Based on R language geographic weighted regression, principal component analysis, discriminant analysis and other spatial heterogeneity data analysis

In the field of natural and social sciences, there is a large amount of data related to geography or space. This type of data generally has serious spatial heterogeneity, and the usual statistical methods cannot deal with the spatial heterogeneity.data is powerless.
A series of methods based on geographically weighted regression: classical geographically weighted regression, semi-parametric geographically weighted regression, multi-scale geographically weighted regression, geographically weighted principal component analysis, geographically weighted discriminant analysis are effective models for dealing with such data.
Starting from the local weighted regression, the R language-based spatial heterogeneity data analysis method is described in detail.

[Features]:
1. Explaining the principles in simple language;
2. Explaining techniques and methods, providing all case data and codes;
3. Combining with project casesExplain the implementation method and connect with the actual work application;
4. Follow the school to operate on the computer, complete the case operation exercise independently, and track and analyze the whole process;
5. The exclusive student group assists in consolidating learning and practical work application communication, withoutOnline Q&A is held regularly.

/// Spatial heterogeneity data analysis based on R language geographic weighted regression, principal component analysis, discriminant analysis, etc.

Topic 1: Descriptive Statistics under Geographically Weighted Regression
1. A brief review of R language operations
2. Basic Principles of Local Weighting
3. Bandwidth and Kernel Function Selection
4. Mean, Standard Deviation and Correlation Coefficient of Local Weighting
5. Quantile and Robust Estimation Based on Quantile
br>

Topic 2: Geographically Weighted Principal Component Analysis
1. Ordinary principal component analysis, factor loadings and factor scoresAnalysis
2. Selection of the number of principal components, gravel map
3. Geographically weighted principal component analysis
4. Spatial loading of principal components
5. Spatial dominant factor analysis

Topic 3: Geographically Weighted Regression
1. Linear Regression: Gauss-Markov Assumption
2.Geographically Weighted Regression: Basic and Robust Methods, Outlier Tests
3. Bandwidth Selection: Modified Akaike Information Method
4. Coefficient Tests: F1, F2, F3 Tests
5. Spatial StabilityTest: Monte Carlo Methods
6. Collinearity and Variable Selection: Ridge Regression and Lasso Regression in Geographically Weighted Regression
7. Geographically Weighted Regression in Space and Time: GTWR 8. Geographically Weighted Regression in QGIS

Topic 4: Advanced Regression and Beyond Regression
1. Multiscale Geographically Weighted Regression: Variable BandwidthChoice
2. Heteroskedastic Models
3. Generalized Geographically Weighted Regression: Link Function, Poisson Regression and Binomial Regression
4. Spatial Weight Matrix and Semiparametric Geographically Weighted Regression
5. PointsNumerical Regression and Geographically Weighted Quantile Regression
6. Discriminant Analysis and Geographically Weighted Discriminant Analysis

More Recommendations
●【Tutorial】R Language Quantile Regression
●【Tutorial】RAnalysis and Application of Language Structural Equation Modeling
●【Tutorial】Practical Technical Application of Bayesian Network Model Based on R Language
●【Tutorial】Practical Technical Application of Modern Bayesian Statistical Method Based on R Language
●[Tutorial] Modern Bayesian statistical methods based on R language (Bayesian parameter estimation, Bayesian regression, Bayesian calculation)
●[Tutorial] R language data statistical analysis and ggplot2 advanced drawing practice application
●[Tutorial] Copula Variable Correlation Analysis and Application Based on R Language
●[Tutorial] Extreme Value Statistics Based on R Language and Its Practical Technical Application in Related Fields
●[Tutorial]R language mixed effect (multi-level nested) model technology application and mixed effect model Bayesian implementation method
●【Tutorial】Meta analysis based on R language [full process, uncertainty analysis] method and Meta machineLearning
●【Tutorial】Based on R language Meta analysis method and advanced practical technology application