Sommereksamen 2013 Titel på kursus: Uddannelse: Semester: Statistik og evidensbaseret medicin Bacheloruddannelsen i Medicin/Medicin med industriel specialisering 2. semester Eksamensdato: 17. juni 2013 Tid: kl. 9.00-12.00 Bedømmelsesform Bestået/Ikke bestået Vigtige oplysninger: Husk at opgive studienummer ikke navn og cpr.nr. på alle ark, der skal medtages i bedømmelsen Husk at aflevere besvarelsen, også hvis du forlader eksamen, før den er slut Ordbøger er til rådighed Skriftlige hjælpemidler er tilladt Medbring jeres egen computer med SPSS eller andet statistisk software installeret Det er tilladt at skrive besvarelsen på dansk eller engelsk Ingen former for kommunikation er tilladt 1
Exam questions in Statistics and Evidence-based medicine, spring 2013 2. sem. Medis/Medicin, Modul 2.4. Statistics : ESSAY-TYPE QUESTION 1. A sample of thirteen measurements of calcium concentration has been collected. The measurements are: 28, 27, 29, 29, 30, 30, 31, 30, 33, 27, 30, 32, 31 [mmole/kg]. Questions: a) Calculate following sample characteristics: mean, median, range, variance, standard deviation and standard error of the mean; b) Is the distribution of calcium concentration normal? (How did you check that?) c) If the distribution of calcium concentration is assumed to be normal, what formula is appropriate to be used to calculate a 95% confidence interval (CI) for the population mean calcium concentration? d) Using this formula, calculate a 95% CI for the population mean calcium concentration and explain the result; e) Using a statistical software (e.g., SPSS), calculate a 95% CI for the population mean calcium concentration and explain the result; f) Are the results in (d) and (e) similar or different? Why? Max point: 18 2
ESSAY-TYPE QUESTION 2. Table below shows the ages of 9 married couples. Husband age Wife age 36 35 72 67 37 33 36 35 51 50 50 46 47 47 50 42 37 36 Questions a) Make a scatterplot of Husband age versus Wife age; b) Calculate the correlation coefficient between Husband age and Wife age; c) Comment on the nature and strength of any association between the two variables; d) Is this association statistically significant? Max point: 11 TRUE OR FALSE QUESTION 3. Indicate whether the statement is true or false. A One of assumptions of a two sample t-test is that the data is metric. B Nationality of medical students is an example of metric data. C The median is the arithmetic average of the measurements. D One of assumptions of a one sample t-test is that the data is not normally distributed. E The variance is the square root of the standard deviation. F As sample size increases, the size of the standard error of the mean decreases. G If the original units in a data set are meters, then the standard deviation of the set is expressed in meters. H Matched-pairs t-test is used, when we are interested in the difference between the means of two independent populations. Max point: 8 3
ESSAY-TYPE QUESTION 4. Suppose that a case-control study was conducted to evaluate the relationship between artificial sweeteners and bladder cancer. 6 cases and 6 controls were enrolled in the study. Among the cases, 3 had used artificial sweeteners in the past. Of the controls, 2 had used sweeteners. Questions: a) What is a case-control study? What is the difference between casecontrol studies and cohort studies? b) Identify, who were the cases and who were the controls in this study; c) Set up the two by two table for these data; d) Calculate the risk ratio (RR) for bladder cancer among those who used artificial sweeteners compared to those who did not use sweeteners. Interpret the result and make a conclusion; e)calculate the odds ratio (OR) for using sweeteners among those with bladder cancer compared to those without bladder cancer. Interpret the result and make a conclusion; f)calculate the 95% confidence interval for the OR in (e). Interpret the result and make a conclusion; g) Should the authorities base their decisions regarding the use of artificial sweeteners just on the results of this study? Max point: 26 4
ESSAY-TYPE QUESTION 5. Consider the table below. It shows the weight for 14 patients in a clinic. Test, whether the mean weight in population of patients in the clinic is equal 70 kg. Patient ID Weight [kg] 1 80 2 55 3 75 4 68 5 65 6 69 7 71 8 73 9 70 10 75 11 77 12 65 13 87 14 81 Questions: a) What test do you choose? Show, that the data satisfy the assumptions for this test; b) Formulate the appropriate null and alternative hypotheses (as a text and in mathematical terms) ; c) Perform the test in SPSS. Outline the main results (the observed difference, p-value, CI interval of the difference); d) Interpret the p-value and the CI obtained; e) What conclusion can you make based on the results of the test? Max point: 22 5
Evidens : EXTENDED MATCHING 6. Evidens Begreber: A. De epidemiologiske metoderegler B. Bias C. Statistisk usikkerhed Opgave: Vælg fra listen af begreber det, der passer bedst til hvert af de nedenstående udsagn. Skal følges for at vurdere kvaliteten af eksisterende viden (litteraturen) Påvirker validiteten Omfatter bl.a. formål/hypoteser og design Kan kun reduceres ved nøje planlægning af undersøgelse Påvirker spredningen (præcisionen) Angiver hvordan ny evidensbaseret viden frembringes Max point: 4 EXTENDED MATCHING 7. Evidens Begreber: A. Ekspert udtalelser B. Kohorde-undersøgelser C. Systematiske reviews D. Case-control undersøgelser Opgave: Vælg fra listen af begreber det, der passer bedst til hvert af de nedenstående udsagn. Indeholder al tilgængeligt evidensbaseret viden indenfor et felt Rangerer nederst i evidens hierarkiet 6
Prospektiv undersøgelse med henblik på påvisning af en kausal sammenhæng Indeholder ofte metaanalyser og dermed statistiske beregninger Retrospektiv undersøgelse med henblik på påvisning af en kausal sammenhæng Rangerer højest i evidens-hierarkiet Max point: 4 MULTIPLE CHOICE OPGAVE 8. Hvilken medicinsk database er kendt for at stille specielt høje krav til, at de epidemiologiske metoderegler er overholdt? A Signahl B Cochrane C Embase D e-medicine E Medicin.dk Max point 2 MULTIPLE CHOICE OPGAVE 9. Nedenstående udsagn angiver en række fakta omkring de epidemiologiske metoderegler, hvilket er IKKE korrekt? A Danner grundlag for bedømmelsen af kvaliteten af egne- og andres studier B Knytter epidemiologi, statistik og evidens sammen C Har fokus på at forstå og fortolke undersøgelsesresultater D Hører ind under det empirisk- analytiske forskningsparadigme E Er styret af formålet med en undersøgelse Max point 3 MULTIPLE CHOICE OPGAVE 10. Begrebet evidensbaseret viden betyder: A Tilgængelige viden af høj metodologisk kvalitet B Behandlinger baseret på ekspertviden og klinisk evidens C Ekspertviden D Viden baseret på erfaringer og gentagne forsøg E En kombination af lægens ekspertise og patientens præferencer Max point 2 7