Housing Market Analysis: Supply-Demand Dynamics a Non-Parametric Approach

Homeownership is part of the “American Dream” and a key tool for households to build wealth. However, increasing house prices have made homeownership less attainable recently. In order to determine the factors affecting home supply, we used non-parametric approaches. Some of them include the Nadaraya-Watson estimator, Local Polynomial estimator, B-spline, P-spline, and the Adapted He approach. The latter is particularly useful when dealing with outliers or non-standard conditional distributions in the data. However, when the functions of the covariates are not easily specified in a parametric manner, a nonparametric regression technique is often employed. One such technique is using B-splines, a nonparametric approach used to estimate the parameters of the unspecified functions in the model. According to the root mean square error, B-splines were identified as the appropriate model. But this model is very liable to overfitting when the number of knots is increased and also becomes less efficient in the presence of outliers, thus the need for a more robust non-parametric regression model to overcome this, the Adapted-He approach in time-varying coefficient model was applied. The estimation procedure involves minimizing the quantile loss function using an LP-Problem technique. These methods were all applied to the US housing data. The study results indicated that interest rates and consumer sentiment had positive and negative effects on the monthly supply when using all of the above-mentioned models. This means that an increase in consumer sentiment will cause an increase in demand, which, in return, will cause a decrease in supply. Whereas an increase in the interest rates of the houses will cause an increase in supply.