skip to Main Content

Please note that this is just a preview of a school assignment posted on our website by one of our clients. If you need assistance with this question too, please click on the Learn More button at the bottom of the page to get started.

I want the completed assignment handed in electronically through myCourses (via the Assignment) as a PDF document. In the name of the file that you submit please be certain to include your name (last name, then first name), the course number, and the assignment number; this helps greatly with grading. You may discuss the homework with each other; however you must turn in your own original solutions – no copying. The intent is that you may participate in a study group, but you must do your own work. Remember, copying someone else’s work and presenting it as your own is cheating (and stealing from them). If you have any questions about cheating, then I suggest that you read the student handbook section on academic honesty. Access the handbook at rules will be enforced.Please show all work for each answer; i.e., show how you arrived at the answer. Also, in order to get full credit, where asked to use JMP to answer questions you must turn in a copy of the portion of the JMP output that is relevant to your solution. Do Not just write down numbers, I need to see where you got the information from the JMP output. Remember the selection tool (fat plus sign) on the Cursor Tool Bar can be used to copy paste output from JMP to other applications. (15 pts) The file CancerMSA.JMP contains the results of an attribute measurement systems analysis performed in radiology department of a large hospital. The study involved two raters, who rated each of a set of images twice, and an expert. The decisions of the expert are considered definitive and correct. The study includes images for two types of cancers Breast and Lung.Use the Variability/Gauge Chart platform to assess the intra rater and inter rater agreement and the accuracy with respect to the Expert. Perform separate analyses for the Breast cancer group and the Lung cancer group, you can do this by declaring “Type” a by variable in the Variability/Gauge Chart launch dialog window. For each “Type” in the Conformance Report set “Yes” as the nonconforming category – this will insure that false positives and false negatives are correctly identified.
(5 pts) For the analyses in part a comment on the intra and inter rater agreement levels based on the Kappa statistic. In terms of agreement, do the raters appear capable for both types of cancer? Explain.
(5 pts) For the analysis in part a comment on the accuracy of the raters with respect to the Expert. Do the raters appear to be in good agreement with the Expert for both types of cancer? Explain.
(5 pts) Finally, comment on the false positive and false negative rates that occur for both types of cancer. Based on the false negatives and positives do you think the raters are capable of making correct decisions – are the error rates acceptable. Keep in mind that a false negative is worse than a false positive for this type of diagnostic imaging.
(15 pts) The prothrombin time (PT) is the time (in seconds) it takes a blood plasma sample to clot after addition of a tissue factor. The PT is used to determine the clotting tendency of blood from a patient. The test is commonly given to patients on “blood thinners” such as Warfarin to measure the therapeutic effect of a given dosage. Because of natural variation in batches of tissue factor, the PT results are usually converted to an International Normalization Ratio or INR. An INR = 1 indicates a normal clotting time for a healthy individual not taking “blood thinners”. INR values in the range of 2.0 to 3.0 are generally considered desirable and therapeutic in preventing blood clots. Doctors consider an INR shift of 0.25 in a patient to be of clinical importance. In a particular MSA on a type of Pro-timer test, 3 operators performed INR measurements on 5 certified QA plasma samples, and each operator redid the test twice (2 repeat measurements). The data are in the file INR MSA.JMP. We will use the Variability Chart platform in JMP (Analyze  Quality and Process  Variability/Attribute Gauge Chart) to perform a measurement systems analysis (MSA) of the data.(2 pts) In the Variability Chart launch dialog specify INR as the response Y, Operator as X, Grouping, QA Samples as Parts, Sample ID, and Certified INR as the Standard. In the Report Window select the Connect Cell Means and Show Group Means options from the main menu – just as we did in the Continuous MSA notes.Comment on the Variability Chart at the top of the Report window. Does there appear to be significant operator to operator variability? Is there significant repeatability variation among the duplicate measurements taken by each operator on each sample? Do all operators seem to measure the 5 samples in the same way?
(3 pts) Select the Variance Components option from the main Report menu. Note, if you receive a Bayesian Variance Components report you can use that report or the more traditional report (the one we used in the MSA notes). Discuss the variance components report in terms of the measurement system. How much of the total variation is due to Operator? How much is due to Repeatability (within)? Do the operators seem consistent in how they measure each of the 5 samples (Operator*Sample variance)?
(3 pts) Given we have certified values for each of the QA samples; it is possible to assess test accuracy or bias. From the Gage Studies submenu select Bias Report and comment on potential measurement bias for each of the 5 certified samples. Do you think the test is accurate enough across the range of INR values used in the study? Recall, doctors consider a deviation of 0.25 to be of clinical interest.
(3 pts) From the Gage Studies submenu select Gage R&R to perform a traditional Gage R&R MSA. Use a Tolerance Interval of 0.5. From the R&R report comment on the relative contributions to measurement error of Operator, Operator*Sample, Repeatability. Which of these appears to be of most concern in terms of measurement error? Why?
(2 pts) Based on the P/T ratio in the Gage R&R report do you think this particular Pro-timer test method is capable of distinguishing a shift of 0.25 (or tolerance of 0.5) in a patient’s INR level? Why or why not?
(2 pts) Based upon the MSA you have just performed, do you think a doctor should adjust a “blood thinner” dosage if a shift of 0.25 (lower or higher) or so is observed in the patient’s latest INR test value? In other words, is this likely to be a true shift in INR or simply test noise? Explain.

Get Help Today

Struggling with this particular assignment? Learn how our team of professional writers can help you today.

Leave a Reply

Your email address will not be published. Required fields are marked *