Background: The S&P/Case-Shiller Home Price Indices are a closely watched collection of measures of changes in the value of residential housing. They show a precipitous 25% decline from a peak in mid-2006 to early 2009. The decline in house values that this represents has led to sharp increases in loan delinquencies, beginning in sub-prime mortgages and progressing to Alt-A mortgages and now credit card debt. The resulting stress on lenders will only increase as long as the decline in house prices continues.
The Case-Shiller indices are adjusted neither for inflation nor for changes in wealth, and from a statistical point of view exhibit non-stationarity. However, an adjusted series such as the ratio of a home price index to per-capita personal income could be expected to show stationary behavior, varying around a long-term mean. Statistical analysis of such a series could be used to explore questions such as for how long and to what level the price decline will continue.
Task: Identify appropriate modifications of the indices, and build statistical models to predict their future values. Develop answers to the questions of for how long and to what level the recent price declines will continue. Use conventional techniques as far as possible, and use simulations to answer questions that these techniques cannot answer.
Data Sources: The indices are published monthly by Standard & Poor's. Comparison series such as Personal Income may be found at the Federal Reserve Board's database.
