This paper studies nonstationarities in a panel of Canadian and US interest rates of different maturities and risk. We focus on methods which model the cross-sectional dependence within the panel as a linear dynamic factor model, and decompose our data into common and idiosyncratic components that we analyze in turn. Our results suggest the presence of a single nonstationary factor in our panel. Since some of the idiosyncratic components are stationary, we conclude that these series are cointegrated. Finally, the dominant factors can be interpreted as level and slope factors as in the term structure literature. Copyright © 2007 John Wiley & Sons, Ltd.