Past Math 158 Linear Models Projects

Airline data

  • Unit: flight between 2 cities
  • Variables: ave cost, max cost, min cost, distance, % on time, yes/no major carrier, # airlines in that market, yes/no international


Baseball data

  • Unit: team
  • Variables: team name, league, year, yes/no post season, % win, team ERA, runs scored per game, team batting average


College data

  • Unit: college/university
  • Variables: student/faculty ratio, freshmen in top 10% of class, acceptance rate, alumni giving rate, geographic location, college/university, graduation rate, freshman retention rate, % of classes under 20, % of classes with 50 or more


Crime data

  • Unit: city
  • Variables: geographic location, ave Jan temp, ave June temp, # robberies per 10,000 people, # auto theft per 10,000 people, population, race breakdown, # children < 18 in jail per 10,000 people, unemployment rate


Drug Treatment data

  • Unit: individual
  • Variables: treatment status, court assignment, gender, age, race, number of prior arrests, number of prior convictions, education level, total days drug testing, total days probation, total days of treatment


Income Dynamics data

  • Unit: American family
  • Variables: age of the head of household, age of wife, number of children, age of the youngest child, family income, state of residence, gender of head of household, race of head of household, poverty level of parents during childhood


Boston house-price data

  • Unit: town outside of Boston
  • Variables: crime rate, proportion of residential land zoned for large lots, proportion of non-retail business acres per town, nitric oxide concentration, average number of rooms per dwelling, weighted distance to five Boston employment centers, pupil-teacher ratio, median value of owner-occupied homes


Movie data

  • Unit: movie within top 100 grossing 1999-2003
  • Variables: year, season, rating, genre, gender of first billed actor, star rating, domestic gross, overseas gross, number of academy award nominations, number of academy wins, opening week revenue, budget, length



Grad School data

  • Unit: MBA program
  • Variables: ave GPA, ave GMAT, acceptance rate, ave starting salary and bonus, % graduates employed at graduation, % of graduates employed three months after graduation, out-of-state tuition and fees, regional focus, part-time option, location, > 75% of students enrolled male (yes/no)


AIDS data

  • Unit: state
  • Variables: location, population, metropolitan status, most common race, AIDS case rate, most common race of AIDS cases, most common cause of HIV, education curriculum required (yes/no), total clients served by assistant program, CDC prevention funding, total Ryan White CARE Act funding


Petroleum data

  • Unit: country
  • Variables: presence of petroleum reserves, landlocked status, GDP per capita, country area, % GDP from agriculture


Assault data

  • Unit: individual
  • Variables: global self-esteem, BSI (a measure of psychological symptoms), positivity of self, positivity of others, race


Economic data:

  • Unit: country
  • Variables: economic growth rate, population growth rate, literacy rate, civil unrest (indicator), government type (categorical)