Question

From the list shown below, for each of the following hypothesis testing situations indicate the type of test you would use. Unless indicated otherwise, the significance level for all the tests is .05

One-sample t test

One sample Wilcoxon signed-ranked test

McNemar Test

Two samples t test for independent means with equal variances

Paired samples t-test

F test

Mann-Whitney U test

Chi-square test

Paired Sample Wilcoxon Signed Ranked test

Two samples t test for independent means with unequal variances

A financial aid advisor wants to see if students are overly optimistic about their future salaries. He knows that the distribution of starting salaries for public health majors graduating from the school is normally distributed with a mean of $ 48,000 or u = $4,000 a month. To determine if public health students are overly optimistic about their potential salaries, the counselor obtains a random sample of 15 MPH students from UWF and asks each one of them individually what they expect their monthly salary will be in their first job after graduation. The 15 students' expected starting monthly salaries had a mean of 4,200. The counselor chooses a one-tailed test and alpha of 0.05. The research question is: Is the student's mean estimated starting salary significantly higher than the actual starting salary for nurse’s students?

Researchers want to find a better way of encouraging children to read more and discovered two possible approaches. To decide which to implement, they randomly select two libraries. In library a they enhanced the children's reading area and shelving as suggested in one plan, and in library B, they enhanced the children's reading area according to the other plan. After a year, they collected data on how many books each member of the two borrowed over the period. The researchers assessed the amount of reading in a Likert scale; therefore, the variable reading was an ordinal variable, and although the distribution was symmetric, the researchers could not assume the data is normally distributed.

Researchers wanted to assess if children living in the far north grow more slowly than those who live in sunnier regions. Their null hypothesis was that there would be no significant difference in height between two samples of 14-year-olds chosen from northern Finland and southern Italy. The randomly selected 50 children aged 14 from two different schools and their heights were measured and recorded in centimeters. It is assumed the test variable “height” was normally distributed in each of the populations; the cases represent a random sample from the population, and the scores on the test variable are independent of each other; and the variances of the normally distributed test variable for the populations are equal

A nurse is leading a smoking cessation group and wants to determine the effectiveness of the intervention. The research question is: will providing a 1-hour smoking cessation workshop help to reduce smoking among the participants? Ho= the smoking cessation workshop is not effective in reducing smoking; Ha: the smoking cessation workshop is effective in reducing smoking. The nurse selects 40 participants. The data is assumed to be normally distributed

An investigator read that there is an antibiotic often tested, well documented, and known to help information stored in memory. This experimenter also knows through scientific reports and guidelines that behavioral therapy has an established efficacy for the treatment of the social phobia. In addition, he knows that behavioral therapy requires the learning of new behaviors which implies information storage.   The number of symptoms of social phobia after two types of therapy was investigated. Two groups of individuals with social phobia were compared. The first group (10 participants) received the behavioral therapy; the second group (15 participants) received the behavioral therapy combined with the antibiotic. After each therapy, both groups showed a decrease in the number of symptoms of social phobia. The number of these symptoms was measured and a test was run to decide whether the combined therapy had more effect on the symptoms than the behavioral therapy alone.

Answer 1

From the list shown below, for each of the following hypothesis testing situations indicate the type of test you would use. Unless indicated otherwise, the significance level for all the tests is .05

One-sample t test

One sample Wilcoxon signed-ranked test

McNemar Test

Two samples t test for independent means with equal variances

Paired samples t-test

F test

Mann-Whitney U test

Chi-square test

Paired Sample Wilcoxon Signed Ranked test

Two samples t test for independent means with unequal variances

A financial aid advisor wants to see if students are overly optimistic about their future salaries. He knows that the distribution of starting salaries for public health majors graduating from the school is normally distributed with a mean of $ 48,000 or u = $4,000 a month. To determine if public health students are overly optimistic about their potential salaries, the counselor obtains a random sample of 15 MPH students from UWF and asks each one of them individually what they expect their monthly salary will be in their first job after graduation. The 15 students' expected starting monthly salaries had a mean of 4,200. The counselor chooses a one-tailed test and alpha of 0.05. The research question is: Is the student's mean estimated starting salary significantly higher than the actual starting salary for nurse’s students?

One-sample t test ( sample mean is compared with population mean)

Researchers want to find a better way of encouraging children to read more and discovered two possible approaches. To decide which to implement, they randomly select two libraries. In library a they enhanced the children's reading area and shelving as suggested in one plan, and in library B, they enhanced the children's reading area according to the other plan. After a year, they collected data on how many books each member of the two borrowed over the period. The researchers assessed the amount of reading in a Likert scale; therefore, the variable reading was an ordinal variable, and although the distribution was symmetric, the researchers could not assume the data is normally distributed.

Mann-Whitney U test ( two groups are compared, data is not normally distributed)

Researchers wanted to assess if children living in the far north grow more slowly than those who live in sunnier regions. Their null hypothesis was that there would be no significant difference in height between two samples of 14-year-olds chosen from northern Finland and southern Italy. The randomly selected 50 children aged 14 from two different schools and their heights were measured and recorded in centimeters. It is assumed the test variable “height” was normally distributed in each of the populations; the cases represent a random sample from the population, and the scores on the test variable are independent of each other; and the variances of the normally distributed test variable for the populations are equal

Two samples t test for independent means with equal variances

A nurse is leading a smoking cessation group and wants to determine the effectiveness of the intervention. The research question is: will providing a 1-hour smoking cessation workshop help to reduce smoking among the participants? Ho= the smoking cessation workshop is not effective in reducing smoking; Ha: the smoking cessation workshop is effective in reducing smoking. The nurse selects 40 participants. The data is assumed to be normally distributed

Paired samples t-test ( before and after data)

An investigator read that there is an antibiotic often tested, well documented, and known to help information stored in memory. This experimenter also knows through scientific reports and guidelines that behavioral therapy has an established efficacy for the treatment of the social phobia. In addition, he knows that behavioral therapy requires the learning of new behaviors which implies information storage.   The number of symptoms of social phobia after two types of therapy was investigated. Two groups of individuals with social phobia were compared. The first group (10 participants) received the behavioral therapy; the second group (15 participants) received the behavioral therapy combined with the antibiotic. After each therapy, both groups showed a decrease in the number of symptoms of social phobia. The number of these symptoms was measured and a test was run to decide whether the combined therapy had more effect on the symptoms than the behavioral therapy alone.

Mann-Whitney U test (( two groups are compared, data, the number of symptoms, is not normally distributed)