Summary RER, including:
- All the Lectures from RER
- Articles
- Relevant additions from the obligatory literature
- Answers to the weekly homework assignments
- Answers to previous exam questions and how to answer them
- Mini summary to prepare for the exam
Week Topic Literature Assignments
1 Introduction Ch. 1 / Adair et al
RES prop + data Ch. 2 + 3 (-2.6/2.7)
Lab Watch video intro Stata 1
Intro to Stata
2 Linear regression l Ch. 4 + 5 / Livy & Klaiber
Watch videos:
Linear Regression
Linear regression ll Ch. 6
Lab 2
3 Linear regression lll Ch. 7 / Zhang et al.
Statistical writing Miller / Schwabisch (2021a)
Lab 3
4 Discrete choice models Ch. 1 – 3 Train / DeMaris
Watch videos:
Probit and Logit Models
Time series models Ch. 6.6 + 8
Watch videos:
Time Series
Lab 4
5 Time series models Ch. 9 / Serrano & Hoesli
RECAP ch. 1 – 8 Ch. 1 – 8 finished / GW (1983)
Lab Schabisch (2021b) 5
6 Instrumental variables Koster et al.
Watch videos:
Instrumental Variables
Time series models lll Ch. 11
Lab 6
7 Forecasting l Ch. 13 / Pace et al.
Forecasting ll
Lab 7
,Contents
Week 01....................................................................................................................................... 3
Lecture 1.1 – Introduction ................................................................................................................... 3
Adair et al. (1996) – Hedonic modelling, housing submarkets and residential valuation .............. 4
Lecture 1.2 - Conceptual model building ........................................................................................... 5
Homework week 01......................................................................................................................... 9
Ch. 3: Statistical tools for real estate analysis ............................................................................... 10
Week 02..................................................................................................................................... 11
Lecture 2.1 - Linear regression l ........................................................................................................ 11
Ivy & Kliber (2016) – maintaining public goods: the capitalized value of local park renovations. 23
Lecture 2.1 – additional lecture on OLS model assumptions (Mantegazzi) ...................................... 24
Lecture 2.2 - Linear regression ll ....................................................................................................... 27
Homework week 02....................................................................................................................... 40
Week 03..................................................................................................................................... 42
Lecture 3.1 – Hedonics ll ................................................................................................................... 42
Zhang et al. (2019) - The external effects of inner‐city shopping centers .................................... 50
Lecture 3.2 – Statistical writing ......................................................................................................... 51
Week 04..................................................................................................................................... 56
Lecture 4.1 – Discrete choice models................................................................................................ 56
DeMaris (1995) – A tutorial in logistic regression ......................................................................... 65
Lecture 4.2 – Time series models l .................................................................................................... 65
Homework week 04....................................................................................................................... 75
Week 05..................................................................................................................................... 76
Lecture 5.1 – Time series models ...................................................................................................... 76
Serrano & Hoesli (2010) - Are Securitized Real Estate Returns more Predictable than Stock
Returns? ........................................................................................................................................ 81
Lecture 5.2 – Recap Ch. 1/8............................................................................................................... 82
Week 06..................................................................................................................................... 88
Lecture 6.1 – Instrumental variables ................................................................................................. 88
Koster et al. (2014) – Is the sky the limit? High rise buildings and office rents ............................ 95
Lecture 6.2 – Time series models lll .................................................................................................. 97
Week 07................................................................................................................................... 102
Lecture 7.1 – Forecasting l .............................................................................................................. 102
Lecture 7.2 – Forecasting ll.............................................................................................................. 102
Week 08................................................................................................................................... 106
Lecture 8.1 – Final lecture: exam preparation ................................................................................ 106
Mini summary for exam preparation: Most important definitions and information ................ 108
,Week 01
Lecture 1.1 – Introduction
Positive relationship between m2 and rents. There are some outliers and varying dots which could
imply omitted variable bias (other factors in play).
How to get to a particular topic? Newspapers, policy report, firms reports. What is mentioned in
academic literature: finding a topic where not much is known about. Mostly focused on quantitative
research methods (however, the research question determines the research method).
, First figure from the book (ch. 1) it is on how to do quantitative research.
How to build a model
1. plot Y on X via scatterplot
- correlation shows statistical relationship between two variables
- correlation does not mean causation (!)
Adair et al. (1996) – Hedonic modelling, housing submarkets and residential valuation
Motivation: There is no clear consensus regarding the empirical basis on which submarkets should be
specified. It is interesting to find how research in housing markets can be integrated in the valuation
process.
Aim: Examine possible linkages between research relating to housing market areas and the valuation
process.
Method: Theoretical perspective followed by hedonic price modelling. The empirical analysis
underlying this paper utilizes multiple regression to examine the existence of housing submarkets
within Belfast and is based on the hypothesis that house price structure can be used to identify and
differentiate housing submarkets. Stepwise options of adding and subtracting variables seek to
develop the best model from all variables based on their statistical significance.
Dependent variable: price
This type of model has the following advantages:
• Robustness
• Provision that variables may change in statistical significance in subsequent stages of analysis
• discrimination between variables
• entry into and deletion from the model reduces risk of multicollinearity between explanatory
variables.
• Criticism: Ignores theoretical considerations with the risk of model mis-specification.
Functional form
Linear models can impose constraints on value response to changes in attribute levels. For example,
each additional square metre of floor space contributes the same amount to value irrespective of the
size of the dwelling and therefore ignores the influence of any quantum effect.
- All the Lectures from RER
- Articles
- Relevant additions from the obligatory literature
- Answers to the weekly homework assignments
- Answers to previous exam questions and how to answer them
- Mini summary to prepare for the exam
Week Topic Literature Assignments
1 Introduction Ch. 1 / Adair et al
RES prop + data Ch. 2 + 3 (-2.6/2.7)
Lab Watch video intro Stata 1
Intro to Stata
2 Linear regression l Ch. 4 + 5 / Livy & Klaiber
Watch videos:
Linear Regression
Linear regression ll Ch. 6
Lab 2
3 Linear regression lll Ch. 7 / Zhang et al.
Statistical writing Miller / Schwabisch (2021a)
Lab 3
4 Discrete choice models Ch. 1 – 3 Train / DeMaris
Watch videos:
Probit and Logit Models
Time series models Ch. 6.6 + 8
Watch videos:
Time Series
Lab 4
5 Time series models Ch. 9 / Serrano & Hoesli
RECAP ch. 1 – 8 Ch. 1 – 8 finished / GW (1983)
Lab Schabisch (2021b) 5
6 Instrumental variables Koster et al.
Watch videos:
Instrumental Variables
Time series models lll Ch. 11
Lab 6
7 Forecasting l Ch. 13 / Pace et al.
Forecasting ll
Lab 7
,Contents
Week 01....................................................................................................................................... 3
Lecture 1.1 – Introduction ................................................................................................................... 3
Adair et al. (1996) – Hedonic modelling, housing submarkets and residential valuation .............. 4
Lecture 1.2 - Conceptual model building ........................................................................................... 5
Homework week 01......................................................................................................................... 9
Ch. 3: Statistical tools for real estate analysis ............................................................................... 10
Week 02..................................................................................................................................... 11
Lecture 2.1 - Linear regression l ........................................................................................................ 11
Ivy & Kliber (2016) – maintaining public goods: the capitalized value of local park renovations. 23
Lecture 2.1 – additional lecture on OLS model assumptions (Mantegazzi) ...................................... 24
Lecture 2.2 - Linear regression ll ....................................................................................................... 27
Homework week 02....................................................................................................................... 40
Week 03..................................................................................................................................... 42
Lecture 3.1 – Hedonics ll ................................................................................................................... 42
Zhang et al. (2019) - The external effects of inner‐city shopping centers .................................... 50
Lecture 3.2 – Statistical writing ......................................................................................................... 51
Week 04..................................................................................................................................... 56
Lecture 4.1 – Discrete choice models................................................................................................ 56
DeMaris (1995) – A tutorial in logistic regression ......................................................................... 65
Lecture 4.2 – Time series models l .................................................................................................... 65
Homework week 04....................................................................................................................... 75
Week 05..................................................................................................................................... 76
Lecture 5.1 – Time series models ...................................................................................................... 76
Serrano & Hoesli (2010) - Are Securitized Real Estate Returns more Predictable than Stock
Returns? ........................................................................................................................................ 81
Lecture 5.2 – Recap Ch. 1/8............................................................................................................... 82
Week 06..................................................................................................................................... 88
Lecture 6.1 – Instrumental variables ................................................................................................. 88
Koster et al. (2014) – Is the sky the limit? High rise buildings and office rents ............................ 95
Lecture 6.2 – Time series models lll .................................................................................................. 97
Week 07................................................................................................................................... 102
Lecture 7.1 – Forecasting l .............................................................................................................. 102
Lecture 7.2 – Forecasting ll.............................................................................................................. 102
Week 08................................................................................................................................... 106
Lecture 8.1 – Final lecture: exam preparation ................................................................................ 106
Mini summary for exam preparation: Most important definitions and information ................ 108
,Week 01
Lecture 1.1 – Introduction
Positive relationship between m2 and rents. There are some outliers and varying dots which could
imply omitted variable bias (other factors in play).
How to get to a particular topic? Newspapers, policy report, firms reports. What is mentioned in
academic literature: finding a topic where not much is known about. Mostly focused on quantitative
research methods (however, the research question determines the research method).
, First figure from the book (ch. 1) it is on how to do quantitative research.
How to build a model
1. plot Y on X via scatterplot
- correlation shows statistical relationship between two variables
- correlation does not mean causation (!)
Adair et al. (1996) – Hedonic modelling, housing submarkets and residential valuation
Motivation: There is no clear consensus regarding the empirical basis on which submarkets should be
specified. It is interesting to find how research in housing markets can be integrated in the valuation
process.
Aim: Examine possible linkages between research relating to housing market areas and the valuation
process.
Method: Theoretical perspective followed by hedonic price modelling. The empirical analysis
underlying this paper utilizes multiple regression to examine the existence of housing submarkets
within Belfast and is based on the hypothesis that house price structure can be used to identify and
differentiate housing submarkets. Stepwise options of adding and subtracting variables seek to
develop the best model from all variables based on their statistical significance.
Dependent variable: price
This type of model has the following advantages:
• Robustness
• Provision that variables may change in statistical significance in subsequent stages of analysis
• discrimination between variables
• entry into and deletion from the model reduces risk of multicollinearity between explanatory
variables.
• Criticism: Ignores theoretical considerations with the risk of model mis-specification.
Functional form
Linear models can impose constraints on value response to changes in attribute levels. For example,
each additional square metre of floor space contributes the same amount to value irrespective of the
size of the dwelling and therefore ignores the influence of any quantum effect.
