Author Question: A researcher is studying the effect upon pain of providing hypnosis with dental work. The ... (Read 72 times)

serike · **on:** Jul 8, 2018

A researcher is studying the effect upon pain of providing hypnosis with dental work.

The researcher's three groups are (1) hypnosis before and during the procedure, (2) hypnosis before but not during the procedure, and (3) no hypnosis. If the researcher plans to use an ANOVA for the statistical analysis, which would be an acceptable way to measure pain, for this study? (Select all that apply.)
a. Present versus absent
b. Worse ... Some ... A Lot ... Unbearable
c. 0- to 100-point verbal numerical scale
d. Systolic blood pressure readings
e. The force with which the subject squeezes a rubber ball with pressure gauge attached

Question 2

Why is post hoc statistical testing not performed with a two-group ANOVA?

a. A researcher is reluctant to perform a post hoc analysis that would require a more stringent level of significance.
b. The F-statistic would be invalidated by the second test.
c. If hypothesis testing reveals that a difference between groups exists, it is obvious what two groups those are.
d. Sample sizes are not large enough for this analysis.

nicoleclaire22 · **Reply #1 on:** Jul 8, 2018

Answer to Question 1

ANS: C, D, E
The parametric statistics used to determine differences that are covered in this chapter are the independent samples t-test, paired or dependent samples t-test, and analysis of variance (ANOVA). ANOVA requires that the dependent variable be at the interval or ratio level: a verbal numerical scale, systolic blood pressure readings, and force with which the subject squeezes a rubber ball are all interval or ratio level variables.

Answer to Question 2

ANS: C
Post hoc tests have been developed specifically to determine the location of group differences after ANOVA is performed on data from more than two groups. The post-hoc analyses performed after the ANOVA preserves the same level of analysis as the ANOVA itself. The F-statistic is not invalidated by performing a post hoc analysis. Sample size is not a consideration when performing a post hoc analysis.