MUST USE STATA TO OPEN ATTACHED DATA SET
1 Applied Statistics [Second Assignment. Due 07/12] 1. The latest NYC Democratic Mayoralty Primary Poll[footnoteRef:1] (released on 06/14) of 876 primary voters and a margin of error of +/- 3.8 percentage points shows that “Eric Adams (24%) leads the field of candidates among New York City likely Democratic primary voters […]. Kathryn Garcia (17%), Maya Wiley (15%), and Andrew Yang (13%) follow.” My neighbor just told me: “Too bad Adams will win, but I'm excited that Garcia will be second. She is the best!” [1: Source: WNBC/Telemundo 47/POLITICO/Marist Poll] a. What should I tell my neighbor? Why? 2. For the following “hypothetical” statements, build the null and alternative hypotheses. 1. Millennials use social media all the time; I suspect they use them at least 5 hours a day in my office. 2. Hispanic people are more likely to drive above the speed limit than African Americans. 3. People that eat junk food don’t live past 85. 4. It is impossible to find an entry-level position that pays less than 25,000 a year. 5. There is no wage gap between men and women. 3. Discuss the implications of the following situation: Suppose you are designing a new state-wide safety net policy for families that fell into poverty due to the COVID-19 pandemic. Your team collected a large and representative sample that concluded, with statistical significance, that families with two or more children earned $50 less than one-child families (yearly). Someone in your team recommended that you exclude one-child families from the new policy because of the results. 4. The average processing time of an immigration application case is 390 days, with a standard deviation of 205 days. Assuming there is a normal distribution, calculate [Excel: NORMSDIST(_)]: 1. The probability that a case is processed within a year (365 days). 2. The probability that a case is processed after two years. 3. The probability that an applicant receives a decision in between one and two years. 5. Differences between groups: Use the dataset "Patient Survival in Drug Trial" [command: sysuse cancer.dta]. 1. Do you agree with the following statement? (Show your process) "If we look at survival rates in the trial, age is such an important factor to consider." 1. Remember to check the following assumptions: normality (visually and conducting a test), equal variance. 2. Because it is a new drug they are testing, the principal investigator wants to know if results hold at a 99% confidence level. Do the results hold? 6. Differences between groups: Use the dataset “NSLW 88” [command: sysuse nlsw88.dta] a. Respond: Are unionized workers older than non-unionized? i. Remember to check the following assumptions: normality (visually and conducting a test), equal variance. 1 Applied Statistics [Second Assignment. Due 07/12] 1. The latest NYC Democratic Mayoralty Primary Poll[footnoteRef:1] (released on 06/14) of 876 primary voters and a margin of error of +/- 3.8 percentage points shows that “Eric Adams (24%) leads the field of candidates among New York City likely Democratic primary voters […]. Kathryn Garcia (17%), Maya Wiley (15%), and Andrew Yang (13%) follow.” My neighbor just told me: “Too bad Adams will win, but I'm excited that Garcia will be second. She is the best!” [1: Source: WNBC/Telemundo 47/POLITICO/Marist Poll] a. What should I tell my neighbor? Why? 2. For the following “hypothetical” statements, build the null and alternative hypotheses. 1. Millennials use social media all the time; I suspect they use them at least 5 hours a day in my office. 2. Hispanic people are more likely to drive above the speed limit than African Americans. 3. People that eat junk food don’t live past 85. 4. It is impossible to find an entry-level position that pays less than 25,000 a year. 5. There is no wage gap between men and women. 3. Discuss the implications of the following situation: Suppose you are designing a new state-wide safety net policy for families that fell into poverty due to the COVID-19 pandemic. Your team collected a large and representative sample that concluded, with statistical significance, that families with two or more children earned $50 less than one-child families (yearly). Someone in your team recommended that you exclude one-child families from the new policy because of the results. 4. The average processing time of an immigration application case is 390 days, with a standard deviation of 205 days. Assuming there is a normal distribution, calculate [Excel: NORMSDIST(_)]: 1. The probability that a case is processed within a year (365 days). 2. The probability that a case is processed after two years. 3. The probability that an applicant receives a decision in between one and two years. 5. Differences between groups: Use the dataset "Patient Survival in Drug Trial" [command: sysuse cancer.dta]. 1. Do you agree with the following statement? (Show your process) "If we look at survival rates in the trial, age is such an important factor to consider." 1. Remember to check the following assumptions: normality (visually and conducting a test), equal variance. 2. Because it is a new drug they are testing, the principal investigator wants to know if results hold at a 99% confidence level. Do the results hold? 6. Differences between groups: Use the dataset “NSLW 88” [command: sysuse nlsw88.dta] a. Respond: Are unionized workers older than non-unionized? i. Remember to check the following assumptions: normality (visually and conducting a test), equal variance.