0% found this document useful (0 votes)
149 views

Means

The document discusses several statistical concepts and analyses related to means, medians, logs, and ratios using tuition data for five colleges. It also discusses analyses of sex discrimination salary data using log transformations, permutation tests on differences in group means and medians, and survival analysis of breast cancer patients in a therapy group versus a control group.

Uploaded by

Mys Tique
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
149 views

Means

The document discusses several statistical concepts and analyses related to means, medians, logs, and ratios using tuition data for five colleges. It also discusses analyses of sex discrimination salary data using log transformations, permutation tests on differences in group means and medians, and survival analysis of breast cancer patients in a therapy group versus a control group.

Uploaded by

Mys Tique
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Means, Medians, Logs, Ratios.

Consider the following tuitions and their natural logs for five colleges:

(a). Find the average In-State tuition. Find the average log(In-State). Confirm that the log of the average is not the same as the average of the logs. (b) Find the median In-State tuition and the median of the logs of In-State tuitions. Verify that the log of the median is the same as the median of the logs. (c) Compute the median of the ratios. Compute the differences of logged tuitions ----log(Out-of-State) minus log(In-State) and compute the median of these differences. Verify that the median of the differences (of log tuitions) is equal to the natural log of the median of ratios (aside from some minor rounding error).

Sex Discrimination. With a statistical computer program, reanalyze the sex discrimination data in Display 1.3 but use the log transformations of the salaries. (a) Draw box plots. (b) Find a p-value for comparing the distributions of salaries. (c) Find a 95% confidence interval for the ratio of population medians. Write a sentence describing the finding.

Consider these artificial data: The difference in averages is -4. What is a one-sided value from the permutation distribution of the difference in averages? (Hint: List the 10 possible groupings; compute the difference in averages for each of these groupings, then calculate the proportion of these less than or equal to -4.)

O-Ring Study. Suppose the O-ring data had actually turned out as shown in Display 4.13. These are the same 24 numbers as before, but with the 2 and 3 switched. What is the one-sided value from the permutation test applied to the statistic? (This can be answered by examining Display 4.10.)

Effect of Group Therapy on Survival of Breast Cancer Patients. Researchers randomly assigned metastatic breast cancer patients to either an control group or a group that received weekly 90minute sessions of group therapy and self-hypnosis, to see whether the latter treatment improved the patients quality of life. The group therapy involved discussion and support for coping with the disease, but the patients were not led to believe that the therapy would affect the progression of their disease. Surprisingly, it was noticed in a follow-up 10 years later the group therapy patients appeared to have lived longer. The data on number of months of survival after beginning of the study are shown in Display 4.17. (Data from a graph in D. Spielgel, J. R. Bloom, H. C. Kraemer, and E. Gottheil, Effect of Psychosocial Treatment on Survival of Patients with Metastatic Breast Cancer, Lancet (October 14, 1989): 888-91.) Notice that three of the women in the treatment group were still alive at the time of the follow-up, so their survival times are only known to be larger than 122 months. Is there indeed evidence of an effect of the group therapy treatment on survival time, and, if so, how much more time can a breast cancer patient expect to live if she receives this therapy? Analyze the data as best as possible and write a brief report of the findings.

Google make a table in latex

You might also like