Analysis of Prices in the Housing Market Using Mixed Models

Abstract Hedonic models, commonly applied for analyzing prices in the property market, do not always fulfil their role, mainly due to the application of simplified assumptions concerning the distribution of variables, the nature of relations or spatial heterogeneity. Classical regression models assumed that the variation of the explained variable (price) is explained by the effect of market features (fixed effects) and the residual component. The hierarchical structure of market data, both as regards market segments and the spatial division, suggests that statistical models of prices should also include random effects for selected subgroups of properties and interactions between variables. The mixed model provides an alternative for constructing various regression models for individual groups or for using binary variables within one model. With its appropriate structure, it makes it possible to take into account both the spatial heterogeneity and to examine the effects of individual features on prices within various property groups. It can also identify synergy effects. The article presents the issue of mixed modelling in the property market and an example of its application in a market of dwellings in Olsztyn. The research used transaction data from the price and value register, supplemented with spatial data. The obtained model was compared with classical regression models and geographically weighted regression. The study also covered the usefulness of mixed models in the mass evaluation of properties, and the possibility of using them in spatial analyses and for the development of property value maps.

Download Full-text

The Impact of Misspecified Random Effect Distribution in a Weibull Regression Mixed Model

Stats ◽

10.3390/stats1010005 ◽

2018 ◽

Vol 1 (1) ◽

pp. 48-76

Author(s):

Freddy Hernández ◽

Viviana Giampaoli

Keyword(s):

Weibull Distribution ◽

Random Effects ◽

Mixed Models ◽

Fixed Effects ◽

Mixed Model ◽

Random Effect ◽

Estimation Procedure ◽

Weibull Regression ◽

Two Parameters ◽

The Impact

Mixed models are useful tools for analyzing clustered and longitudinal data. These models assume that random effects are normally distributed. However, this may be unrealistic or restrictive when representing information of the data. Several papers have been published to quantify the impacts of misspecification of the shape of the random effects in mixed models. Notably, these studies primarily concentrated their efforts on models with response variables that have normal, logistic and Poisson distributions, and the results were not conclusive. As such, we investigated the misspecification of the shape of the random effects in a Weibull regression mixed model with random intercepts in the two parameters of the Weibull distribution. Through an extensive simulation study considering six random effect distributions and assuming normality for the random effects in the estimation procedure, we found an impact of misspecification on the estimations of the fixed effects associated with the second parameter σ of the Weibull distribution. Additionally, the variance components of the model were also affected by the misspecification.

Download Full-text

Generalized linear mixed models for multi-reader multi-case studies of diagnostic tests

Statistical Methods in Medical Research ◽

10.1177/0962280215579476 ◽

2015 ◽

Vol 26 (3) ◽

pp. 1373-1388 ◽

Cited By ~ 3

Author(s):

Wei Liu ◽

Norberto Pantoja-Galicia ◽

Bo Zhang ◽

Richard M Kotz ◽

Gene Pennello ◽

...

Keyword(s):

Mixed Models ◽

Diagnostic Tests ◽

Fixed Effects ◽

Mixed Model ◽

Linear Mixed Model ◽

Generalized Linear Mixed Models ◽

Characteristic Curve ◽

Linear Mixed Models ◽

Parametric Bootstrap ◽

Pseudo Likelihood

Diagnostic tests are often compared in multi-reader multi-case (MRMC) studies in which a number of cases (subjects with or without the disease in question) are examined by several readers using all tests to be compared. One of the commonly used methods for analyzing MRMC data is the Obuchowski–Rockette (OR) method, which assumes that the true area under the receiver operating characteristic curve (AUC) for each combination of reader and test follows a linear mixed model with fixed effects for test and random effects for reader and the reader–test interaction. This article proposes generalized linear mixed models which generalize the OR model by incorporating a range-appropriate link function that constrains the true AUCs to the unit interval. The proposed models can be estimated by maximizing a pseudo-likelihood based on the approximate normality of AUC estimates. A Monte Carlo expectation-maximization algorithm can be used to maximize the pseudo-likelihood, and a non-parametric bootstrap procedure can be used for inference. The proposed method is evaluated in a simulation study and applied to an MRMC study of breast cancer detection.

Download Full-text

Using mixed models to combine smooth size-selection and catch-comparison curves over hauls

Canadian Journal of Fisheries and Aquatic Sciences ◽

10.1139/f03-029 ◽

2003 ◽

Vol 60 (4) ◽

pp. 448-459 ◽

Cited By ~ 29

Author(s):

R J Fryer ◽

A F Zuur ◽

N Graham

Keyword(s):

Mixed Models ◽

Fixed Effects ◽

Mixed Model ◽

Random Effect ◽

Categorical Variable ◽

Size Selection ◽

Research Survey ◽

Different Levels ◽

Selection Of ◽

Comparison Data

Parametric size-selection curves are often combined over hauls to estimate a mean selection curve using a mixed model in which between-haul variation in selection is treated as a random effect. This paper shows how the mixed model can be extended to estimate a mean selection curve when smooth nonparametric size-selection curves are used. The method also estimates the between-haul variation in selection at each length and can model fixed effects in the form of the different levels of a categorical variable. Data obtained to estimate the size-selection of dab by a Nordmøre grid are used for illustration. The method can also be used to provide a length-based analysis of catch-comparison data, either to compare a test net with a standard net or to calibrate two research survey vessels. Haddock data from an intercalibration exercise are used for illustration.

Download Full-text

Effects of spatial heterogeneity on bacterial genetic circuits

10.1101/2019.12.22.886473 ◽

2019 ◽

Author(s):

Carlos Barajas ◽

Domitilla Del Vecchio

Keyword(s):

Differential Equation ◽

Ordinary Differential Equation ◽

Spatial Heterogeneity ◽

Mixed Models ◽

Mixed Model ◽

Spatial Effects ◽

Genetic Circuits ◽

Association Rate Constant ◽

Ode Model ◽

Association Rate

AbstractIntracellular spatial heterogeneity is frequently observed in bacteria, where the chromosome occupies part of the cell’s volume and a circuit’s DNA often localizes within the cell. How this heterogeneity affects core processes and genetic circuits is still poorly understood. In fact, commonly used ordinary differential equation (ODE) models of genetic circuits assume a well-mixed ensemble of molecules and, as such, do not capture spatial aspects. Reaction-diffusion partial differential equation (PDE) models have been only occasionally used since they are difficult to integrate and do not provide mechanistic understanding of the effects of spatial heterogeneity. In this paper, we derive a reduced ODE model that captures spatial effects, yet has the same dimension as commonly used well-mixed models. In particular, the only difference with respect to a well-mixed ODE model is that the association rate constant of binding reactions is multiplied by a coefficient, which we refer to as the binding correction factor (BCF). The BCF depends on the size of interacting molecules and on their location when fixed in space and it is equal to unity in a well-mixed ODE model. The BCF can be used to investigate how spatial heterogeneity affects the behavior of core processes and genetic circuits. Specifically, our reduced model indicates that transcription and its regulation are more effective for genes located at the cell poles than for genes located on the chromosome. The extent of these effects depends on the value of the BCF, which we found to be close to unity. For translation, the value of the BCF is always greater than unity, it increases with mRNA size, and, with biologically relevant parameters, is substantially larger than unity. Our model has broad validity, has the same dimension as a well-mixed model, yet it incorporates spatial heterogeneity. This simple-to-use model can be used to both analyze and design genetic circuits while accounting for spatial intracellular effects.Abstract FigureHighlightsIntracellular spatial heterogeneity modulates the effective association rate constant of binding reactions through a binding correction factor (BCF) that fully captures spatial effectsThe BCF depends on molecules size and location (if fixed) and can be determined experimentallySpatial heterogeneity may be detrimental or exploited for genetic circuit designTraditional well-mixed models can be appropriate despite spatial heterogeneityStatement of significanceA general and simple modeling framework to determine how spatial heterogeneity modulates the dynamics of gene networks is currently lacking. To this end, this work provides a simple-to-use ordinary differential equation (ODE) model that can be used to both analyze and design genetic circuits while accounting for spatial intracellular effects. We apply our model to several core biological processes and determine that transcription and its regulation are more effective for genes located at the cell poles than for genes located on the chromosome and this difference increases with regulator size. For translation, we predict the effective binding between ribosomes and mRNA is higher than that predicted by a well-mixed model, and it increases with mRNA size. We provide examples where spatial effects are significant and should be considered but also where a traditional well-mixed model suffices despite severe spatial heterogeneity. Finally, we illustrate how the operation of well-known genetic circuits is impacted by spatial effects.

Download Full-text

Addressing cluster-constant covariates in mixed effects models via likelihood-based boosting techniques

PLoS ONE ◽

10.1371/journal.pone.0254178 ◽

2021 ◽

Vol 16 (7) ◽

pp. e0254178

Author(s):

Colin Griesbach ◽

Andreas Groll ◽

Elisabeth Bergherr

Keyword(s):

Mixed Models ◽

Fixed Effects ◽

Regression Models ◽

Computational Effort ◽

Likelihood Inference ◽

Gradient Boosting ◽

Current State ◽

Selection Step ◽

Boosting Algorithm

Boosting techniques from the field of statistical learning have grown to be a popular tool for estimating and selecting predictor effects in various regression models and can roughly be separated in two general approaches, namely gradient boosting and likelihood-based boosting. An extensive framework has been proposed in order to fit generalized mixed models based on boosting, however for the case of cluster-constant covariates likelihood-based boosting approaches tend to mischoose variables in the selection step leading to wrong estimates. We propose an improved boosting algorithm for linear mixed models, where the random effects are properly weighted, disentangled from the fixed effects updating scheme and corrected for correlations with cluster-constant covariates in order to improve quality of estimates and in addition reduce the computational effort. The method outperforms current state-of-the-art approaches from boosting and maximum likelihood inference which is shown via simulations and various data examples.

Download Full-text

Statistical Modelling

10.36253/88-8453-192-6 ◽

2004 ◽

Author(s):

Annibale Biggeri ◽

Emanuela Dreassi ◽

Corrado Lagazio ◽

Marco Marchi

Keyword(s):

Spatial Data ◽

Mixed Models ◽

Regression Models ◽

International Workshop ◽

Statistical Modelling ◽

Correlated Data ◽

Data Modelling ◽

Scientific Disciplines ◽

Parametric Regression Models ◽

Cross Fertilization

The book collects the proceedings of the 19th International Workshop on Statistical Modelling held in Florence on July 2004. Statistical modelling is an important cornerstone in many scientific disciplines, and the workshop has provided a rich environment for cross-fertilization of ideas from different disciplines. It consists in four invited lectures, 48 contributed papers and 47 posters. The contributions are arranged in sessions: Statistical Modelling; Statistical Modelling in Genomics; Semi-parametric Regression Models; Generalized Linear Mixed Models; Correlated Data Modelling; Missing Data, Measurement of Error and Survival Analysis; Spatial Data Modelling and Time Series and Econometrics.

Download Full-text

Metabolic Adaptations to Dynamic Energy Requirements during Lactation and Pregnancy in Dairy Cows with Varying Proportions of Holstein and Simmental Breed

Proceedings ◽

10.3390/ieca2020-08833 ◽

2020 ◽

Vol 73 (1) ◽

pp. 9

Author(s):

Deise Aline Knob ◽

André Thaler Neto ◽

Helen Schweizer ◽

Anna Weigand ◽

Roberto Kappes ◽

...

Keyword(s):

Energy Balance ◽

Dairy Cows ◽

Fixed Effects ◽

Mixed Model ◽

Negative Energy ◽

Negative Energy Balance ◽

Repeated Measure ◽

Holstein Cows ◽

Mixed Model Analysis ◽

Genetic Groups

Depending on the breed or crossbreed line, cows have to cope with a more or less severe negative energy balance during the period of high milk yields in early lactation, which can be detected by beta-hydroxybutyrate (BHBA) and non-esterified fatty acids (NEFAs) in blood. Preventing cows from undergoing a severe negative energy balance by breeding and/or feeding measures is likely to be supported by the public and may help to improve the sustainability of milk production. The aim was to compare BHBA and NEFA concentrations in the blood of Holstein and Simmental cows and their crosses during the prepartum period until the end of lactation. In total, 164 cows formed five genetic groups according to their theoretic proportion of Holstein and Simmental genes as follows: Holstein (100% Holstein; n = 9), R1-Hol (51–99% Holstein; n = 30), F1 crossbreds (50% Holstein, 50% Simmental; n = 17), R1-Sim (1–49% Holstein; n = 81) and Simmental (100% Simmental; n = 27). NEFA and BHBA were evaluated once a week between April 2018 and August 2019. A mixed model analysis with fixed effects breed, week (relative to calving), the interaction of breed and week, parity, calving year, calving season, milking season, and the repeated measure effect on cows was used. Holstein cows had higher NEFAs (0.196 ± 0.013 mmol/L), and Simmental cows had the lowest NEFA concentrations (0.147 ± 0.008 mmol/L, p = 0.03). R1-Sim, F1 and R1-Hol cows had intermediate values (0.166 ± 0.005, 0.165 ± 0.010, 0.162 ± 0.008 mmol/L; respectively). The highest NEFA value was found in the first week after calving (0.49 ± 0.013 mmol/L). BHBA did not differ among genetic groups (p = 0.1007). There was, however, an interaction between the genetic group and week (p = 0.03). While Simmental, R1-Sim and F1 cows had the highest BHBA value, the second week after calving (0.92 ± 0.07 and 1.05 ± 0.04, and 1.10 ± 0.10 mmol/L, respectively), R1-Hol and Holstein cows showed the BHBA peak at the fourth week after calving (1.16 ± 0.07 and 1.36 ± 0.12 mmol/L, respectively). Unexpectedly, Holstein cows had a high BHBA peak again at week 34 after calving (1.68 ± 0.21 mmol/L). The genetic composition of the cows affects NEFA and BHBA. Simmental and R1-Sim cows mobilize fewer body reserves after calving. Therefore, dairy cows with higher degrees of Simmental origin might be more sustainable in comparison with Holstein genetics in the present study.

Download Full-text

Research on Spatiotemporal Differentiation and Influence Mechanism of Urban Resilience in China Based on MGWR Model

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18031056 ◽

2021 ◽

Vol 18 (3) ◽

pp. 1056

Author(s):

Yu Chen ◽

Mengke Zhu ◽

Qian Zhou ◽

Yurong Qiao

Keyword(s):

Spatial Heterogeneity ◽

Spatial Correlation ◽

Spatial Data ◽

Central Area ◽

Urban System ◽

Entropy Method ◽

Driving Factors ◽

Spatial Data Analysis ◽

Eastern Region ◽

Urban Resilience

Urban resilience in the context of COVID-19 epidemic refers to the ability of an urban system to resist, absorb, adapt and recover from danger in time to hedge its impact when confronted with external shocks such as epidemic, which is also a capability that must be strengthened for urban development in the context of normal epidemic. Based on the multi-dimensional perspective, entropy method and exploratory spatial data analysis (ESDA) are used to analyze the spatiotemporal evolution characteristics of urban resilience of 281 cities of China from 2011 to 2018, and MGWR model is used to discuss the driving factors affecting the development of urban resilience. It is found that: (1) The urban resilience and sub-resilience show a continuous decline in time, with no obvious sign of convergence, while the spatial agglomeration effect shows an increasing trend year by year. (2) The spatial heterogeneity of urban resilience is significant, with obvious distribution characteristics of “high in east and low in west”. Urban resilience in the east, the central and the west are quite different in terms of development structure and spatial correlation. The eastern region is dominated by the “three-core driving mode”, and the urban resilience shows a significant positive spatial correlation; the central area is a “rectangular structure”, which is also spatially positively correlated; The western region is a “pyramid structure” with significant negative spatial correlation. (3) The spatial heterogeneity of the driving factors is significant, and they have different impact scales on the urban resilience development. The market capacity is the largest impact intensity, while the infrastructure investment is the least impact intensity. On this basis, this paper explores the ways to improve urban resilience in China from different aspects, such as market, technology, finance and government.

Download Full-text

The Differential Effects of Caregiving Intensity on Overnight Hospitalization in the Previous 2 Years

Innovation in Aging ◽

10.1093/geroni/igaa057.249 ◽

2020 ◽

Vol 4 (Supplement_1) ◽

pp. 76-76

Author(s):

Kylie Meyer ◽

Zachary Gassoumis ◽

Kathleen Wilber

Keyword(s):

Health Services ◽

Fixed Effects ◽

Regression Models ◽

P Value ◽

Logistic Regression Models ◽

Spousal Caregiving ◽

Health Insurance Status ◽

Race Ethnicity ◽

Self Assessed Health ◽

Retirement Study

Abstract Caregiving for a spouse is considered a major stressor many Americans will encounter during their lifetimes. Although most studies indicate caregiving is associated with experiencing diminished health outcomes, little is known about how this role affects caregivers’ use of acute health services. To understand how spousal caregiving affects the use of acute health services, we use data from the Health and Retirement Study. We apply fixed effects (FE) logistic regression models to examine odds of experiencing an overnight hospitalization in the previous two years according to caregiving status, intensity, and changes in caregiving status and intensity. Models controlled for caregiver gender, age, race, ethnicity, educational attainment, health insurance status, the number of household residents, and self-assessed health. Overall, caregivers were no more likely to experience an overnight hospitalization compared to non-caregivers (OR 0.92; CI 0.84 to 1.00; p-value=0.057). However, effects varied according to the intensity of caregiving and the time spent in this role. Compared to non-caregivers, for example, spouses who provided care to someone with no need for assistance with activities of daily living had lower odds of experiencing a hospitalization (OR 0.77; CI 0.66 to 0.89). In contrast, caregivers who provided care to someone with dementia for 4 to <6 years had 3.29 times the odds of experiencing an overnight hospitalization (CI 1.04 to 10.38; p-value=0.042). Findings indicate that, although caregivers overall appear to use acute health services about as much as non-caregivers, large differences exist between caregivers. Results emphasize the importance of recognizing diversity within caregiving experiences.

Download Full-text

Econometric Analysis of the Impact of Propensities on Economic Occurrences: A Macroeconomic Perspective

Folia Oeconomica Stetinensia ◽

10.2478/v10031-011-0021-2 ◽

2012 ◽

Vol 10 (2) ◽

pp. 138-154 ◽

Cited By ~ 1

Author(s):

Mariusz Doszyń

Keyword(s):

Spatial Data ◽

Fixed Effects ◽

Classical Model ◽

Econometric Analysis ◽

Dummy Variables ◽

Macroeconomic Variables ◽

Current State ◽

Famous Book ◽

Direct Models ◽

The Impact

Econometric Analysis of the Impact of Propensities on Economic Occurrences: A Macroeconomic PerspectiveThe main aim of this article was the specification of problems connected with analysis of impact of human propensities on economic occurrences and also a proposition of econometric tools enabling the identification of this impact. According to the meaning of propensities in economics the current state of knowledge is mostly an effect of considerations presented by J.M. Keynes in his famous book "The General Theory of Employment, Interest and Money" where J.M. Keynes proposed such economic categories as the average and marginal propensities. One of the goals of the presented deliberations was to specify problems related with economic theory of propensities. Such propensities as a propensity to consume, to save, to invest and thesaurisation were particularly carefully analysed. The impact of these propensities on basic macroeconomic variables was considered with respect to the classical model, the neoclassical Solow-Swan model and theIS-LMscheme. In case of spatial data the effects of the impact of propensities could be analysed by means of models with dummy variables showing presence of given propensities. A procedure enabling the construction of such variables was proposed. In case of time series, conceptions delivered by the integration and cointegration theory could be applied. Especially such models as VAR and VECM could be useful. Models for panel data enable direct (models with fixed effects) or indirect (models with random effects) consideration of the impact of propensities on the analysed processes.

Download Full-text