The overall Best State ranking from U.S. News & World Report shows how each of the 50 U.S. states ranks in 68 metrics across seven categories. The data behind the rankings were based on McKinsey & Company’s Leading States Index.
In calculating the rankings, each of the seven categories were assigned weightings based on a national survey that asked people to prioritize each subject in their state:
Note: Weights don’t add to 100 due to rounding.
The elements of the categories and the weightings assigned to each were:
Health Care
Education
Infrastructure
Crime & Corrections
Opportunity
Economy
Government
U.S. News and McKinsey created an index score for each metric for each state. In each metric, the top state based on the raw data was given 100 points and the bottom state was given 1 point. States between these were indexed proportionally. Then, we multiplied the weight for each metric by each state’s index score to calculate weighted averages. These weighted averages were then ranked 1-50 to determine the category and sub-category rankings.
For the overall rankings, U.S. News created a weighted average of the seven category rankings and multiplied each by the weight for each category, and then ranked the outcome. We chose this method for the overall ranking so that it would not be skewed by large differences in scores at a metric level.
Weights within categories and subcategories were selected in collaboration with experts based on each metric’s relative importance and breadth. For example, mortality metrics in the health care index were weighed the most heavily in that category because they encompass many factors of health in the state. For categories where there was no clear order of importance, equal weighting was used.
The Survey
For the weighting of the Best States ranking, U.S. News wanted to use an objective measure reflecting the priorities of citizens for their state governments. McKinsey conducts a citizen experience survey on a fairly regular basis which asks Americans how satisfied they are with various state government services and where they think their state governments should focus resources. Between September 28 and October 14, 2016, McKinsey surveyed 11,100 adults ages 18 and up to reach a demographically representative sample of 500 responses from 22 states, which collectively accounted for 75 percent of the U.S. population. The survey results were weighted to be representative of the country’s population across all ages, genders, ethnicities and household incomes.
The categories for the survey aligned with the questions that were asked of citizens. We based the weightings for the categories on a question that asked respondents to rank the categories, like health and education, 1-7 in order of what matters most in their satisfaction with their home states. The weights for the categories were calculated from the average rank for each among the respondents. Since the survey was completed before the finalization of the Best States rankings, survey responses for crime & corrections on this question were unavailable. That category’s weight was based on the correlation between how satisfied respondents said they were with public safety in their state and how satisfied respondents said they were with their state overall.
The Data
In order to select metrics for the project, we consulted experts in each of the categories for guidance. These are the criteria we used in choosing metrics:
These guidelines meant that some of the desired metrics were not available, such as recidivism in the criminal justice system, which is measured differently across different states. Where possible, we selected a close substitute (successful parole completions).
In developing the Best States ranking, we pulled data from the following sources:
For each set, we used the most recent data available as of Dec. 22, 2016. Because datasets have different schedules for updates, data come from different years and months. This allowed us to pull many more data points. All data will be updated again for the 2018 relaunch of Best States.
In some cases, data for certain states are missing because not all states provide data for all metrics. In other cases, especially in states with small populations, there weren’t enough people to have a statistically significant sample in a given year, which led to missing values. We omitted metrics with missing data from the calculation of rankings for those states.
Ties were rare in the dataset because we calculated scores to the maximum amount of decimal places without rounding. In some cases, where the score was from a letter grade, such as the digitization index, there were ties.
Best States didn’t rank Washington, D.C., or U.S. territories such as Puerto Rico. Data for Washington, D.C. were included for national averages.
You can see all the raw data behind the Best States ranking on the Data Explorer.