Spatial Dependence in the Residential Canadian Housing Market

Abstract

This paper studies the spatial dependence of residential resale housing returns in ten major Canadian Census Metropolitan areas (or CMAs) from 1992Q4 to 2012Q4 and makes the following methodological contributions. Firstly, in the context of a spatial dynamic panel data model we use grid search to derive the appropriate spatial weight matrix W among different possible specifications. We select the compound W with the minimum root mean squared error formed from geographical distances and the ten CMAs’ gross domestic product. Secondly, contrary to common practice in the literature, we decompose the impacts of explanatory variables into direct and indirect impacts and proceed to derive and plot the impulse response functions of housing returns to external shocks. The empirical results suggest that Canadian residential housing markets exhibit statistically significant spatial dependence and spatial autocorrelation and that both geographical distances and economic closeness are the dominant channels of spatial interaction. Furthermore, the special feature of the Canadian housing market is that the responses to the shocks do not spread widely across regions and that they fade fast over time.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Notes

  1. 1.

    Canada Mortgage and Housing Corporation (or CMHC) Canadian Housing Observer 2012.

  2. 2.

    Another available housing price measure is the Multiple Listing Services (MLS\(^{{\circledR }}\)) conducted by Canadian Real Estate Association (or CREA). However, the MLS\(^{{\circledR }}\) index are not quality adjusted. Holios and Pesando (1992) discussed some shortcomings of MLS\(^{{\circledR }}\) index, including mix of units sold varies over time, so that the ’quality’ of dwelling units sold is not held constant; the short-run signals regarding price movements often diverge; and the MLS index suggests a more rapid rate of price escalation.

  3. 3.

    Detailed definition of bungalow and two-story executive can be found in Glossary of Housing Types of Royal LePage House Price Survey.

  4. 4.

    See Appendix A for the detailed list of selected 10 CMAs and their geographical locations. A CMA is a larger area than a city as it also includes municipalities adjacent to the city urban core. Geographic definitions used by Royal LePage is slightly differ from those used by Statistics Canada. However, it is the closest data available.

  5. 5.

    More specifically, we use annual CMA-level household income divided by the annual national level household income, and we assume this ratio remain constant in a given year. Then, we use this ratio multiplied by the quarterly national level income to get the quarterly CMA-level household income.

  6. 6.

    In most applied spatial econometrics, the same spatial weight matrix is used in both spatial lags of dependent variable and disturbances. We tried to estimate our model with different weight matrices in spatial lags and spatial errors, yet the results did not change much. This indicates that spatial dependence of housing returns and spatial autocorrelation in disturbances comes from a similar channel.

  7. 7.

    We thank the anonymous referee for clarifying this point.

  8. 8.

    We also tried to construct economic weight matrix using the negative exponential function. However, in those cases we ran into computational problems and as such we only use the inverse distance weighting function to construct the economic weight.

  9. 9.

    The variable movi,j includes all people lived in different address 5 years before the census year, regardless of where did they moved. While the other variable in Eq. 6migi,j only counts the number of people moved between CMA i and j specifically, and it does not include the population growth from immigrants and external migrants. These two variables are different, and we think they are both important to be used to explain the spatial dependence of housing returns.

  10. 10.

    The absolute value of eigenvalues of the matrix \(\hat {\lambda }W\) are 0.7984, 0.2289, 0.1600, 0.1548, 0.1180, 0.1010, 0.0984, 0.0712, 0.05338, and 0.0147. The absolute value of eigenvalues of the matrix \(\hat {\rho }W\) are 0.9916, 0.2843, 0.1987, 0.1922, 0.1465, 0.1254, 0.1222, 0.0885, 0.0663, and 0.0183. All absolute eigenvalues are less than 1, which ensures our spatial system is stationary. Equation 21 in Appendix C shows the overall impacts of spatial interactive relations on the housing returns.

  11. 11.

    It is worth noting that the weight matrices used in spatial models are typically assumed to be exogenous. However, the exogeneity assumption may not be reasonable. Kelejian and Piras (2014) discuss an estimation method with an endogenous weight matrix. Similarly, in Case et al. (1993), many of the weight matrices used to capture economic similarities are likely to be endogenous. In our case we also use weight matrices based on economic factors, yet the finally selected W in Eq. 12 formed by geographical distances and the real GDP levels is taken to be exogenous as geographical factors and GDP levels are taken as given. In that sense, the issue of endogeneity that we face may not be as severe. Given the complexity of our approach for arriving at the final choice of the weight matrix based on a data driven grid search method, we leave any issue of endogeneity for future research.

  12. 12.

    The magnitude of one standard deviation of population growth in each CMA is listed in last column of Table 7.

References

  1. Allen, J., Amano, R., Byrneand, D.P., Gregory, A.W. (2006). Canadian city housing prices and urban market Segmentation. Bank of Canada Working Paper. Series: 2006–49.

  2. Anselin, L. (1988). Spatial Econometrics: Methods and Models. The Netherlands: Kluwer Academic Publishers, Dordrecht.

    Google Scholar 

  3. Baltagi, B.H., Song, S.H., Koh, W. (2003). Testing panel data regression models with spatial error correlation. Journal of Econometrics, 117, 123–150.

    Article  Google Scholar 

  4. Baltagi, B.H., Song, S.H., Jung, B., Koh,W. (2007). Testing panel data regression models with spatial and serial error correlation. Journal of Econometrics, 140, 5–51.

    Article  Google Scholar 

  5. Behrens, K., & Thisse, J.F. (2007). Regional economics: A new economic geography perspective. Regional Science and Urban Economics, 37(4), 457–465.

    Article  Google Scholar 

  6. Brady, R.R. (2011). Measuring the diffusion of housing prices across space and over time. Journal of Applied Econometrics, 26(2), 213–231.

    Article  Google Scholar 

  7. Breusch, T., & Pagan, A. (1980). The lagrange multiplier test and its applications to model specification in econometrics. Review of Economic Studies, 47, 239–253.

    Article  Google Scholar 

  8. Case, A.C., Rosen, H.S., Hines, J.R. (1993). Budget spillovers and fiscal policy interdependence: evidence from the States. Journal of Public Economics, 52(3), 285–307.

    Article  Google Scholar 

  9. Cliff, A.D., & Ord, J.K. (1969). The Problem of spatial autocorrelation. Papers in Regional Science 1, Studies in Regional Science, 25-55, edited by A. J Scott. London: Pion.

    Google Scholar 

  10. Cliff, A.D., & Ord, J.K. (1981). Spatial Process: Models and Applications. London: Pion.

    Google Scholar 

  11. Dolde, W., & Tirtiroglu, D. (2002). Housing price volatility changes and their effects. Real Estate Economics, 30(1), 41–66.

    Article  Google Scholar 

  12. Fotheringham, S., Charlton, M., Brunsdon, C. (1996). The geography of parameter space: an investigation of spatial non-stationarity. International Journal of Geographic Information Systems, 10, 605–627.

    Article  Google Scholar 

  13. Gallin, J. (2006). The long-run relationship between house prices and income: evidence from local housing markets. Real Estate Economics, 34(3), 417–438.

    Article  Google Scholar 

  14. Geary, R.C. (1954). The contiguity ratio and statistical mapping. The Incorporated Statistician, 5, 115–145.

    Article  Google Scholar 

  15. Getis, A., & Aldstadt, J. (2004). Constructing the spatial weights matrix using a local tatistic. Geographical Analysis, 36(2), 90–104.

    Article  Google Scholar 

  16. Glaeser, E.L., & Gyourko, J. (2006). Housing dynamics. NBER Working Papers 12787, National Bureau of Economic Research Inc.

  17. Guirguis, H.S., Giannikos, C.I., Garcia, L.G. (2007). Price and volatility spillovers between large and small Cities: a study of the Spanish market. Journal of Real Estate Portfolio Management, 13(4), 311–316.

    Google Scholar 

  18. Gupta, R., & Miller, S.M. (2012). The time-series properties of housing prices: a case study of the southern California market. Journal of Real Estate Finance and Economics, 44, 339–361.

    Article  Google Scholar 

  19. Haggett, P., Cliff, A.D., Frey, A. (1977). Location Analysis in Human Geography, 2nd edn. New York: Wiley.

    Google Scholar 

  20. Holios, A.J., & Pesando, J.E. (1992). Monitoring price behaviour in the resale housing market: a note on measurement and implications for policy. Canadian Public Policy, XVIII, 57–61.

    Google Scholar 

  21. Holly, S., Pesaran, M.H., Yamagata, T. (2010). A spatial-temporal model of house prices in the USA. Journal of Econometrics, 158(1), 160–173.

    Article  Google Scholar 

  22. Hossain, B., & Latif, E. (2009). Determinants of housing price volatility in Canada: a dynamic analysis. Applied Economics, 41, 3521–3531.

    Article  Google Scholar 

  23. Karoglou, M., Morley, B., Thomas, D. (2013). Risk and structural instability in U.S. house prices. Journal of Real Estate Finance and Economics, 46(3), 424–436.

    Article  Google Scholar 

  24. Kelejian, H.H., & Pruch, I.R. (1998). A generalized spatial two-stage least squares procedure for estimating a spatial autoregressive model with autoregressive disturbances. Journal of Real Estate Finance and Economics, 17, 99–121.

    Article  Google Scholar 

  25. Kelejian, H.H., & Piras, G. (2014). Estimation of spatial models with endogenous weighting matrices, and an application to a demand model for cigarettes. Regional Science and Urban Economics, 46, 140–149.

    Article  Google Scholar 

  26. LeSage, J.P. (2004). A family of geographically weighted regression models. In Anselin, L., Florax, R.J.G.M., & Rey, S.J. (Eds.) Advances in Spatial Econometrics: Methodology, Tools and applications (pp. 241–264). Heidelberg: Springer.

  27. LeSage, J., & Pace, R.K. (2009). Introduction to Spatial Econometrics. Boca Raton: Taylor & Francis CRC Press.

    Google Scholar 

  28. LeSage, J., & Pace, R.K. (2014). The biggest myth in spatial econometrics. The Econometrics, 2(4), 217–249.

    Article  Google Scholar 

  29. Ley, D., & Tutchener, J. (2001). Immigration, globalization and house prices in Canada’s gateway cities. Housing Studies, 16(2), 199–223.

    Article  Google Scholar 

  30. Manski, C. (1993). Identification of endogenous social effects: The reflection problem. The Review of Economic Studies, 60, 531–542.

    Article  Google Scholar 

  31. Meen, G. (1999). Regional house prices and the ripple effect: A new interpretation. Housing Studies, 4(6), 733–753.

    Article  Google Scholar 

  32. Miles, W. (2008). Volatility clustering in U.S. home prices. Journal of Real Estate Research, 30(1), 73–90.

    Google Scholar 

  33. Miller, N., & Peng, L. (2006). Exploring metropolitan housing price volatility. Journal of Real Estate Finance and Economics, 43, 5–18.

    Article  Google Scholar 

  34. Mutl, J., & Pfaermayr, M. (2011). The Hausman test in a Cli and Ord panel model. Econometrics Journal, 14, 48–76.

    Article  Google Scholar 

  35. Pesaran, M.H. (2004). General diagnostic tests for cross section dependence in panels, Cambridge Working Papers in Economics, CESIfo 1229.

  36. Pinkse, J., Slade, M.E., Brett, C. (2002). Spatial price competition: a semiparametric approach. Econometrica, 70, 1111–1153.

    Article  Google Scholar 

  37. Sun, Y. (2016). Functional-coefficient spatial autoregressive models with nonparametric spatial weights. Journal of Econometrics, 195, 134–153.

    Article  Google Scholar 

  38. Tsai, C., Chen, M., Ma, T. (2010). Modeling house price volatility states in the UK by switching ARCH models. Applied Economics, 42(9), 1145–1153.

    Article  Google Scholar 

  39. Yu, J, de Jong, R., Lee, L.F. (2008). Quasi-maximum likelihood estimators for spatial dynamic panel data with fixed effects when both n and T are large. Journal of Econometrics, 146(1), 118–134.

    Article  Google Scholar 

  40. Zhang, C., & Murayama, Y. (2000). Testing local spatial autocorrelation using k-order neighbors. Int J Geographic Information Science, 14, 681–692.

    Article  Google Scholar 

  41. Zhang, C., & Murayama, Y. (2003). Evaluation on the prominences of irregular areas based on spatial weight matrices. Geographical Review of Japan, 76A, 777–787.

    Article  Google Scholar 

  42. Zhu, B., Fuss, R., Rottke, N.B. (2013). Spatial linkages in returns and volatilities among U.S. regional housing markets. Real Estate Economics, 41(1), 9–64.

    Article  Google Scholar 

Download references

Acknowledgments

This paper is part of the Ph.D. thesis of the first author. It has been presented at the 2nd Annual Doctoral Workshop in Applied Econometrics, the 41th Annual Conference of the Eastern Economics Association, and the 49th Annual Conference of the Canadian Economics Association. We wish to thank an anonymous referee for very useful comments that helped with interpretation of our results. We also want to thank Dr. Martin Burda, Xuefeng Pan, Dr. Christos Ntantamis and participants in the conferences, for their helpful comments on earlier drafts of this paper. We wish also thank Dr. Paul Anglin and Dr. Min Seong Kim for their valuable comments. The second author would like to thank for the financial support from the Social Science and Humanities Research Council of Canada Insightful Grant 435-2016-0340.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yiguo Sun.

Appendices

Appendix

A. List of CMAs

B. Detailed Data Sources

  • Building Permits: CANSIM Table 026-0006.

  • Housing Starts: CANSIM Table 027-0052.

  • Completed: CANSIM Table 027-0060.

  • Construction Union Wage Index (UWI): Table 327-0045. The UWI data is not available for Regina from 1992Q2 to 2007 Q1, so the Prairie Region data is used for that period instead.

  • NHPI: CANSIM Table 327-0046

  • Rent index: CANSIM Table 326-0020.

  • Population and unemployment rate: CANSIM Table 282-0090 for year 1992Q2-1995Q4 and Table 282-0109 for year 1996Q1-2013Q1. Data in January and February 1996 is not available, so the data in March 1996 is used for 1996Q1 instead of quarterly average.

  • Household income: quarterly and annually national household income are from CANSIM Table 380-0083, and annual CMA-level household income is from CANSIM Table 202-0605, which is real median after-tax household income. The income data is not available for Regina from year 1992 to 1997, so the household income for province Saskatchewan is used at that period.

C. The IRF of the Shock to Housing Returns

C.1 The Derivation of the IRF of the Shock to Housing Returns

An impulse response function traces out the magnitude and duration of a variable in response to a shock. We apply this technique to our dynamic spatial panel data model to better understand the effect of shocks on housing returns over time and across spaces. From model (1)–(2), we have

$$ Y_{t}=\gamma Y_{t-1}+\lambda W_{N}Y_{t}+X_{t-1}\beta+\mu+v_{t}\tau_{N}+\left( I_{N}-\rho W_{N}\right){}^{-1}\varepsilon_{t}. $$
(15)

To simplify the notation, let INλWN = A, and INρWN = B. Rearranging (20), we have

$$ Y_{t}=A^{-1}\gamma Y_{t-1}+A^{-1}X_{t-1}\beta+A^{-1}\left( \mu+v_{t}\tau_{N}\right)+A^{-1}B^{-1}\varepsilon_{t}. $$
(16)

The instant impulse response to a one-time shock in εt of magnitude η at time t is

$$ IRF_{0}=A^{-1}B^{-1}\eta. $$
(17)

At period t + 1,

$$ Y_{t+1}=A^{-1}\gamma Y_{t}+A^{-1}X_{t}\beta+A^{-1}\left( \mu+v_{t+1}\tau_{N}\right)+A^{-1}B^{-1}\varepsilon_{t+1}. $$
(18)

If we substitute Eq. 21 into Eq. 23, we get

$$\begin{array}{@{}rcl@{}} Y_{t+1}&= & \gamma^{2}A^{-2}Y_{t-1}+\gamma A^{-2}X_{t-1}\beta+A^{-1}X_{t}\beta+\left( \gamma A^{-2}+A^{-1}\right)\mu\\ && +\gamma A^{-2}v_{t}\tau_{N}+A^{-1}v_{t+1}\tau_{N}+\gamma A^{-2}B^{-1}\varepsilon_{t}+A^{-1}B^{-1}\varepsilon_{t+1}. \end{array} $$

We assume the shock to εt does not pass on to the the variable Xs, εs and vs for st, then we hold Xs and vsunchanged for all period st. Therefore, we could clearly observe how the housing return in response to such a shock. Then, one time shock in ε at time t results

$$ Y_{t+1}=\gamma^{2}A^{-2}Y_{t-1}+\left( \gamma A^{-2}+A^{-1}\right)\left( X_{t-1}\beta+\mu+v_{t}\tau_{N}\right)+\gamma A^{-2}B^{-1}\varepsilon_{t}+A^{-1}B^{-1}\varepsilon_{t+1}. $$
(19)
Table 8 The list of the selected 10 CMAs

The corresponding impulse response function in period t + 1 is

$$ IRF_{1}=\gamma A^{-2}B^{-1}\eta. $$
(20)

Repeating this procedure we have

$$\begin{array}{@{}rcl@{}} Y_{t+2}&= & \gamma^{3}A^{-3}Y_{t-1}+\left( \gamma^{2}A^{-3}+\gamma A^{-2}+A^{-1}\right)\left( X_{t-1}\beta+\mu+v_{t}\tau_{N}\right)\\ && +\gamma^{2}A^{-3}B^{-1}\varepsilon_{t}+\gamma A^{-2}B^{-1}\varepsilon_{t+1}+A^{-1}B^{-1}\varepsilon_{t+2} \end{array} $$
$$\begin{array}{@{}rcl@{}} Y_{t+3}&= & \gamma^{4}A^{-4}Y_{t-1}+\left( \gamma^{3}A^{-4}+\gamma^{2}A^{-3}+\gamma A^{-2}+A^{-1}\right)\left( X_{t-1}\beta+\mu+v_{t}\tau_{N}\right)\\ && \gamma^{3}A^{-4}B^{-1}\varepsilon_{t}+\gamma^{2}A^{-3}B^{-1}\varepsilon_{t+1}+\gamma A^{-2}B^{-1}\varepsilon_{t+2}+A^{-1}B^{-1}\varepsilon_{t+3} \end{array} $$
$$\vdots $$
$$\begin{array}{@{}rcl@{}} Y_{t+h}&= & \gamma^{h+1}A^{-\left( h+1\right)}Y_{t-1}+\left[\gamma^{h}A^{-(h+1)}+\gamma^{h-1}A^{-h}+\cdots+\gamma A^{-2}+A^{-1}\right]\left( X_{t-1}\beta+\mu\right)\\ && +\gamma^{h}A^{-\left( h+1\right)}B^{-1}\varepsilon_{t}+\gamma^{h-1}A^{-h}B^{-1}\varepsilon_{t+1}+\cdots+\gamma A^{-2}B^{-1}\varepsilon_{t+h-1}+A^{-1}B^{-1}\varepsilon_{t+h}. \end{array} $$

The corresponding impulse response functions are

$$IRF_{2}=\gamma^{2}A^{-3}B^{-1}\eta $$
$$IRF_{3}=\gamma^{3}A^{-4}B^{-1}\eta $$
$$\vdots $$
$$ IRF_{h}=\gamma^{h}A^{-\left( h+1\right)}B^{-1}\eta $$
(21)

for h = 0, 1, 2,...T.

In order to construct the 95% confidence interval for each impulse response, we need to compute the standard error for the IRFh. The delta method is used to compute the standard error. We take the derivative of the transformed function with respect to the parameter, and multiply it by the asymptotic variance of the untransformed parameter. To be specific,

$$ Var(IRF_{h})=\left( \frac{\partial IRF_{h}}{\partial\gamma},\frac{\partial IRF_{h}}{\partial\lambda},\frac{\partial IRF_{h}}{\partial\rho}\right){\Sigma}^{-1}\left( \frac{\partial IRF_{h}}{\partial\gamma},\frac{\partial IRF_{h}}{\partial\lambda},\frac{\partial IRF_{h}}{\partial\rho}\right)^{\prime} $$
(22)

where Σ is the asymptotic variance-covariance matrix of the estimators of γ, λ and ρ. We then construct the 95% confidence interval

$$ CI=\hat{IRF_{h}}\pm1.96\cdot se(\hat{IRF_{h}}) $$
(23)

where the \(\hat {IRF_{h}}\) is the estimate of IRFh. The detailed derivatives of IRFh can be found below.

C.2 Derivatives of IRFh of the shock to housing returns

In order to construct the 95% confidence interval, we need to compute the standard errors for the estimates of IRFh, then apply the delta method. The derivatives of IRFh with respect to parameter (γ,λ,ρ) in each period, from h = 0 to h = 6, are presented below.

In period t, h = 0, we impose a shock and denote it by η, then

$$\begin{array}{@{}rcl@{}} IRF_{0}(\gamma,\lambda,\rho)&= & \left( I_{N}-\lambda W_{N}\right)^{-1}\left( I_{N}-\rho W_{N}\right)^{-1}\eta\\ &= & A^{-1}B^{-1}\eta. \end{array} $$
(24)

The derivative of IRF0 with respect to \(\left (\gamma ,\lambda ,\rho \right )\) is

$$\begin{array}{@{}rcl@{}} \frac{\partial IRF_{0}}{\partial\gamma}&= & 0;\\ \frac{\partial IRF_{0}}{\partial\lambda}&= & \left[\left( B^{-1}\eta\right)^{T}\otimes I_{N}\right]\frac{d\left[vec\left( A^{-1}\right)\right]}{d\lambda}\\ &= & \left[\left( B^{-1}\eta\right)^{T}\otimes I_{N}\right]\frac{d\left\{ vec\left[\left( A^{-1}\right)\right]\right\}} {dvec\left( A\right)}\cdot\frac{d\left[vec\left( I_{N}-\hat{\lambda}W_{N}\right)\right]}{d\lambda}\\ &= & \left[\left( B^{-1}\eta\right)^{T}\otimes I_{N}\right]\left[-\left( A^{-1}\right)^{T}\otimes A^{-1}\right]\left[-vec\left( W_{N}\right)\right]\\ &= & \left[\left( A^{-1}B^{-1}\eta\right)^{T}\otimes A^{-1}\right]vec\left( W_{N}\right);\\ \frac{\partial IRF_{0}}{\partial\rho}&= & \left( h^{T}\otimes A^{-1}\right)\cdot\frac{d\left[vec\left( B^{-1}\right)\right]}{d\rho}\\ &= & \left( \eta^{T}\otimes A^{-1}\right)\frac{d\left[vec\left( B^{-1}\right)\right]}{dvec\left( B\right)}\cdot\frac{d\left[vec\left( I_{N}-\hat{\rho}W_{N}\right)\right]}{d\rho}\\ &= & \left( \eta^{T}\otimes A^{-1}\right)\left[\left( B^{-1}\right)^{T}\otimes B^{-1}\right]vec\left( W_{N}\right)\\ &= & \left[\left( B^{-1}\eta\right)^{T}\otimes\left( A^{-1}B^{-1}\right)\right]vec\left( W_{N}\right) \end{array} $$

where “ ⊗” refers to the Kronecker product, and \(vec\left (W_{N}\right )\) is the vectorization of matrix WN and transforms WN into a column vector.

In period t + h, where h ≥ 1

$$\begin{array}{@{}rcl@{}} IRF_{h}(\gamma,\lambda,\rho)&= & \gamma\left( I_{N}-\lambda W_{N}\right)^{-(h+1)}\left( I_{N}-\rho W\right)^{-1}\eta \\ &= & \gamma A^{-(h+1)}B^{-1}\eta. \end{array} $$
(25)

For h ≥ 1, the derivative of IRFh with respect to \(\left (\gamma ,\lambda ,\rho \right )\) is

$$\begin{array}{@{}rcl@{}} \frac{\partial IRF_{h}}{\partial\gamma}&= & h\gamma^{h-1}A^{-(h + 1)}B^{-1}\eta;\\ \frac{\partial IRF_{h}}{\partial\lambda}&= & \gamma^{h}\overset{{\scriptscriptstyle h + 1}}{\underset{{\scriptscriptstyle j = 1}}{\sum}}\left[\left( A^{-(h + 2-j)}B^{-1}\eta\right)^{T}\otimes A^{-j}\right]vec\left( W_{N}\right);\\ \frac{\partial IRF_{1}}{\partial\rho}&= & \gamma^{h}\left[\left( B^{-1}\eta\right)^{T}\otimes\left( A^{-(h + 1)}B^{-1}\right)\right]vec\left( W_{N}\right). \end{array} $$

D. The IRF to a Population Growth Shock

D.1 The Derivation of IRF to the Population Growth Shock

We first need to compute the impulse response functions of a one-time shock to the explanatory variables Xt−1. From Eq. 1, we have

$$\begin{array}{@{}rcl@{}} Y_{t}&= & \gamma A^{-1}Y_{t-1}+A^{-1}X_{t-1}\beta+A^{-1}\left( \mu+v_{t}\tau_{N}\right)+A^{-1}u_{t} \end{array} $$
(26)
$$\begin{array}{@{}rcl@{}} Y_{t+1}&= & \gamma^{2}A^{-2}Y_{t-1}+\gamma A^{-2}X_{t-1}\beta+A^{-1}X_{t}\beta+\left( \gamma A^{-2}+A^{-1}\right)\mu+ \\ & &+\gamma A^{-2}v_{t}\tau_{N}+A^{-1}v_{t+1}\tau_{N}+\gamma A^{-2}u_{t}+A^{-1}u_{t+1} \end{array} $$
(27)
$$\begin{array}{@{}rcl@{}} Y_{t+2}&= & \gamma^{3}A^{-3}Y_{t-1}+\gamma^{2}A^{-3}X_{t-1}\beta+\gamma A^{-2}X_{t}\beta+A^{-1}X_{t+1}\beta \\ & &+\left( \gamma^{2}A^{-3}+\gamma A^{-2}+A^{-1}\right)\mu+\gamma^{2}A^{-3}v_{t}\tau_{N}+\gamma A^{-2}v_{t+1}\tau_{N}+A^{-1}v_{t+2}\tau_{N} \\ & &+\gamma^{2}A^{-3}u_{t}+\gamma A^{-2}u_{t+1}+A^{-1}u_{t+2} \end{array} $$
(28)
$$\begin{array}{@{}rcl@{}} &&\vdots \\ Y_{t+h}&= & \gamma^{h+1}A^{-\left( h+1\right)}Y_{t-1}+\gamma^{h}A^{-\left( h+1\right)}X_{t-1}\beta+\gamma^{h-1}A^{-h}X_{t}\beta+\cdots+\gamma A^{-2}X_{t+h-2}\beta \\ & &+A^{-1}X_{t+h-1}\beta+\left( \gamma^{h}A^{-\left( h+1\right)}+\gamma^{h-1}A^{-h}+\ldots+\gamma A^{-2}+A^{-1}\right)\mu \\ & &+\gamma^{h}A^{-\left( h+1\right)}v_{t}\tau_{N}+\gamma^{h-1}A^{-h}v_{t+1}\tau_{N}+\cdots+\gamma A^{-2}v_{t+h-1}\tau_{N}+A^{-1}v_{t+h}\tau_{N} \\ & &+\gamma^{h}A^{-\left( h+1\right)}u_{t}+\gamma^{h-1}A^{-h}u_{t+1}+\cdots+\gamma A^{-2}u_{t+h-1}+A^{-1}u_{t+h} \end{array} $$
(29)

where INλWN = A. We denote an N × 1 vector ψ to be the shock on population growth at time t − 1. βp is the coefficient in front of the population growth. Then, the corresponding impulse response functions are

$$\begin{array}{@{}rcl@{}} IRF_{0}&= & A^{-1}\psi\beta_{p} \end{array} $$
(30)
$$\begin{array}{@{}rcl@{}} IRF_{1}&= & \gamma A^{-2}\psi\beta_{p} \\ IRF_{2}&= & \gamma^{2}A^{-3}\psi\beta_{p} \\ &&\vdots\\ IRF_{h}&= & \gamma^{h}A^{-(h+1)}\psi\beta_{p}. \end{array} $$
(31)

Equation 34 is the response in quarter t, and it is also referred to as impulse response at horizon zero. We also apply the delta method and Eq. 28 to construct the 95% confidence interval for each IRF’s. The detail of derivatives that required to construct the error bound is given below.

D. 2 The Derivatives of IRF to a Population Growth Shock

In this section, we include the detailed derivatives that required by Eq. 27 to construct the 95% confidence interval of the impulse response functions. This section is similar to the previous section Appendix C.

We calculate the derivatives of IRF with respect to parameters space γ, λ and βp, where A = INλWN, βp is the parameter in front of the population growth, and ψ is an N × 1 vector denotes the shock to the population growth at horizon zero.

When h = 0, IRF0 = A−1ψβp, the derivative of IRF0 with respect to \(\left (\gamma ,\lambda ,\beta _{p}\right )\) is

$$\begin{array}{@{}rcl@{}} \frac{\partial IRF_{0}}{\partial\gamma}&= & 0;\\ \frac{\partial IRF_{0}}{\partial\lambda}&= & \left[\left( \psi\beta_{p}\right)^{T}\otimes I_{N}\right]\frac{d\left[vec\left( A^{-1}\right)\right]}{d\lambda}\\ &= & \left[\left( \psi\beta_{p}\right)^{T}\otimes I_{N}\right]\frac{d\left\{ vec\left[\left( A^{-1}\right)\right]\right\}} {dvec\left( A\right)}\frac{d\left[vec\left( I_{N}-\lambda W_{N}\right)\right]}{d\lambda}\\ &= & \left[\left( \psi\beta_{p}\right)^{T}\otimes I_{N}\right]\left[-\left( A^{-1}\right)^{T}\otimes A^{-1}\right]\left[-vec\left( W_{N}\right)\right]\\ &= & \left[\left( A^{-1}\psi\beta_{p}\right)^{T}\otimes A^{-1}\right]vec\left( W_{N}\right);\\ \frac{\partial IRF_{0}}{\partial\beta_{p}}&= & A^{-1}\psi. \end{array} $$

In period t + h, where h ≥ 1

$$IRF_{h}=\gamma^{h}A^{-(h+1)}\psi B. $$

For h ≥ 1, the derivative of IRFh with respect to \(\left (\gamma ,\lambda ,\beta _{p}\right )\) is

$$\begin{array}{@{}rcl@{}} \frac{\partial IRF_{h}}{\partial\gamma}&= & h\gamma^{h-1}A^{-(h + 1)}\psi\beta_{p};\\ \frac{\partial IRF_{h}}{\partial\lambda}&= & \gamma^{h}\overset{{\scriptscriptstyle h + 1}}{\underset{{\scriptscriptstyle j = 1}}{\sum}}\left[\left( A^{-(h + 2-j)}\psi\beta_{p}\right)^{T}\otimes A^{-j}\right]vec\left( W_{N}\right);\\ \frac{\partial IRF_{1}}{\partial\beta_{p}}&= & \gamma^{h}A^{-(h + 1)}\psi. \end{array} $$

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhang, Y., Sun, Y. & Stengos, T. Spatial Dependence in the Residential Canadian Housing Market. J Real Estate Finan Econ 58, 223–263 (2019). https://doi.org/10.1007/s11146-017-9623-2

Download citation

Keywords

  • Canadian residential resale housing returns
  • Impulse response functions
  • Spatial dependence
  • Spatial dynamic panel data models
  • Spatial weight matrix