scholarly journals Using Light-at-Night (LAN) Satellite Data for Identifying Clusters of Economic Activities in Europe

2015 ◽  
Vol XL-7/W3 ◽  
pp. 1403-1409
Author(s):  
N. A. Rybnikova ◽  
B. A. Portnov
Keyword(s):  
Missing Data ◽  
Statistical Models ◽  
Economic Activities ◽  
Satellite Measurements ◽  
Light At Night ◽  
Multivariate Statistical ◽  
Development Policies ◽  
Economic Forces ◽  
Satellite Sensors ◽  
Sufficient Degree

Enterprises organized in clusters are often efficient in stimulating urban development, productivity and profit outflows. Identifying clusters of economic activities (EAs) thus becomes an important step in devising regional development policies, aimed at facilitating regional economic development. However, a major problem with cluster identification stems from limited reporting of specific EAs by individual countries and administrative entities. Even Eurostat, which maintains most advances regional databases, provides data for less than 50% of all regional subdivisions of the 3<sup>rd</sup> tier of the Nomenclature of Territorial Units for Statistics (NUTS3). Such poor reporting impedes identification of EA clusters and economic forces behind them. In this study, we test a possibility that missing data on geographic concentrations of EAs can be reconstructed using Light-at-Night (LAN) satellite measurements, and that such reconstructed data can then be used for the identification of EA clusters. As we hypothesize, LAN, captured by satellite sensors, is characterized by different intensity, depending on its source – production facilities, services, etc., – and this information can be used for EA identification. The study was carried out in three stages. First, using nighttime satellite images, we determined what types of EAs can be identified, with a sufficient degree of accuracy, by LAN they emit. Second, we calculated multivariate statistical models, linking EAs concentrations with LAN intensities and several locational and development attributes of NUTS3 regions in Europe. Next, using the obtained statistical models, we restored missing data on EAs across NUTS3 regions in Europe and identified clusters of EAs, using spatial analysis tools.

Engagement Through the Diaspora Channel

2017 ◽  
Author(s):  
Michael S. Danielson
Keyword(s):  
Civil Society ◽  
Statistical Models ◽  
State Level ◽  
The State ◽  
Multivariate Statistical ◽  
Political Factors ◽  
Data Set ◽  
Level Data ◽  
Municipal Level

The first empirical task is to identify the characteristics of municipalities which US-based migrants have come together to support financially. Using a nationwide, municipal-level data set compiled by the author, the chapter estimates several multivariate statistical models to compare municipalities that did not benefit from the 3x1 Program for Migrants with those that did, and seeks to explain variation in the number and value of 3x1 projects. The analysis shows that migrants are more likely to contribute where migrant civil society has become more deeply institutionalized at the state level and in places with longer histories as migrant-sending places. Furthermore, the results suggest that political factors are at play, as projects have disproportionately benefited states and municipalities where the PAN had a stronger presence, with fewer occurring elsewhere.

scholarly journals Dynamic model updating (DMU) approach for statistical learning model building with missing data

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Rahi Jain ◽  
Wei Xu
Keyword(s):  
Missing Data ◽  
Dynamic Model ◽  
Statistical Models ◽  
Missing Values ◽  
Model Building ◽  
Model Updating ◽  
Biological Data ◽  
Bayesian Regression ◽  
Biological Research ◽  
Original Dataset

Abstract Background Developing statistical and machine learning methods on studies with missing information is a ubiquitous challenge in real-world biological research. The strategy in literature relies on either removing the samples with missing values like complete case analysis (CCA) or imputing the information in the samples with missing values like predictive mean matching (PMM) such as MICE. Some limitations of these strategies are information loss and closeness of the imputed values with the missing values. Further, in scenarios with piecemeal medical data, these strategies have to wait to complete the data collection process to provide a complete dataset for statistical models. Method and results This study proposes a dynamic model updating (DMU) approach, a different strategy to develop statistical models with missing data. DMU uses only the information available in the dataset to prepare the statistical models. DMU segments the original dataset into small complete datasets. The study uses hierarchical clustering to segment the original dataset into small complete datasets followed by Bayesian regression on each of the small complete datasets. Predictor estimates are updated using the posterior estimates from each dataset. The performance of DMU is evaluated by using both simulated data and real studies and show better results or at par with other approaches like CCA and PMM. Conclusion DMU approach provides an alternative to the existing approaches of information elimination and imputation in processing the datasets with missing values. While the study applied the approach for continuous cross-sectional data, the approach can be applied to longitudinal, categorical and time-to-event biological data.

DECISION MAKING BY VARIABLE CONTRIBUTION IN DISCRIMINANT, LOGIT, AND REGRESSION ANALYSES

2004 ◽  
Vol 03 (02) ◽  
pp. 265-279 ◽  
Author(s):  
STAN LIPOVETSKY ◽  
MICHAEL CONKLIN
Keyword(s):  
Decision Making ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Statistical Models ◽  
Regression Analyses ◽  
Discriminant Functions ◽  
Multivariate Statistical ◽  
Linear Discriminant ◽  
Variable Contribution ◽  
Linear Aggregate

Comparative contribution of predictors in multivariate statistical models is widely used for decision making on the importance of the variables for the aims of analysis and prediction. However, the analysis can be made difficult because of the predictors' multicollinearity that distorts estimates for coefficients in the linear aggregate. To solve the problem of the robust evaluation of the predictors' contribution, we apply the Shapley Value regression analysis that provides consistent results in the presence of multicollinearity both for regression and discriminant functions. We also show how the linear discriminant function can be constructed as a multiple regression, and how the logistic regression can be approximated by linear regression that helps to obtain the variables contribution in the linear aggregate.

scholarly journals Bayesian Case Influence Measures for Statistical Models With Missing Data

2012 ◽  
Vol 21 (1) ◽  
pp. 253-271 ◽  
Author(s):  
Hongtu Zhu ◽  
Joseph G. Ibrahim ◽  
Hyunsoon Cho ◽  
Niansheng Tang
Keyword(s):  
Missing Data ◽  
Statistical Models

Measuring Threat and Violence

2018 ◽  
pp. 43-56
Author(s):  
Jeffrey S. Kopstein ◽  
Jason Wittenberg
Keyword(s):  
Statistical Models ◽  
Census Data ◽  
Location Information ◽  
Ecological Inference ◽  
Multivariate Statistical ◽  
Original Dataset ◽  
Geographical Unit ◽  
Nationalist Parties ◽  
Electoral Data

This chapter describes our data and methods. Our analysis is based on an original dataset of census returns, electoral results, and pogrom location information. We gathered these data at the lowest geographical unit for which they could be merged, yielding observations for over 2,000 localities. We use census data on religion and electoral data on support for Jewish and non-Jewish nationalist parties to measure the degree of perceived political threat prior to the outbreak of war. We establish the characteristics of those localities where pogroms occurred using a variety of methods, including multivariate statistical models and ecological inference.

Sign in / Sign up

Export Citation Format

Share Document