The Sustainable Development Goals (SDGs), particularly Goal 11 (Sustainable Cities and Communities) and Goal 13 (Climate Action), underscore the interconnectedness between air quality and climate change. Escalating levels of air pollution in both urban and rural regions of Indonesia necessitate a deeper understanding of the factors contributing to air quality degradation. This study employs a generalized linear modeling approach, specifically focusing on ordinal logistic regression, to explore the determinants influencing the Air Quality Index (AQI) across 34 provinces in Indonesia. Key predictors, including motor vehicle density, population density, Greenhouse Gas (GHG) emissions, and forest cover, are analyzed to assess their impact on air quality levels. The findings indicate that the number of motor vehicles and the extent of forest cover are significant predictors of air quality. Elevated motor vehicle density is shown to deteriorate the AQI, while larger forest cover areas are associated with improvements in air quality. These results emphasize the importance of targeted environmental interventions, particularly those aimed at reducing vehicle emissions and preserving forest ecosystems. The study highlights the need for the development and enforcement of policies that promote sustainable urban mobility and forest conservation to mitigate air pollution. By providing a comprehensive statistical framework through ordinal logistic regression, this research offers actionable insights for policymakers. The findings can guide the formulation of effective environmental management strategies, supporting efforts to achieve sustainable development objectives. Moreover, this study demonstrates the relevance of adopting rigorous statistical models to address complex environmental challenges, contributing to the broader discourse on sustainability and climate action.

Data at a smaller regional level has now become a necessity for local governments. The average data on household expenditure on food and non-food is designed for provincial and district/city estimation levels. Subdistrict-level statistics are not currently available. Small area estimation (SAE) is one method to address the problem. The Empirical Best Linear Unbiased Prediction (EBLUP)—Fay Herriot Multivariate method estimates the average household expenditure on food and non-food at the sub-district level in Central Java Province in 2020. Meanwhile, for the sub-districts that are not sampled, the estimation of average household expenditure is done by adding cluster information to the EBLUP Multivariate modeling. The K-Medoids Cluster method is used to classify sub-districts based on their characteristics. Small area estimation using the EBLUP-FH Multivariate method can enhance the parameter estimations obtained using the direct estimation method because it results in a lower level of variation (RSE). For sub-districts that are not sampled, the Residual Standard Error (RSE) value from the estimated results using the EBLUP-FH Multivariate method with cluster information is lower than 25%, indicating that the estimate is accurate.

Analysis of the market position will be easier, efficient, and informative when based on a perceptual map, that can display objects and characteristics. With perceptual map we can identify the information about the objects similarity, the characteristics relationships, and relationship between the object and the characteristics. Characteristics of the object are usually more than two variables, those variables that sometimes are qualitative and some are quantitative. Based on that this paper introduce a method of analysis called hybrid correspondence analysis and correlation (HCAC), this method is the incorporation of correspondence analysis (CA) with biplot of correlation, where the mapped of two qualitative variables is using CA, and for quantitative variables is using correlations. HCAC produces a perceptual map that displays the object, the qualitative characteristics, and quantitative characteristics in a single map, without changing the quantitative data into qualitative data, so that the information obtained is more complete. A reference for mapping quality is counted from the first and second cumulative percent of eigenvalues where resulting from CA.

Ministry of Housing Republic of Indonesia explained that the Constitution mandates that every citizen has the right to reside. Jakarta, Surabaya, Bandung, Semarang, and Yogyakarta are five of Java’s major cities with high population and investment opportunities, so the housing needs in that five cities is very high. Market sentiment analysis recorded the average of property purchasing power for Indonesian society around Rp 250 million, which the author assumes that the highest price for Indonesian middle class. Based on the fact, does the Indonesian middle class have the ability to purchase a house in the five major cities of Java? What facilities do they get? Both questions can be answered using the results of correspondence analysis.

Analysis of the object and the characteristics will be much easier, efficient, and informative when based on a perceptual map, which can display objects and characteristics. Indicator matrix is a matrix where the rows represent objects and the columns is a dummy variable representing characteristics. This article writes about techniques to make perceptual map from indicator matrix, where that can provide information about the similarity between objects, the diversity of each characteristic, correlations between the characteristics, and characteristic values ​​for each object, the techniques we call Hybrid Latent Class Cluster with PCA Biplot, where Latent Class Cluster Analysis is used to transform the indicator matrix to cross section matrix, where rows represent the objects and columns represent the characteristics, the observation cells is the probability of characteristic for each object, next the cross section matrix mapped using Principal Component Analysis Biplot (PCA Biplot). Key Words: Hybrid Latent Class Cluster with PCA Biplot, Latent Class Cluster Analysis, Biplot Principal Component Analysis, Indicator Matrix.

Classical correspondent analysis (CA) is one of the probabilistic methods which is often used in analyzing two qualitative variables. We apply a different method called Simplification of Classical Correspondence Analysis (SoCA) in calculating the row and column principal coordinates. The proposed method is simple, and it gives more accurate results than the results obtained by the CA. We apply the proposed method to identify the characteristics of the Indonesian online shopping frauds.