Assignment # 1 Biostastics

Assignment # 1 1. Which of the following is least likely to be considered an ordinal variable during analysis? A) Education level (Primary school, High school, Bachelor’s, Master’s, Phd/Md/Jd) B) BMI category (Underweight, Normal, Overweight, Obese) C) BMI (kg/m 2 ) D) Age divided into quartiles (<25 th Percentile, 25-50 th Percentile, 50-75 th percentile, >75 th percentile) 2. Which of the following is not a main goal of biostatistics in research practice? A) Improve the intellectual content of data reported from a trial/study. B) Rely on statistical tests to assess validity of a study. C) Report only those results which indicate influential observations. D) Organize data into understandable forms. 3. Suppose a researcher conducts an analysis of the relationship between cardiovascular disease and type II diabetes. The basic summary of the findings are presented in the following table. Pati ent BMI (kg/m 2 ) Hypertensi on (Y/N) Diabet es Type II (Y/N) Smoking status (Never, Quit, Social, Current) Educat ion Status (<High , High, >High) Alcoh ol (>2 drinks a day? Y/N) Religious Background (Catholic, Jewish, Muslim, Other) Ethnicity (AA, W, A, H, Other) A 27 N N Current <High Y Catholic AA B 34 Y Y Never >High Y Other A C 21 N N Quit High Y Other W D 28 Y N Social >High N Muslim W E 36 Y Y Current <High Y Jewish W A) Describe the following in reference to their status as a variable, observation, or value: column 3, row 5, column 3/row 2, column 9.  Column 5 is the variable in the dataset, stating the smoking status of different patients.  Column 3 is the variable in the data set, stating whether the patient has hypertension or not.  Row 5 is the value in the dataset, which states the value observed in patient E of different variables.  Column 3/Row 2 is an observation, which is an observation of the variable (hypertension) in that value (patient B).  Column 9 is the variable in the dataset, stating the Ethnicity of different values (patients).

B) Are any of the variables included in the study ordinal? If so, identify the ordinal variables.  In this dataset, Smoking status and education status variables are ordinal. The reason for this is that the patients can be ordered with respect to their education status as low to high. 4. Suppose a researcher conducts an experiment to assess the measuring capabilities of a new device aimed at detecting the boiling point of a chemical. The chemical has a known boiling point of 120 degrees Fahrenheit. His measurement device is tested 10 times, and results in the following measurements for boiling point. What can we say about the device with regard to its precision, accuracy, and potential bias?  The accuracy of the device is determined by how close its measurements are to the known value of 120 degrees Fahrenheit. The precision is determined by how close the measurements are to each other. Any potential bias could be traced back to either the device always over- or under-estimating, or to some systematic error in the measurement process. Measuremen t Boiling Point (degrees Fahrenheit) 1 129 2 137 3 136 4 141 5 139 6 142 7 136 8 127 9 143 10 123 5. Suppose a researcher wants to observe the relationship between BMI (kg/m 2 ) and hypertension (Y/N) in a group of men aged 50-65. In order to more accurately assess the relationship, she collects relevant information on annual income ($/year), hours of sleep each night (#hours/night), calorie consumption per day (#calories/day), family history of hypertension (Y/N), and depression (Indexed score 1-7). Classify each of the variables under investigation as categorical, quantitative, or ordinal.  Annual income: Quantitative  Hours of sleep each night: Quantitative.  Calories consumption per day: Quantitative  Family history of hypertension: Categorical  Depression index: Ordinal 6. A surveyor decides to sample students randomly from a classroom in order to get information about teacher satisfaction. There are 29 students in the class, and the surveyor has randomly

surveys. Use the following excerpt from a random number table to select the 3 physicians. Describe your methodology. 643872 059431 984367 020684  Select the first 2 digits of each of the random numbers, we get 64, 05, 98, 02 in which 05 and 02 lies from 1 to 15. Choose those 2 members. Select the 2 nd  and 3 rd  digits of each random number, so we get 43, 59, 84, and 20 in which no number lies from 1 to 15. Select the 3 rd and 4 th  digits of each random number, so we get 38,94,43,06 in which 06 lies from 1 to 15. Choose that number. Thus, we obtain the random numbers 02, 05, and 06. Therefore, we pick 2 nd , 5 th,  and 6 th  doctors. 11. Suppose that six individuals are interested in taking part in a study relating BMI to a number of health outcomes. The following 6 numbers represent the individuals’ BMI (kg/m 2 ). 25.78 21.06 36.54 29.51 18.96 34.05 A) What is the mean and median of the individuals’ BMIs?  The mean is 26.9833 and the median is 25.645. B) Suppose that a BMI above 30 is considered obese. What is the relative frequency of obesity in this group?  The relative frequency is 33.33% 12. The following measurements represent the systolic and diastolic blood pressures (mm HG) for a group of individuals awaiting confirmation for enrollment in a study investigating the efficacy of a new anti-hypertensive medication. SYSB P DIASB P 118 73 132 81 147 87 145 91 129 73 126 81 132 83 156 97 164 102 162 101

167 103 121 78 A) Create a stem-and-leaf plot for both systolic and diastolic blood pressure.  Systolic blood pressure is arranged in ascending order: 118, 121, 126, 129, 132, 132, 145, 147, 156, 162, 164, 167. Stem Leaf 11 8 12 1 6 9 13 2 2 14 5 7 15 6 16 2 4 7 Key 15 | 6 = 156  Diastolic blood pressure is arranged in ascending order: 73, 73, 78, 81, 81, 83, 87, 91, 97, 101, 102, 103. Stem Leaf 7 3 3 8 8 1 1 3 7 9 1 7 10 1 2 3 Key 10 | 1 = 101