Module 11.3: Mean Differences, Difference in Means Flashcards
What does application of either of the t-tests used to test differences between the means of two populations require?
1) that samples are independent
2) that they are normally distributed
When is a pooled variances used with a t-test and when is the sample variance used for both populations during a t-test?
for testing the hypothesis that the means of two normally distributed populations are equal, when the variances of the populations are unknown but assumed to be equal.
when variances are unknown and assumed to be unequal, sample variance from both populations is used.
When is a paired comparisons test used (“test of significance”)?
does the test require the sample data to be normally distributed?
What is the test statistic used for a paired comparisons test?
when the two samples are dependent, meaning an event has affected both sets of observations.
yes, needs to be normally distributed.
the t-statistic.
When is the chi-square test used?
Is the chi-square test asymmetrical? Bounded by 0?
Does it approach normal distribution share as degrees of freedom increases?
for hypothesis tests concerning the variance of a normally distributed population.
Yes, it is asymmetrical, and bounded by 0.
Yes, it becomes more normal as DOF increase
When is the F-test used?
What are the two main assumptions of the F-test?
for hypotheses concerned with the equality of the variances of two populations.
under the assumption that the populations from which samples are drawn are normally distributed and that the samples are independent.
What determined the shape of the f-distribution?
Is it bound? and which direction is it skewede?
two separate degrees of freedom
bound by 0 on the left and skewed right.
For an f-test when the sample variances are equal what is the value of the f-test statistic?
1
What is the test statistic for the hypotheses relating to whether the true population correlation coefficient is equal to zero?
t-statistic with n-2 degrees of freedom.
What are the three situations where a nonparametric test is called for?
1) the assumptions about the distribution that support a parametric test are not met.
2) when data are ranks and not values.
3) when the hypothesis does not involve the parameters of the distribution.
What is a Spearman rank correlation test and when is it used?
can be used when the data is not normally distributed.
For an F-test is the larger sample in the numerator or the denominator?
numerator. if exceeds upper critical value, you should reject.
If larger sample was numerator, then the f test statistic will be greater than 1.
