Quiz 4 Material

Question 1

What is statistical significance?

Answer 1

It is the degree of correlation or amount of difference necessary in order for there to be support for a hypothesis.

Question 2

Explain what alpha, beta, and p represent in terms of statistical significance.

Answer 2

alpha: the probability of making a Type I error
beta: the probability of making a Type II error.
p: the exact probability of the likelihood of the results erroneously being due to chance

Question 3

What are Type I and Type II errors?

Answer 3

Type I: rejecting the null hypothesis when it is true
Type II: Accepting the null hypothesis when it is false

Question 4

Describe the procedure used in hypothesis testing, specifying each step.

Answer 4

• Create a null and directional (alternative) statistical hypotheses from the research hypothesis
• Select an appropriate alpha level: limit chance incorrectly reject null hypothesis
  – often use 0.05, or more stringent 0.01. Occasionally, pilot work, exploratory, or proof of concept, 0.10 or 0.15 but difficult to study b/c not very stringent
  – 1 or 2 tailed, 1 better but only used if direction of difference known
• Collect Data and run statistical analysis using computer program (ie. SAS) input data receive p value (determine the appropriate statistic)
• Make decision regarding null hypothesis: p < alpha reject null, p > alpha do not reject
• Draw statistical and research conclusions

Question 5

What is the difference between a null and directional hypothesis?

Answer 5

The null hypothesis states that groups do not differ from each other
The directional hypothesis indicates that one group differs from another as a function of the independent variable

Question 6

Why do researchers need to select appropriate alpha values prior to statistical testing?

Answer 6

Because the alpha guides the determination to reject or accept the null hypothesis

Question 7

Differentiate among the three types of t-tests. Be able to describe each type.

Answer 7

One-sample 1 test “Student’s t test”: compares sample mean to population mean with normative data
Independent t Test: compare two independent groups of participants to each other on one variable (two samples from same pop or one from two different population)
Dependent t Test: compare two mean scores that are related (two tests same group or two related groups b/c matched or one group two conditions)

Question 8

What measure is used to assess meaningfulness of significant differences? Be able to describe this measure.

Answer 8

Effect size.
Significance testing tells that groups are different. Effect size tells how different groups are: an estimate of the strength of group differences.