Thanksgiving Day

Thanksgiving Day Holiday Period Estimate for 2020

A frequently asked question is “How much more dangerous is travel over the Thanksgiving Day holiday?” Two aspects of this question must be considered: “Compared to what?” and “What about changes in the amount of driving?”

NSC compares the holiday to periods of similar length, specifically from 6 p.m. Wednesday to 11:59 p.m. Sunday, during the weeks immediately before and after the Thanksgiving Day weekend. This chart shows the fatality data from FARS for 1995 to 2019 for comparable weekends. The average number of traffic deaths during the Thanksgiving Day holiday period over the last six years is 4% lower than the average number of traffic deaths during the comparison periods (408 vs. 425 deaths). The difference between these two means is not statistically significant.

  • Chart
  • Data Table

Source: NSC analysis of NHTSA FARS data

NSC also compares the Thanksgiving Day holiday to other holiday periods. When comparing holiday periods of different lengths, an average fatality per day rate is used. The summer holidays tend to have higher average fatality rates per day than winter holidays; in 2018 Thanksgiving experienced the second lowest daily fatality average ahead of only Christmas.

  • Chart
  • Data Table

Source: NSC analysis of NHTSA FARS data

The second question concerns changes in the amount of travel or exposure. NSC is not aware of any data system that tracks changes in vehicle miles of travel by day of the year on a national basis. Lacking an objective measure of exposure change, NSC assumes travel is greater on holiday weekends than on non-holiday weekends. If that is in fact true, then with greater travel and fewer deaths, the risk of dying in a traffic crash during the Thanksgiving Day holiday period is less than comparable non-holiday periods.

Estimate methods

The objective is to estimate the number of deaths that will occur in traffic crashes during the Thanksgiving Day holiday period based on data available several weeks before the holiday. The estimate developed by NSC includes all traffic deaths from crashes during the holiday period.

The general procedure involves three steps. First, historical data is used to determine the average fraction that holiday fatalities are of the total motor-vehicle deaths for the month. Second, total traffic deaths for the coming month in which the holiday falls are estimated using a time series forecasting model. Third, the projected total for the month is multiplied by the fraction to obtain the holiday estimate.

Holiday as percent of monthly fatalities: Total November motor-vehicle deaths are calculated using the latest six years of final data available from the National Center for Health Statistics. Traffic fatality estimates for the Thanksgiving Day period are calculated using data from NHTSA FARS.

The table shows total motor-vehicle fatalities for November and traffic fatalities from crashes that occurred during the holiday period. From 2013 to 2018, fatalities from crashes during the Thanksgiving Day holiday period averaged 12.46% of the total fatalities in November.

Traffic deaths during the Thanksgiving holiday period as a percent of total motor-vehicle deaths in November

Year November Thanksgiving Period Percent
2013 3,060 360 11.76%
2014 3,175 403 12.69%
2015 3,159 392 12.41%
2016 3,535 439 12.42%
2017 3,408 470 13.79%
2018 3,300 385 11.67%
6-year average 3,273 408 12.46%

Source: NCHS and NHTSA FARS data

A time series model was developed to forecast an estimate of total traffic deaths for November 2020. An exponential smoothing model with seasonality was constructed based on monthly traffic deaths recorded  through September 2020. This model was chosen because of the seasonal pattern in traffic deaths. The model was developed using Tableau 2020.3. The model forecasts total traffic fatalities for November 2020 to be 3,894. Multiplying the projected total fatalities by the fraction obtained in the first step gives an estimate of 485 traffic fatalities from crashes during the holiday period.

The 90% confidence interval for the estimate of total November motor-vehicle deaths is 3,214 to 4,574. If we assume the fraction of November deaths that occur during the Thanksgiving holiday period is normally distributed, then the 90% confidence interval for that fraction is 11.82% to 13.09%. Combining these two estimates gives the confidence interval for the Thanksgiving holiday period estimate: 380 to 599 traffic deaths.