Homework 01

Youth Tobacco Survey

The National Youth Tobacco Survey is a federally-funded survey to assess tobacco usage in youth. It has done this since 1999 using a survey given to middle and high school students across the country with a rather large number of questions. Some of the questions have changed over the years, but they are generally stable. It is a stratified survey - there’s a lot going into the survey design that we won’t get into here.

The raw data from past years until 2019 are available (for now) at this link. The data are not harmonized: to some extent, different formats are available for different years. Your job will be to extract some summary statistics from a few particular years. Which years depends on the first letter of your last name:

• A: 1999 and 2000
• B-C: 2002 and 2004
• D: 2006 and 2009
• E-I: 2011 and 2012
• J-L: 2013 and 2014
• M-P: 2015, 2016, and 2017
• Q-Z: 2018 and 2019

You should download the SAS version of the datasets for your years and extract from the datasets the following statistics, for each combination of age and sex, in each year:

• n: sample size (i.e., number of students in this combination of age, sex, and year)
• p_cig: percent of students who report having ever tried a cigarette
• p_vape: percent of students who report having ever tried an e-cigarette
• first_age: mean reported age at which students first smoked, of those who have reported smoking
• num_cigs: mean number of cigarettes smoked in the past 30 days, of those who have reported smoking
• p_will_smoke: percent of students who say they will smoke a cigarette in the next year
• p_harmful: percent of students who say that they think the smoke from other people’s cigarettes is harmful to them

You may have missing data for some of these. In particular, please include NAs in the age and sex columns, so that for instance the n column will tell us how many people had missing data for age. (To do this, the dropna argument to groupby may be useful.)

Assignment: You should upload to Canvas two things:

• a csv file with columns for year, age, sex, and the nine variables above
• a self-contained ipynb document that briefly describes the data and how you produced the CSV file

The ipynb report should be readable: it should have markdown cells that describe what’s happening, that are formatted in a readable way. The report should contain:

• an introduction describing the data: how it was collected, what it was collected for, and where it was downloaded from
• a precise description of each of the variables above, and how it was extracted from the dataset
• a conclusion giving your thoughts on how well this data describes the quantities we’re trying to measure

Furthermore, the ipynb document should produce the csv file if evaluated in a folder containing the SAS data downloaded from this link. (The ipynb document should not actually download the data.)