1# RECORD f2f2e8d4e0c68be7054271b21b3018d65c7e131c2# TITLE: THE CALCULATION OF REGIONAL INDEX OF DWELLING PRICES IN CROATIA3# YEAR: 2020.0 VENUE: Proceedings of the 14th Economics & Finance Conference, Lisbon DOI: 10.20472/efc.2020.014.0134# AUTHORS: Tanja Slišković; Tomislav Sekur5# PAGES: 23 CANDIDATE TABLE PAGES (1-based): [19, 20]6# ABSTRACT: : In the existing literature in the field of housing economics, great attention has been paid to modeling housing prices. Residential property prices are generally very important indicator as they may indicate developments in the local economy. Moreover, many existing research have proven that there is a strong interdependence of the movement of housing prices with economic developments. Therefore, different market participants (home owners, potential buyers, lessors, tenants etc.), as well as subjects from broader economic environment (banks, local government, researchers etc.) are interested in trends on housing market, and in particular in housing prices. For that reason, constant improvement of housing prices statistics is very important for all mentioned entities. In Croatia, the issue of housing prices has become topical in the last 15 years due to the turbulent developments in the domestic housing market. Generally, the indicator which is most available to the general public is average price which is published by real estate agencies and advertisers. Such indicator fails to reflect real prices movements since it encompasses the difference in quality of the offered/sold housing units on the market. The more reliable indicator would be one that is “cleared” form the impact that qualitative characteristics of the housing unit have on its price. The most commonly used method for constructing such price indicators is hedonic approach. Hedonic indices provide information about real change in the price between two points of time. The methodology of calculation hedonic housing price index in Croatia has advanced significantly over the last 12 years. In this research we use hedonic model approach to calculate the index of dwelling prices for Croatia, as well as for four regions (The City of Zagreb, Middle and South Adriatic, Istria and North Adriatic and the region Other). The variables which are included in the model are price of the dwelling, location, floor area, number of rooms, the construction year and time of sale. Two different indices based on asked and realized prices are calculated within this research. The comparison between calculated indices shows that there are large price differences between geographically different Croatian dwelling markets. Acknowledgment: This work has been supported by the Croatian Science Foundation under the project no. 6785.789===== PAGE 1 (score 7, numeric-paren 0, table-words 0, var-words 7) =====101128 September 2020, 14th Economics & Finance Virtual Conference, Lisbon12ISBN 978-80-7668-002-9, IISES13DOI: 10.20472/EFC.2020.014.01314TAMARA SLIŠKOVIĆ15Faculty of Economics and Business, University of Zagreb, Croatia16TOMISLAV SEKUR17Faculty of Economics and Business, University of Zagreb, Croatia18THE CALCULATION OF REGIONAL INDEX OF DWELLING PRICES IN19CROATIA20Abstract:21In the existing literature in the field of housing economics, great attention has been paid to modeling22housing prices. Residential property prices are generally very important indicator as they may23indicate developments in the local economy. Moreover, many existing research have proven that24there is a strong interdependence of the movement of housing prices with economic developments.25Therefore, different market participants (home owners, potential buyers, lessors, tenants etc.), as26well as subjects from broader economic environment (banks, local government, researchers etc.) are27interested in trends on housing market, and in particular in housing prices. For that reason, constant28improvement of housing prices statistics is very important for all mentioned entities.29In Croatia, the issue of housing prices has become topical in the last 15 years due to the turbulent30developments in the domestic housing market. Generally, the indicator which is most available to31the general public is average price which is published by real estate agencies and advertisers. Such32indicator fails to reflect real prices movements since it encompasses the difference in quality of the33offered/sold housing units on the market. The more reliable indicator would be one that is “cleared”34form the impact that qualitative characteristics of the housing unit have on its price. The most35commonly used method for constructing such price indicators is hedonic approach. Hedonic indices36provide information about real change in the price between two points of time. The methodology of37calculation hedonic housing price index in Croatia has advanced significantly over the last 12 years.38In this research we use hedonic model approach to calculate the index of dwelling prices for Croatia,39as well as for four regions (The City of Zagreb, Middle and South Adriatic, Istria and North Adriatic40and the region Other). The variables which are included in the model are price of the dwelling,41location, floor area, number of rooms, the construction year and time of sale. Two different indices42based on asked and realized prices are calculated within this research. The comparison between43calculated indices shows that there are large price differences between geographically different44Croatian dwelling markets.45Acknowledgment: This work has been supported by the Croatian Science Foundation under the46project no. 6785.47Keywords:48Housing Price Index, Dwelling, Hedonic Estimation, Multiple Regression Analysis, Croatian Housing49Market50JEL Classification: R21, R31, O1851134525354===== PAGE 19 (score 39, numeric-paren 0, table-words 12, var-words 2) =====5556Appendix 57 58Table 9:The estimation of the hedonic model of asked prices in Zagreb 59Dependent Variable: LOG(P1) 60 61 62Method: Least Squares 63 64 65Date: 08/30/20 Time: 00:15 66 67 68Sample: 1 3337 69 70 71 72Included observations: 3219 73 74 75White heteroskedasticity-consistent standard errors & covariance 76Variable 77Coefficient Std. Error 78t-Statistic 79Prob. 80C 817.706989 0.017256 82446.6207 830.0000 84DCRNOMEREC 85-0.192300 0.017415 -11.04192 860.0000 87DDUBRAVA 88-0.377987 0.019585 -19.29949 890.0000 90DMAKSIMIR 91-0.096760 0.018481 -5.235652 920.0000 93DMEDVESCAK 940.055555 0.023387 952.375410 960.0176 97DNZISTOK 98-0.418401 0.017952 -23.30669 990.0000 100DNZZAPAD 101-0.313912 0.017758 -17.67760 1020.0000 103DPESCENICA 104-0.251558 0.016708 -15.05572 1050.0000 106DPODSLJEME 107-0.146101 0.021798 -6.702402 1080.0000 109DTRESNJEVKAJUG 110-0.249923 0.016653 -15.00791 1110.0000 112DTRESNJEVKASJEVER -0.252768 0.016343 -15.46675 1130.0000 114DTRNJE 115-0.153101 0.019373 -7.902877 1160.0000 117DZAPAD 118-0.368335 0.015318 -24.04536 1190.0000 120DOSTALO 121-0.649177 0.022750 -28.53489 1220.0000 123M2 124-2.91E-07 3.70E-07 -0.785351 1250.4323 126ROOMS 1270.007505 0.003754 1281.999280 1290.0457 130NEWBUILT 1310.099279 0.007989 13212.42750 1330.0000 134Y2011 135-0.043895 0.009690 -4.529957 1360.0000 137Y2012 138-0.061058 0.013966 -4.371788 1390.0000 140Y2013 141-0.158550 0.011234 -14.11381 1420.0000 143Y2014 144-0.205981 0.013525 -15.22945 1450.0000 146Y2015 147-0.220215 0.018519 -11.89116 1480.0000 149Y2016 150-0.266672 0.017488 -15.24890 1510.0000 152Y2017 153-0.191486 0.025517 -7.504326 1540.0000 155Y2018 156-0.106877 0.032034 -3.336331 1570.0009 158Y2019 159-0.006022 0.043527 -0.138343 1600.8900 161R-squared 1620.436415 Mean dependent var 7.449059 163Adjusted R-squared 1640.432002 S.D. dependent var 0.261592 165S.E. of regression 1660.197151 Akaike info criterion -0.401652 167Sum squared resid 168124.1069 Schwarz criterion 169-0.352569 170Log likelihood 171672.4583 Hannan-Quinn criter. -0.384060 172F-statistic 17398.90049 Durbin-Watson stat 1741.656141 175Prob(F-statistic) 1760.000000 177 178 179 180 181Table 10:The estimation of the hedonic model of realized prices in Zagreb 182Dependent Variable: LOG(P2) 183 184 185Method: Least Squares 186 187 188Date: 08/27/20 Time: 15:10 189 190 191Sample: 1 3337 192 193 194 195Included observations: 2165 196 197 198White heteroskedasticity-consistent standard errors & covariance 199Variable 200Coefficient Std. Error 201t-Statistic 202Prob. 203C 2047.623342 0.020539 205371.1680 2060.0000 207DCRNOMEREC 208-0.195300 0.022228 -8.786229 2090.0000 210DDUBRAVA 211-0.361379 0.022825 -15.83260 2120.0000 213DMAKSIMIR 214-0.120617 0.023352 -5.165284 2150.0000 21628 September 2020, 14th Economics & Finance Virtual Conference, Lisbon217ISBN 978-80-7668-002-9, IISES218152219220221===== PAGE 20 (score 37, numeric-paren 0, table-words 9, var-words 2) =====222223DMEDVESCAK 2240.003451 0.028025 2250.123140 2260.9020 227DNZISTOK 228-0.396463 0.021462 -18.47240 2290.0000 230DNZZAPAD 231-0.372616 0.023762 -15.68091 2320.0000 233DPESCENICA 234-0.236935 0.022053 -10.74384 2350.0000 236DPODSLJEME 237-0.177905 0.024790 -7.176523 2380.0000 239DTRESNJEVKAJUG 240-0.213640 0.019579 -10.91145 2410.0000 242DTRESNJEVKASJEVER -0.242985 0.019835 -12.25032 2430.0000 244DTRNJE 245-0.146050 0.023029 -6.342120 2460.0000 247DZAPAD 248-0.355352 0.019206 -18.50261 2490.0000 250DOSTALO 251-0.630402 0.039632 -15.90634 2520.0000 253M2 254-8.16E-07 3.10E-07 -2.628739 2550.0086 256ROOMS 2570.001888 0.004493 2580.420138 2590.6744 260NEWBUILT 2610.105327 0.010633 2629.905290 2630.0000 264Y2011 265-0.053690 0.010777 -4.981859 2660.0000 267Y2012 268-0.058429 0.016597 -3.520490 2690.0004 270Y2013 271-0.192586 0.019340 -9.958040 2720.0000 273Y2014 274-0.198033 0.013706 -14.44818 2750.0000 276Y2015 277-0.195098 0.018972 -10.28352 2780.0000 279Y2016 280-0.217193 0.018910 -11.48542 2810.0000 282Y2017 283-0.118972 0.025440 -4.676569 2840.0000 285Y2018 286-0.050125 0.033336 -1.503644 2870.1328 288Y2019 2890.045607 0.042373 2901.076311 2910.2819 292R-squared 2930.385131 Mean dependent var 7.347311 294Adjusted R-squared 2950.377944 S.D. dependent var 0.256927 296S.E. of regression 2970.202640 Akaike info criterion -0.342835 298Sum squared resid 29987.83365 Schwarz criterion 300-0.274621 301Log likelihood 302397.1193 Hannan-Quinn criter. -0.317889 303F-statistic 30453.59151 Durbin-Watson stat 3051.802330 306Prob(F-statistic) 3070.000000 308 309 310 311 312Table 11: The estimation of the hedonic model of asked prices in Middle and South Adriatic 313Dependent Variable: LOG(P1) 314 315 316Method: Least Squares 317 318 319Date: 08/30/20 Time: 01:16 320 321 322Sample: 1 764 323 324 325 326Included observations: 760 327 328 329White heteroskedasticity-consistent standard errors & covariance 330Variable 331Coefficient Std. Error 332t-Statistic 333Prob. 334C 3357.727209 0.041317 336187.0236 3370.0000 338DUBNER 3390.128713 0.030430 3404.229751 3410.0000 342SIBKNIN 343-0.299180 0.033002 -9.065405 3440.0000 345ZAD 346-0.218092 0.028281 -7.711500 3470.0000 348M2 349-0.001484 0.000729 -2.034951 3500.0422 351ROOMS 3520.026734 0.017047 3531.568189 3540.1173 355NEWBUILT 3560.097784 0.026151 3573.739135 3580.0002 359Y2011 360-0.059602 0.037582 -1.585942 3610.1132 362Y2012 363-0.105214 0.035846 -2.935163 3640.0034 365Y2013 366-0.215053 0.037513 -5.732712 3670.0000 368Y2014 369-0.175157 0.038453 -4.555087 3700.0000 371Y2015 372-0.255112 0.067164 -3.798320 3730.0002 374Y2016 375-0.078141 0.037563 -2.080287 3760.0378 377Y2017 378-0.094542 0.047668 -1.983357 3790.0477 380Y2018 381-0.007452 0.095247 -0.078238 3820.9377 383Y2019 384-0.396220 0.162145 -2.443609 3850.0148 386R-squared 3870.262737 Mean dependent var 7.521154 388Adjusted R-squared 3890.247873 S.D. dependent var 0.311264 390S.E. of regression 3910.269945 Akaike info criterion 0.239629 392Sum squared resid 39354.21538 Schwarz criterion 3940.337172 39528 September 2020, 14th Economics & Finance Virtual Conference, Lisbon396ISBN 978-80-7668-002-9, IISES397153398399400===== PAGE 21 (score 38, numeric-paren 0, table-words 12, var-words 1) =====401402Log likelihood 403-75.05883 Hannan-Quinn criter. 0.277191 404F-statistic 40517.67585 Durbin-Watson stat 4061.839914 407Prob(F-statistic) 4080.000000 409 410 411 412 413Table 12: The estimation of the hedonic model of realized prices in Middle and South Adriatic 414Dependent Variable: LOG(P2) 415 416 417Method: Least Squares 418 419 420Date: 08/30/20 Time: 01:21 421 422 423Sample: 1 764 424 425 426 427Included observations: 760 428 429 430Variable 431Coefficient Std. Error 432t-Statistic 433Prob. 434C 4357.762938 0.071034 436109.2849 4370.0000 438DUBNER 4390.120050 0.042691 4402.812087 4410.0051 442SIBKNIN 443-0.337109 0.059068 -5.707172 4440.0000 445ZAD 446-0.315614 0.050880 -6.203091 4470.0000 448M2 449-0.001967 0.000884 -2.225607 4500.0263 451ROOMS 4520.010474 0.020836 4530.502682 4540.6153 455NEWBUILT 4560.074622 0.049487 4571.507921 4580.1320 459Y2011 460-0.030996 0.071972 -0.430670 4610.6668 462Y2012 463-0.178715 0.062808 -2.845430 4640.0046 465Y2013 466-0.258386 0.063389 -4.076213 4670.0001 468Y2014 469-0.221898 0.066987 -3.312550 4700.0010 471Y2015 472-0.262983 0.092377 -2.846845 4730.0045 474Y2016 475-0.077674 0.074019 -1.049381 4760.2943 477Y2017 478-0.083912 0.079037 -1.061678 4790.2887 480Y2018 481-0.009276 0.150266 -0.061731 4820.9508 483Y2019 484-0.379294 0.258008 -1.470088 4850.1420 486R-squared 4870.146218 Mean dependent var 7.433601 488Adjusted R-squared 0.129004 S.D. dependent var 0.466968 489S.E. of regression 4900.435808 Akaike info criterion 1.197599 491Sum squared resid 141.3070 Schwarz criterion 4921.295142 493Log likelihood 494-439.0875 Hannan-Quinn criter. 1.235161 495F-statistic 4968.494439 Durbin-Watson stat 1.907842 497Prob(F-statistic) 4980.000000 499 500 501 502 503Table 13:The estimation of the hedonic model of asked prices in Istria and North Adriatic 504Dependent Variable: LOG(P1) 505 506 507Method: Least Squares 508 509 510Date: 08/30/20 Time: 01:34 511 512 513Sample: 1 371 514 515 516 517Included observations: 371 518 519 520White heteroskedasticity-consistent standard errors & covariance 521Variable 522Coefficient Std. Error 523t-Statistic 524Prob. 525C 5267.638522 0.058302 527131.0168 5280.0000 529LICSENJ 530-0.486551 0.069408 -7.010057 5310.0000 532PRIMGOR 5330.023283 0.071772 5340.324407 5350.7458 536M2 537-0.000919 0.000506 -1.815385 5380.0703 539ROOMS 540-0.034939 0.023296 -1.499773 5410.1346 542NEWBUILT 5430.175797 0.042835 5444.104006 5450.0001 546Y2011 5470.010525 0.071917 5480.146351 5490.8837 550Y2012 551-0.242294 0.084286 -2.874677 5520.0043 553Y2013 554-0.309512 0.064353 -4.809625 5550.0000 556Y2014 557-0.161151 0.047011 -3.427920 5580.0007 559Y2015 560-0.245795 0.070573 -3.482869 5610.0006 562Y2016 563-0.376120 0.059516 -6.319657 5640.0000 565Y2017 566-0.089088 0.093580 -0.952002 5670.3417 56828 September 2020, 14th Economics & Finance Virtual Conference, Lisbon569ISBN 978-80-7668-002-9, IISES570154571