An analysis shows strong statistical correlations between the historical RevPAR growth in top 25 markets such as New York, Boston and Los Angeles.
HENDERSONVILLE, Tennessee—All markets are not created equally, or so conventional wisdom goes. And while that may hold true when examining market attributes and demand drivers, it’s not always the case when analyzing performance.
In fact, an analysis of revenue-per-available-room growth among the top 25 U.S. markets revealed strong correlation among a handful of seemingly disparate MSAs.
For those of you who might be a little rusty on statistics, correlation coefficients (or R-values) measure the strength and direction of the linear relationship between two variables. They range between -1.0 and +1.0, where:
- A value near 1.00 indicates a strong, positive correlation (e.g. When A moves up, so does B).
- A value near 0.00 indicates no correlation (e.g. When A moves up, B may move up or down or not move at all).
- A value near -1.00 indicates a strong, negative correlation (e.g. When A moves up, B moves down).
It is important to note correlation does not mean causation. Just because A and B move in the same direction, that doesn’t mean A moving up is the cause of B also moving up, and vice versa. Also, this analysis examines the historical relationships between markets. Strong or weak relationships identified will not predict future performance.
With statistics 101 out of the way, let’s dive into the data.
New York, Los Angeles and Boston posted the strongest correlation in RevPAR growth rates among the top 25 markets. These three markets had correlation coefficients of 0.70 or higher, indicating a strong relationship in historical RevPAR percent change performance. Year-over-year market RevPAR growth has moved in the same direction for these three markets 73% of the months since January 1988.
Boston and New York were the most highly correlated markets of the Top 25 (r=.79). RevPAR in these large East Coast metros moved in same direction 83% of months in this analysis.
Los Angeles was most strongly correlated with New York (r = 0.74) but also had a strong relationship with Boston (r=0.70).
Figure 1 shows RevPAR growth rates for these three gateways over the past 30 years.
While most of the top 25 markets were moderately correlated to each other with an average of 0.43, Norfolk/Virginia Beach displayed particularly weak correlation compared to all other top 25 markets.
Sixteen of the top 25 markets were most weakly correlated to Norfolk. The market had an absolute R-value of less than 0.10 with nine of the top 25 markets, indicating there is almost no statistical relationship between Norfolk’s and those markets’ RevPAR percent change performance. One possible explanation: Norfolk has a more leisure-heavy traveler mix than many of the other top 25 markets, which may create opportunities for RevPAR growth at different points in the economic cycle.
Does this mean we can completely refute the statement all markets are not created equally? The answer is no. This analysis shows that RevPAR growth between some top 25 markets moves similarly, which makes it possible for a degree of comparison.
This article represents an interpretation of data collected by STR, parent company of HNN. Please feel free to comment or contact an editor with any questions or concerns.