101 online or in a traditional classroom. With a null hypothesis of no difference, she finds no statistically significant difference in learning (t(10) = 0.70,p= .50). Should she conclude that online courses are just as effective as regular courses are?

Yes, because the p-value is large.

No, because a large p-value is not evidence that the null hypothesis is true.

No, because only p < 0.05 would justify doing so.

Yes, because the 95% CI would not include 0 difference in learning.

8.

A Type II error is

rejecting the null hypothesis when it is actually true.

failing to reject the null hypothesis when it is actually true.

rejecting the null hypothesis when it is actually false.

failing to reject the null hypothesis when it is actually false.

9.

A researcher administers a moral-reasoning test to participants randomly assigned to complete the test during the morning or during the afternoon. She finds that those who took the test in the afternoon are more judgmental than those who took it in the morning,t(38) = 2.71,p= 0.01. She rejects the null hypothesis that time of day has no effect on moral reasoning. What type of error is her conclusion related to?

Type II

Neither. The p-value is so small that there is no doubt that her results are accurate.

Both Type I and Type II

Type I

10.

In NHST, once a test statistic is available, its distribution should be consulted in order to determine ap-value. How is it determined?

by determining the probability of a p-value less extreme

by determining the probability of a p-value more extreme

by determining the mode of the test-distribution statistic

by multiplying the test statistic by 1.96