Two-stage principal component analysis on interval-valued data using patterned covariance structures

Four sets, each of 100 bacterial isolates, were derived from two different flax rhizosphere and corresponding control (nonrhizosphere soil) samples. A two-stage principal component analysis was used to compare the nature and properties of these bacterial cultures which were selected by a random sampling method from primary isolation plates. These 400 experimental isolates were characterized by their reaction to a set of 98 tests. Principal component analysis was applied separately to the data for each of the four sets of cultures. The sets were then compared both in terms of the leading discriminating tests and of the detailed properties of the clusters of isolates detected. Because these isolates and a set of 100 named cultures (previously studied) were subjected to the same tests, the properties of groups of isolates from different sets could be directly compared. The kinds of isolates predominant in the rhizosphere samples were not represented amongst isolates derived from the corresponding control soil populations. The specific kinds of amino-acid-requiring isolates present in the control soil populations were not found in the corresponding rhizosphere populations. The two control soil sets of isolates (predominantly arthrobacter–coryneform-like organisms) were generally similar in their reactions to the tests used, but the two sets of rhizosphere isolates (predominantly pseudomonas-like organisms) were relatively dissimilar. The named species studied previously were not sufficiently indicative of the diversity found in the experimental isolates: this was especially true of the arthrobacter-like isolates. The numerical analyses yielded useful groupings of tests and of cultures and aided in their evaluation.

In this paper we present a distributed multicolumnar system using an intracolumnar principal component analysis (PCA) for a topology preserving mapping of real-world grey level distributions within a two-dimensional intercolumnar Kohonen Feature Map. A two-stage principal component analysis within each processing column allows a similarity preserving description with only a few highly effective fitting parameters suited for a local translation invariant processing.

This study tries to measure inclusive growth in the post-reform period of India and assesses its performance in different aspects of inclusiveness like economic inclusion, environmental sustainability, human capability, gender equity, and financial inclusion. We construct a composite inclusive growth index (IGI) using time series data for India over the period 1990 - 2020. Fifteen developmental indicator variables, categorized as economic expansion, environmental sustainability, gender equity, human capabilities, and financial inclusion, are used to construct the present IGI. The two-stage principal component analysis (PCA) method is used to derive the weights of the indicators. Results show that India performed quite well during the period 1991-2000 and 2001-2010 in all aspects of inclusive growth. However, the improvement rates of all dimensions of inclusive growth decidedly slowed down in the recent period (2011-2020). The inclusive growth index increased from 11.925 percent during 1991-2000 to 12.403 percent during 2001-2010 and declined to 2.572 percent during 2011-2020. Our present index measure will help researchers and policymakers to assess the performance of a country to its inclusive growth achievements and to track the time trend over time. Hence, this index measure will be crucial for formulating inclusive growth policies.

Hand-to-mouth (HtM) behavior matters to macroeconomic policies and economic stability, yet its determinants and link to financial access remain underexplored in Asian developing countries. This study addresses this gap using the Global Findex Database 2021 across twenty-seven economies. A novel Financial Access Index (FAI) is constructed via a two-stage principal component analysis (PCA), integrating traditional and digital financial dimensions. A univariate probit model is employed to examine correlations. Results show a negative correlation between financial access and HtM behavior, with individuals in higher-FAI countries being less likely to be HtM. Significant heterogeneity exists across different country groups, subregions, rural and urban areas, and vulnerable populations. Key determinants include tertiary education and income levels. The unemployment rate, share of the informal sector and share of employment working in agriculture are positively associated with HtM behavior, while there is a negative linkage between the Human Development Index (HDI) and the behavior. This study contributes by providing empirical evidence on financial access and HtM behavior in Asian developing countries, offering policy insights to enhance financial access and conduct macroeconomic policies.

This paper examines the impact of FI on bank stability within Ethiopian context, using panel data from 17 commercial banks over the period 2015-2023. Given the scarcity of research focused on the relationship between FI and bank stability in Ethiopia, this paper seeks to address a crucial gap by analyzing both conventional and digital aspects of FI in relation with bank stability. A two-stage principal component analysis (PCA) was conducted to construct a composite FI index, integrating 10 conventional and 5 digital indicators. The study applied a two-step robust system generalized method of moments (GMM) to analyze the effects of FI on bank stability, tests nonlinearities using Lind and Mehlum's (2010) U-test, and examines causality through Dumitrescu-Hurlin (2012) and Juodis et al. (2021) causality tests. The result reveals an inverted U-shaped relationship between FI and bank stability. FI enhances stability up to a 30.3% threshold, beyond which increased transaction costs, information asymmetries, and adverse selection risks weaken stability. Capital adequacy moderates this effect, raising the threshold to 35.1%, but its stabilizing role diminishes at higher levels. Granger causality tests confirm a bidirectional relationship. Additionally, bank efficiency and GDP growth enhance stability, while real interest rates, total assets, and income diversification exert destabilizing effects. This study makes three key contributions. First, it provides the first empirical analysis of the FI-stability nexus in Ethiopia. Second: (i), it develops a multidimensional FI index; (ii), explores both linear and nonlinear relationships, and (iii) examines macroprudential regulation as a moderating factor. Third, it tests causality, offering policy insights. To enhance stability while mitigating risks, policymakers must balance FI expansion, enforce regulatory frameworks, and implement targeted capital requirements. Regulators should strengthen consumer protection and financial literacy, while banks must optimize outreach, manage credit risk, and ensure prudent asset allocation and liquidity management to sustain financial stability.

Constructing a composite financial inclusion index for developing economies

Spatial correlation of pollution of the water resource in Taipei, Taiwan, were examined by analyzing the antibiotic resistance patterns (ARPs) of 96 Escherichia coli colonies, which were isolated from 7 sampling sites in 3 river sections. The ARPs were the growth patterns of isolated E. coli colonies in the medium with seven kinds of antibiotics, including ampicillin, chlortetracycline, erythromycin, oxytetracycline, streptomycin, tetracycline, and salinomycin of different concentrations. The results showed that the survival rate of E. coli decreased with increasing concentration of antibiotics; however, various ARPs under different antibiotics of different concentrations significantly increased both the useful information and complexities. Hierarchical cluster analysis (HCA) and two-stage principal component analysis (PCA) were applied to analyze the spatial correlations and interrelations of distinct ARPs among sampling sites in this study. It was found that the seven sampling sites can be categorized into three groups which may represent three possible pollution characteristics.

This work addresses face recognition for detecting a small and particular set of individuals over a huge population of people. A new approach is developed which uses training samples of both target classes and non-target outliers. Two-stage Principal Component Analysis (PCA) schemes are proposed for flexible feature extraction. Experimental results reveal that the new approach improves the accurate rate of detection significantly.

Multidimensional assessment of financial inclusion is crucial for understanding both the financial aspect of people’s lives and the state’s overall financial situation. The northern territories play a significant role in modern Russia, and it is important to study their financial inclusion. The aim of this study is to compare financial inclusion in the northern regions of Russia between 2000 and 2022 and identify the main trends and factors influencing financial accessibility in these areas. To achieve this goal, we need to identify and analyze the main factors that affect financial accessibility in the northern regions and create a rating based on these factors. This will help us better understand the current situation and make informed decisions about future policies. The approach proposed in this paper, which is based on a two-stage principal component analysis (PCA), allows us to get rid of subjective processes in the weighing of indicators and form a comprehensive assessment of financial well being. This method involves endogenous assignment of weights and the creation of a composite index. The Kaiser criterion is used to identify the main components. As a result of our study, we have determined that the most significant factors influencing financial well-being are the number of operating credit institutions, their branches, and funds (deposits) held by legal entities and individuals, both in rubles and foreign currency. We have also developed financial accessibility indices that allow us to conduct rating assessments of regions and identify significant changes over time. The results of the study will help us to evaluate the effectiveness of the current policy and provide a basis for developing targeted measures to achieve convergence in financial accessibility in northern Russia.

PurposeThe purpose of this paper is to calculate the financial inclusion index and analyze its dynamics in developing countries.Design/methodology/approachThe authors use the two-stage principal component analysis (PCA) method and consider financial technology innovations to improve the accuracy of the financial inclusion index.FindingsThe authors found a downward trend in the financial inclusion index in most developing countries over the study period. The authors also found that a high financial inclusion index is linked to high scores in the Doing Business and high business climate regulation ranking. In addition, the authors observed that the rates of low financial inclusion in developing countries are due to low utilization of and unequal access to financial services.Practical implicationsThe analysis suggests that policymakers in developing countries could invest in digital infrastructure to extend access to financial services in remote areas. They could also encourage financial innovation, particularly in financial technologies, by adopting flexible regulatory frameworks. Promoting the financial inclusion of marginalized groups through targeted initiatives tailored to their needs is another solution. They could also encourage the use of financial services by raising awareness and educating populations through training programs. Finally, to improve the business climate, governments could simplify administrative procedures and promote transparency and legal stability.Originality/valueUnlike previous studies, the use of the two-stage PCA method and the consideration of financial technology (Fintech) innovations such as mobile money in the determinants of the financial inclusion index improve the accuracy of the index.

The present study was carried out to analyze the status of company risk of fifteen selected FMCG companies in India during the period 2003-04 to 2017-18 on the basis of company risk index (CRI). In the present study Two-stage Principal Component Analysis ((TSPCA) was used for the purpose of designing the overall CRI of each of the selected companies. An attempt was also made to identify the impact of the CRI of selected companies on their profitability during the same period adopting regression analysis technique. A notable outcome of the study is that half of the selected companies were placed in the category of higher level of company risk whereas one third of the companies under study found place in the category of lower level of company risk. The study also revealed that high company risk was well compensated by high overall return while high company risk was not at all compensated by high owners’ return in the selected companies during the period under study. No study has so far been made in India in the recent times to analyze company risk applying a CRI which has been formulated adopting Two-Stage Principal Component Analysis (TSPCA) technique. In order to bridge the gap, an attempt has been made in the present paper to design a suitable CRI applying TSPCA for measuring the company risk.

In this paper, a new index of digital financial inclusion is developed using the access, usage, and availability dimensions of digital financial inclusion. The two-stage principal component analysis is applied to develop an index using the IMF financial access survey data for 68 countries from the year 2014-2021. The countries are further divided into four groups using World Bank income classifications. The new index proposed in this study covers 68 countries based on continuous data from the IMF FAS survey. The index is a contribution to the ongoing literature on digital finance and will be used as a device to measure digital financial inclusion. The results show that the high-income countries are technologically advanced and have a higher ranking in digital financial inclusion while the upper middle (UMIC) and lower-middle-income countries (LMIC) are making steady progress with respect to the digitization of the financial sector while low-income countries are less digitally inclusive due to lack of digital infrastructure. Moreover, they have the problem of a lack of digital finance data. International financial institutions i.e. The World Bank, IMF, and national financial institutions such as central banks should work towards a vibrant and digitally inclusive financial sector.

This paper measures economic integration in the Asia-Pacific (AP) region using a composite index. The weights of the index are obtained from a two-stage principal component analysis. In the first stage, we obtain a convergence index to measure the extent of convergence among the main macroeconomic indicators of a sample of AP economies. In the second stage, we use indicators of trade, FDI, and tourism, as well as the convergence index, to compute the weights for the composite index. We found that economic convergence in the AP region increased until 1998 but has since fallen back. The integration of trade, investment, and people flows increased between 1990 and 2000, weakened slightly to 2003, and has since picked up again. Among the 17 sample economies, Singapore, Hong Kong, and Chinese Taipei are the most integrated with the AP region and Indonesia and China are the least integrated.

Accurate three-phase identification from Solid Oxide Fuel Cell (SOFC) anode micrograph is challenged by both noise and intensity inhomogeneity. In this paper, a novel framework is proposed for porous Ni-YSZ cermet anode Optical Microscopy (OM) image segmentation. The proposed framework takes advantage of a statistical model in which an observed image is decomposed into two multiplicative components (bias field and true image) and one additive component (noise). A two-stage Principal Component Analysis with Local Pixel Grouping (LPG-PCA) denoising algorithm is firstly performed to suppress additive noise, it can preserve more image local structural features by modeling a pixel and its nearest neighbors as a vector variable and selecting training samples with similar contents to this variable in a local window for PCA transformation. In order to enhance the robustness to noise, uneven illumination and other outliers, a kernel metric is introduced into fuzzy clustering method embedded with bias field correction for image segmentation. The proposed method has been compared to other state-of-the-art segmentation algorithms on both simulated images and real SOFC anode OM images. Extensive experiments results have demonstrated that the proposed framework can successfully eliminate the influence of both uneven illumination and noise on real Ni/YSZ anode OM images to obtain a better three-phase identification accuracy. The high-quality segmentation results lay firm foundation for accurate microstructural parameter extraction.

Increment-based recursive transformed component statistical analysis for monitoring blast furnace iron-making processes: An index-switching scheme