Why residuals can be useful in real estate valuation

(1)

1

WHY

RESIDUAL

S

CAN BE USEFUL

IN REAL ESTATE VALUATION

Author: dr eng. Małgorzata Renigier - Biłozor E-mail: malgorzata.renigier@uwm.edu.pl

DELFT 2007

Department of Real Estate Management

and Regional Development

(2)

2

Residuals as a simplified representative of stochastic factors exerting influence on real estate value

(

i

)

i

y

f

x

e

=

−

,

β

Empirical value Value from a model

RESIDUALS

error in statistical analyses

unpredictable of the systems reactions

(evidence of random processes and uncertainty)

INTERPRETATION of RESIDUALS

(3)

3

Reasons for developing different method

for mass appraisal of real estate

not only the causal-effect of dependence on the market low predictability of the reliable real estate value

the growth of interest in the mass appraisal of real estate in Poland huge changes inn the real estate market in Poland

failure in the use of the linear regression (classical method)

government - studies on the mass appraisal for tax load aims

FIRST THOUGHT about APPLICATION of RESIDUALS

(4)

100,0 120,0 140,0 0,0 20,0 40,0 60,0 80,0 Denmark Luxemburg Spai n Sweden UK. _Italy Netherl a nds German y

Austria France _Finland Irel

and

Malta

Belgium _Slovenia

Czech.R

ep.

Portugal _Hungary Estonia Greece Slovaki

a Liithuani a Latvi a Poland

average area of flats area of flats per person

(5)

0 5 000 10 000 15 000 20 000 25 000 30 000 35 000 40 000 199 6 199 7 199 8 199 9 200 0 200 1 200 2 200 3 200 4 200 5 Denmark Netherlands Ireland UK Luxembourg Sw eden Germany Finland Spain 0 1 000 2 000 3 000 4 000 5 000 6 000 7 000 8 000 9 000 10 000 199 6 199 7 199 8 199 9 200 0 200 1 200 2 200 3 200 4 200 5 Belgium France Portugal Austria Italy Greece Malta Cyprus 0 250 500 750 1 000 1 250 1 500 1 750 2 000 199 6 199 7 199 8 199 9 200 0 200 1 200 2 200 3 200 4 200 5 Estonia Latvia Hungary Lithuania Slovenia Czech Rep. Slovakia Poland ABOVE 10.000 € 2.000 - 10.000 € BELOW 2.000 €

(6)

0 Dolno śl ąskie Kujawsko-pom or.

Lubelskie Lubuskie Łódzkie

Ma łopolskie Mazowieckie Opolskie Podkarpackie Podlaskie _Pom orskie Ślą skie Ś wi ętokrzyskie Warm.-mazurskie Wielkopol skie Zachodniopom or.

dec. 2002 dec. 2003 dec 2004 dec. 2005 dec. 2006

THE PRICES OF FLATS ON THE SECONDARY MARKET

(7)

0 Dolno śl ąskie Kujawsko- pom or. Lubelskie Lubuskie Ł ódzkie Ma łopolskie Mazowieckie Opolskie Podkarpackie Podlaskie _Pom orskie _Śląskie Ś wi ętokrzyskie Warm.-mazurskie Wielkopol skie Zachodniopom or.

Dec. 2005 Mar. 2006 Jul. 2006 Sep. 2006 Dec. 2006 Mar 2007

(8)

Gorzów Wlkp.

Dec. 2005 Mar 2006 Jul. 2006 Oct. 2006 Dec. 2006

0 Wroc ław Bydgoszcz Toru ń Lublin Zi elona Góra Ł ód ź Kraków Warszawa Opole Rzeszów _Bia łystok _Gda ńsk Katowic e Kielc e Olsztyn Pozna ń Szczecin Mar 2007

(9)

average wages 2006 0 Gorzów Wielk. Wroc ław Bydgoszcz Toru ń Lublin Zielona Góra Łód ź Krakó w Warsza wa Opole Rze szó w Bia łystok Gda ńsk Katowice Kielc e Olsztyn _Pozna ń Sz cz ec in

prices of flats mar 2006 prices of flats mar 2007

AVERAGE WAGES AND PRICES OF FLATS ON THE SECONDARY MARKET

(10)

0,0 0,2 0,4 0,6 0,8 1,0 1,2 1,4 1,6 1,8 Wr o cł aw B yd g o szcz To ru ń Lubl in Go rz ó w W ie lk . Z iel ona G ó ra Ł ód ź K rak ów Wa rsza w a Op o le R ze szó w Bia łyst o k Gd a ń sk Ka to w ic e Kie lc e O lszt yn Po zn a ń S zcze ci n mar-06 mar-07

THE AREA OF THE FLAT, WHAT CAN BE PURCHASED FOR

(11)

11

THE FORM OF THE RESIDUALS DEVELOPMENT FOR USES IN THE VALUATION OF REAL ESTATE

THE RESIDUALS

Full Partial Full

(

i i

)

i i

y

f

x

e

=

−

,

β

(

)

(

)

(

)

∑ ∑ ∑ ∑ ∑ = = = = = + + + + + + + + + + + + = odlK odlC odlH atrL atrW m m m m m m m m m E W K l l l l l l l PZP Ud DD T G data k k k k k j UT j j i front gleb pow i i x d x c x b x a x c x b x a x b x a x a x a a y , , , , 4 3 2 , , 3 2 , , , , , 2 , , log ˆ -90 -80 -70 -60 -50 -40 -30 -20 -10 0 10 20 30 40 50 60 70 80 90 100

Graphical form – maps Numerical form – the geostatistical model

(12)

12

Podlesna

Nad Jeziorem Dlugim

Dajtki Kortowo Likusy Brzeziny Jaroty Pieczewo Mazurskie Pojezierze Podgrodzie Lupsztych Gutkowo Sródmiescie -80 -70 -60 -50 -40 -30 -20 -10 0 10 20 30 40 50 60 70 80 90 100 Podlesna

Nad Jeziorem Dlugim

Dajtki Kortowo Likusy Brzeziny Jaroty Pieczewo Mazurskie Pojezierze Podgrodzie Lupsztych Gutkowo Sródmiescie

„The possibility of the utilization of the residuals from the model in the interpretation of innovative spatial processes”

GRAPHICAL FORM – MAPS

Spatial model of the residual of

undeveloped real estate in Olsztyn _{dr eng. Małgorzata Renigier-Biłozor}

POLAND

(13)

13

SPATIO-TEMPORAL CHANGES

I rok - 1997 II rok-1998 III rok-1999 IV rok-2000

-20 -15 -10 -5 0 5 10 15 20 25 30 35 40 -30 -25 -20 -15 -10 -5 0 5 10 15 20 25 30 35 40 45 50 -40 -35 -30 -25 -20 -15 -10 -5 0 5 10 15 20 25 30 -60 -50 -40 -30 -20 -10 0 10 20 30 40 50 60 70 80 90 100 -80 -70 -60 -50 -40 -30 -20 -10 0 10 20 30 40 50 60 70 -50 -40 -30 -20 -10 0 10 20 30 40 50 60 70 80 90 100 -50 -45 -40 -35 -30 -25 -20 -15 -10 -5 0 5 10 15 20 25 30

V rok-2001 VI rok-2002 VII rok-2003

Analysis of the spatial distribution of residuals, after their division, we can trace and see occurence and diffusions of the innovation and analysis of reasons spatio-temporal changes at a time.

(14)

14 Issue Speculative (forecast) value

Market space

(information about transactions on the market)

Stochastic inference

Deterministic

value The residualvalue

Deterministic inference with stochastic

elements

Innovations, perturbations, disturbances of the market

system The spatial residuals The geostatistical model Developmental-strategic solutions Analyses of optimization and profitability Individual counselling with an average level of risk Individual counselling with a great level of risk

Taxation solutions Formal-legal solutions in REM and SM Planning and urbanistic solutions Conception P R O B L E

(15)

15

Surfer is a grid based Graphics program used for

Mapping XYZ data into grids.

The gridding methods in Surfer allow you to produce accurate contour, surface, wireframe, vector, image, and shaded relief maps from your XYZ data.

The data can be randomly dispersed over the map area, and Surfer's gridding will interpolate your data onto a grid. You have a multitude of gridding methods (Inverse Distance, Kriging, Minimum

Curvature, Polynomial Regression, Triangulation, Nearest Neighbor, Shepard's Method, Radial Basis Functions, Natural Neighbor, Moving Average, and Local Polynomial) to choose from, so you can produce

exactly the map you want.

GIS program -SURFER

(16)

16

GIS program -SURFER

These grids can be used to create many map types including Contour maps, Vector Maps, Wire frame maps, and surface maps.

Contour maps -

two-dimensional representation of three-dimensional data

(17)

17

GIS program -SURFER

Surface maps -

enable the perfect visualization of three-dimensional data maps

(18)

18

Wireframe maps –

these maps provide a three dimensional display of data and enable use color zones in independent X,Y,Z scaling.

GIS program -SURFER

(19)

19

GIS program -SURFER

Vector Maps -

show direction and magnitude of data at points on a map.