An investigator would like to conduct an independent samples ...

[burton19126]

An investigator would like to conduct an independent samples t-test to compare means between two samples. The sample size for each sample is 10.
 
  Upon initial evaluation it is found that both samples are not likely to be drawn from normally distributed populations. Further, investigation resulted that the population variances are unknown and are quite different. Should the investigator continue with the analysis? Why or why not?

Question 2

Positive correlation leads to small values of d, with 0 being the lower limit.
 
  Indicate whether the statement is true or false

[swimkari]

Answer to Question 1

No. Although the population variances are unknown and are not equal, the t-test is not applicable because the populations from which the independent samples are taken are found to be nonnormal. Also, the central limit theorem is not helpful with a small sample size of 10. Therefore, the investigator might consider nonparametric tests that do not require normal distributions.

Answer to Question 2

TRUE