Sample Selection Bias Research Articles

Digital Therapeutics in Mental Health Care: A Critical Evaluation of Mobile Applications and Online Interventions for Anxiety and Depression

This research study evaluates the effectiveness, usability, and limitations of digital mental health interventions, particularly mobile applications and online platforms, in managing anxiety and depression. As digital therapeutics gain traction as innovative tools in mental health care, their potential for accessibility, scalability, and personalization positions them as valuable complements to traditional therapeutic approaches. The study utilized a cross-sectional design and meta-analysis of quantitative data from clinical trials, peer-reviewed studies, and user feedback. Key findings revealed that digital interventions significantly reduce symptoms of anxiety and depression, with paired t-tests confirming notable symptom relief post-intervention (p < 0.01). Regression analysis highlighted user engagement and personalized content as critical factors, with higher engagement correlating with improved mental health outcomes. Demographic analysis indicated that older participants experienced the most pronounced benefits, underscoring the importance of tailored approaches for different age groups. Limitations included short-term follow-up periods and potential sample selection bias, pointing to the need for more diverse, long-term research. The study concludes that digital therapeutics hold significant promise for enhancing mental health care, recommending future integration with traditional services and the adoption of emerging technologies like artificial intelligence to optimize user engagement and outcomes.

Impact of Adverse Childhood Experiences on Child Development in South America: A Systematic Review

Abstract Background Adverse Childhood Experiences (ACEs) have garnered attention globally for their detrimental effects on children’s development, such as lower communication, gross and fine motor, and personal-social domains. While extensively studied in high-income countries, there remains a gap in understanding their prevalence and impact in low- and middle-income countries (LMICs). This review aimed to identify, evaluate, and summarize the findings of an association between ACEs and children’s developmental and mental health outcomes in South America Methods A systematic review was conducted to investigate the association between ACEs and childhood development in South America. Databases MEDLINE, PsycINFO, Web of Science, Applied Social Sciences Index and Abstracts, Literatura Latino Americana em Ciências da Saúde, IBECS and CINAHL were searched. Selection criteria encompassed studies from Brazil, Colombia, Argentina, Peru, Venezuela, Chile, Ecuador, Bolivia, Paraguay, Uruguay, Guyana and Suriname examining the effects of ACEs on developmental outcomes and mental health disorders in children under 18 years old. Quality assessment aligned with World Health Organization standards was employed. Results Twenty-four studies met the inclusion criteria, with most categorized as low or very low quality. While the majority demonstrated a significant association between ACEs and developmental or mental health outcomes, a few studies reported null findings. Challenges in study quality, such as small sample sizes and selection bias, were identified. Conclusions Despite limitations in study quality, findings underscore the impact of ACEs on child development and mental health in South America. Because of the low quality of the existent studies the next steps should be to grasp a greater understanding of the issue. This review also highlights the urgency for further research and targeted interventions to mitigate the long-term consequences of ACEs in this region. Key messages • ACEs profoundly affect child development and mental health in South America, necessitating urgent attention and intervention. • Addressing the impact of ACEs in South America is critical for fostering healthier developmental trajectories and enhancing public health outcomes.

Climate Risks and Real Gold Returns over 750 Years

Using data that cover the annual period from 1258 to 2023, we studied the link between real gold returns and climate risks. We documented a positive contemporaneous link and a negative predictive link. Our findings further show that the predictive link historically gave rise to significant out-of-sample forecasting gains. The positive contemporaneous link is consistent with the view that investors viewed gold as a safe haven in times of elevated climate risks. The negative predictive link, in turn, is consistent with an overshooting scenario in which the real gold price overshot in response to climate risks, only to return subsequently to a lower value. Our findings should provide important implications for investors and policymakers, given that our analysis covered the longest possible data sample involving the gold market, and hence, was independent of any sample selection bias.

Assessing the impact of migration on the happiness of household women left behind: evidence from Punjab, Pakistan

The concept of happiness is becoming an increasingly significant area of focus in the evaluation of overall quality of life. This research examines the impact of migration on the well-being of women who remain in their place of residence following the migration of their family members. The study employs data from the Multiple Indicators Cluster Survey (2017–2018) in Punjab, Pakistan, and addresses sample selection bias through Propensity Score Matching (PSM). Moreover, as the dependent variable is ordinal, the study employed ordered logistic regression to examine the correlation between migration and happiness, taking into account migration status and other variables. The findings indicate that women from migrant backgrounds tend to benefit from migrating, primarily in terms of enhanced financial resources. In order to gain insight into the varying effects of migration on women’s happiness, the study employed heterogeneity analysis, which revealed that the influence of migration on women’s happiness differs across various areas. In conclusion, the combination of propensity score matching (PSM) with ordered logistic regression and heterogeneity analysis represents a robust methodology for evaluating the impact of migration on women’s perceptions of happiness. The study demonstrates that migration has the potential to improve the quality of life of women who remain in their home countries, particularly those residing in financially disadvantaged households.

The impact of green low-carbon development on public health: a quasi-natural experimental study of low-carbon pilot cities in China.

In recent years, climate change and environmental pollution have posed significant threats to public health. As environmental policies such as low-carbon city initiatives are progressively implemented, their role in enhancing public health has become a topic of growing interest. This study aimed to investigate the relationship between green low-carbon development and public health and to analyze the underlying mechanisms. We utilized data from 271 prefecture-level cities in China spanning from 2007 to 2020, focusing on green low-carbon development, climate change, environmental pollution, and public health. Employing the quasi-natural experimental framework of China's low-carbon city pilot projects, we constructed a multi-site difference-in-differences (DID) model for empirical analysis. Various robustness checks, including parallel trend tests, placebo tests, sample selection bias checks, and adjustments to the temporal and spatial scope of the samples, were conducted to ensure the reliability of the results. Additionally, we explored the positive effects of green low-carbon development on public health through dual mediation pathways involving climate change mitigation and pollution reduction. Finally, we examined the heterogeneity of the results across different city tiers, economic growth rates, levels of technological investment, and green finance development. The findings indicate that green low-carbon development significantly enhances public health, a conclusion supported by robustness tests. Mechanism analysis reveals that the benefits of green low-carbon development on public health are realized through mitigating climate change and reducing environmental pollution. Further analysis reveals that the positive impact on public health is more pronounced in first-and second-tier cities, as well as in cities with faster economic growth, greater technological investment, and more developed green finance sectors. This study highlights the crucial role of urban green low-carbon development in improving environmental quality and public health. In addition to providing empirical evidence that supports the promotion of green low-carbon development in cities, the results point to policy recommendations for enhancing public health. Moreover, the findings contribute to the development of environmental policies and the implementation of the "Healthy China" strategy.

The economic benefit of spearfishing as an impure public good: A case study of invasive Lionfish in Florida

Lionfish (Pterois miles and P. volitans) is a highly invasive species originally from the South Pacific and Indian Oceans. As an effort to control its exponentially growing population, the Florida Fish and Wildlife Conservation Commission has launched a program called “Lionfish Challenge” to promote harvesting of lionfish from Florida waters. The program provides anglers with a unique recreational opportunity because they would need to dive and spearfish to harvest lionfish. Furthermore, participants in the program not only gain utility from spearfishing as a private good but also as a public good, knowing that they are contributing to the ecosystem in Florida waters. This paper contributes to the literature by measuring the economic benefit for participants from spearfishing as an impure public good. Using data provided by the Florida Fish and Wildlife Conservation Commission, a travel cost method was applied to model the demand for lionfish fishing trips. Data included information about counties where lionfish were harvested at the trip-level, but only if participants took a trip and harvested lionfish. Therefore, those who are good at catching lionfish had a higher probability of being included in the data. To account for potential sample selection bias, a probability weight was applied, using the average number of lionfish harvested as a proxy. Results indicate that the per-trip consumer surplus per participant was between $965.89 and $1,597.36, depending on model specifications, with the preferred specification indicating a mean CS of $1,117.72 per trip. The seasonal consumer surplus per participant was indicated to be between $4,550.45 and $3487.91, again, depending on model specification.

Influence of company secretary characteristics on information disclosure violations: evidence from China

AbstractThis study analyzed data from 1999 to 2015 on Chinese listed companies to examine the impact of the Company Law of the People’s Republic of China (2006) on company secretary characteristics and information violations. A cross-sectional estimation was used to explore the impact of the Company Law (2006) on the status and expertise of Chinese company secretaries and information disclosure violations. Propensity score matching addressed the endogeneity problem caused by sample selection bias. The results showed that the Company Law (2006) significantly enhanced the status and expertise of company secretaries, mitigating information disclosure violations among those with higher status or professional ability. However, the interaction of higher status and professional ability adversely increased information disclosure violations. Improvements in the status and expertise of company secretaries also led to increased internal replacements and reduced external punishment for errant company secretaries. These findings have implications for enhancing the quality of information disclosure and controlling future violations. They are valuable to regulators, boards of directors, and investors.

Gender wage gap among highly educated workers: some evidence from Spain

PurposeThe study aims to estimate wage models controlled for sample selection bias and apply the traditional Blinder–Oaxaca decomposition to examine the gender wage gap.Design/methodology/approachThis research provides new evidence concerning the drivers of the gender pay gap for highly educated workers in Spain.FindingsThe results show the existence of empirical evidence about the presence of the gender wage gap among tertiary-educated workers. An interesting conclusion is that holding a master’s degree has a positive impact since it diminishes the unexplained component of the gender pay gap.Research limitations/implicationsThe survey used only analyses the labour insertion of tertiary-educated workers and its temporal scope does not allow us to examine the evolution of the gender wage gap throughout their careers.Social implicationsThe findings indicate that there is room for the implementation of policies aimed at diminishing gender inequality in the labour market even for highly educated workers, which could complement the current Spanish labour legislation regulating the gender pay gap in firms.Originality/valueThis paper bridges two bodies of the economic literature: human capital returns and the gender wage gap. The data used represent a contribution to the economic literature.

Green fund investors and ESG performance: Evidence from China

Using the ESG scores from the Bloomberg Database and the manually filtered green fund investor data, we study the influence of green fund investors on the Chinese A-shares' ESG performance. As we have found, the holding of fund investors who pay attention to sustainable development can improve the firm's ESG performance, and this improvement is more pronounced in state-owned enterprises, heavily polluting industries, and after the green policy announcement. Our findings are robust after considering the reverse causality endogeneity concern and sample selection bias. In addition, the holdings of green fund investors favor the company's status as a green index constituent and its long-term financial performance. Further, the mechanism test reveals the influencing channel of this improvement and supports that it is long-term green fund investors themselves improving the firms' ESG performance and can improve a firm's ESG performance by attracting other long-term investors and new mutual fund investors, and increasing the level of media scrutiny pressure. Our paper contributes to figuring out the impact of institutional holding on ESG development and further points out the source of this influence.

Faktor Kunci Kepatuhan Pajak UMKM E-Commerce di DKI Jakarta : Modernisasi Sistem Pajak, Religiusitas, Love of Money, dan Sanksi Pajak

Purpose: The purpose of this study is to examine how Religiosity, love of money, tax sanctions, and modernization of the tax system affect tax compliance of MSME businesses. Methodology: The sampling method is based on the formula of Roscoe's theory. Using the SmartPLS 4.0 program for PLS-SEM data analysis, the researcher tested the hypothesis at a significance level of 5%. Results: the results of the study, taxpayer compliance in e-commerce is significantly influenced by the modernization of the tax system for MSMEs; taxpayer compliance in is not significantly influenced by religiosity for the same business; and e-commerce is significantly influenced by love of money. In terms of MSME e-commerce tax compliance, tax sanctions do not have a significant effect. Limitations: This study may only cover a small portion of e-commerce MSMEs in DKI Jakarta, so the results may not fully represent the entire population of e-commerce MSMEs in the area if the sample used is not taken randomly or there is a tendency to select certain respondents, then the results of the study can be influenced by sample selection bias. Contribution: This study adds to the existing literature on tax compliance, particularly in the context of MSMEs in the e-commerce sector. It provides new insights into how factors such as tax system modernization, religiosity, love of money, and tax sanctions interact to influence tax compliance. By testing a theoretical model involving various factors influencing tax compliance, this study strengthens or challenges existing theories related to tax compliance behavior, particularly in the context of the digital economy

Does agricultural knowledge technical training promote adoption of sustainable agricultural practices?

ABSTRACT The promotion and adoption of sustainable agricultural practices is an important issue in China’s agricultural development policy, particularly because it offers a path to protecting land and water resources to ensure food security. Despite tremendous efforts in encouraging farmers to adopt sustainable agricultural practices (SAPs), adoption has remained low. The lack of relevant information on the use and benefits of these SAPs has been recognized as a major constraint limiting their adoption. Agricultural knowledge and technology training (AKT) could be leveraged to bridge this gap to increase their adoption. Given the paucity of evidence, this study investigates the impact of participation in AKT on SAPs using data on a sample of farmers from Sichuan province of China. We apply the Endogenous-treatment Poisson regression to account for sample selection bias. The empirical results reveal that AKT improved the adoption intensity of SAPs by 74.6%, indicating that policy makers and related stakeholders should provide more agricultural schooling and training to improve farmers’ human capital endowment. These findings have implication on the provision of support for the development of rural policies to promote internet access and basic infrastructure to accelerate the adoption of these multiple sustainable practices.

Artificial intelligence for optimizing recruitment and retention in clinical trials: a scoping review.

The objective of our research is to conduct a comprehensive review that aims to systematically map, describe, and summarize the current utilization of artificial intelligence (AI) in the recruitment and retention of participants in clinical trials. A comprehensive electronic search was conducted using the search strategy developed by the authors. The search encompassed research published in English, without any time limitations, which utilizes AI in the recruitment process of clinical trials. Data extraction was performed using a data charting table, which included publication details, study design, and specific outcomes/results. The search yielded 5731 articles, of which 51 were included. All the studies were designed specifically for optimizing recruitment in clinical trials and were published between 2004 and 2023. Oncology was the most covered clinical area. Applying AI to recruitment in clinical trials has demonstrated several positive outcomes, such as increasing efficiency, cost savings, improving recruitment, accuracy, patient satisfaction, and creating user-friendly interfaces. It also raises various technical and ethical issues, such as limited quantity and quality of sample size, privacy, data security, transparency, discrimination, and selection bias. While AI holds promise for optimizing recruitment in clinical trials, its effectiveness requires further validation. Future research should focus on using valid and standardized outcome measures, methodologically improving the rigor of the research carried out.

The State-of-the-Art of Mycobacterium chimaera Infections and the Causal Link with Health Settings: A Systematic Review.

(1) Background. A definition of healthcare-associated infections is essential also for the attribution of the restorative burden to healthcare facilities in case of harm and for clinical risk management strategies. Regarding M. chimaera infections, there remains several issues on the ecosystem and pathogenesis. We aim to review the scientific evidence on M. chimaera beyond cardiac surgery, and thus discuss its relationship with healthcare facilities. (2) Methods. A systematic review was conducted on PubMed and Web of Science on 7 May 2024 according to PRISMA 2020 guidelines for reporting systematic reviews, including databases searches with the keyword "Mycobacterium chimaera". Article screening was conducted by tree authors independently. The criterion for inclusion was cases that were not, or were improperly, consistent with the in-situ deposition of aerosolised M. chimaera. (3) Results. The search yielded 290 eligible articles. After screening, 34 articles (377 patients) were included. In five articles, patients had undergone cardiac surgery and showed musculoskeletal involvement or disseminated infection without cardiac manifestations. In 11 articles, respiratory specimen reanalyses showed M. chimaera. Moreover, 10 articles reported lung involvement, 1 reported meninges involvement, 1 reported skin involvement, 1 reported kidney involvement after transplantation, 1 reported tendon involvement, and 1 reported the involvement of a central venous catheter; 3 articles reported disseminated cases with one concomitant spinal osteomyelitis. (4) Conclusions. The scarce data on environmental prevalence, the recent studies on M. chimaera ecology, and the medicalised sample selection bias, as well as the infrequent use of robust ascertainment of sub-species, need to be weighed up. The in-house aerosolization, inhalation, and haematogenous spread deserve experimental study, as M. chimaera cardiac localisation could depend to transient bacteraemia. Each case deserves specific ascertainment before tracing back to the facility, even if M. chimaera represents a core area for healthcare facilities within a framework of infection prevention and control policies.

The carbon emission reduction effect of green fiscal policy: a quasi-natural experiment

Carbon emission reduction is crucial for mitigating global climate change, and green fiscal policies, through providing economic incentives and reallocating resources, are key means to achieve carbon reduction targets. This paper uses data covering 248 cities from 2003 to 2019 and applies a multi-period difference-in-differences model (DID) to thoroughly assess the impact of energy conservation and emission reduction (ECER) fiscal policies on enhancing carbon emission (CE1) reduction and carbon efficiency (CE2). It further analyzes the mediating role of Green Innovation (GI), exploring how it strengthens the impact of ECER policies. We find that: (1) ECER policies significantly promote the improvement of carbon reduction and CE2, a conclusion that remains robust after excluding the impacts of concurrent policy influences, sample selection biases, outliers, and other random factors. (2) ECER policies enhance CE1 reduction and CE2 in pilot cities by promoting green innovation, and this conclusion is confirmed by Sobel Z tests. (3) The effects of ECER policies on CE1 reduction and the improvement of CE2 are more pronounced in higher-level cities, the eastern regions and non-resource cities. This research provides policy makers with suggestions, highlighting that incentivizing green innovation through green fiscal policies is an effective path to achieving carbon reduction goals.

Do Protective Tariffs Influence Firms’ Competitive Stance? Application of a Competitive Leverage Model in The Presence of Simultaneous Equation and Sample Selectivity Bias

ABSTRACT: We propose a Competitive Leverage model, and apply it to analyze the impact of tariffs on the attitudes of domestic import-competing firms, especially regarding their disincentives to maintain a Competitive Stance against foreign competitors in the domestic market. We propose that tariffs are a disincentive to the pursuit and maintenance of production efficiency in firms and industries. When countries implement tariff protection for their domestic firms, the most common excuse sounds reasonable, except that it is also economically flawed. While the short-run impacts of such a measure might seem plausible, its long-term effects appear to be less than favorable, and may, in fact, turn out to be damaging to the economy. The paper applies the competitive leverage concept in a unique way to highlight how tariffs distort the output levels of domestic firms, and gives an empirical analysis of the model, using USA data to verify the predictions of the model. Particularly, we develop a Cournot-competition type Competitive Leverage model, and use it to examine the role played by tariffs as a disincentive to a typical firm’s pursuit and maintenance of production efficiency. The competitive leverage model is formulated and applied to verify the effects of tariff protection from the typical domestic firm’s strategic interaction standpoint. We further apply cross-sectional data to carry out an empirical analysis of the model, to verify how tariffs impact the domestic firm’s output and pricing decisions. Our findings would enable us to contribute to the debate about the need to remove protective tariffs, on the grounds that tariffs do not only enable domestic firms to operate inefficiently, but also tends to distort the output and pricing outcomes that would otherwise have been realized in the free market. The results from the study are used to propose some major policy implications of imposing tariff protection, among which are that there is need for implementation of more deliberately sustained Research and development program on the part of domestic firms in the economy, to enable them withstand vigorous competition in a free-trade world. Also, since protective tariffs significantly increase firms’ profit rates, which in turn enables them to unduly earn and accumulate economic rents that amount to inefficiencies and distortions in free-market prices and quantities outcomes, governments should always resist any pressures from big businesses to impose protective tariffs against competition from international rivals. Yet a clear public policy implication from this paper is that, at the macro level, as the results suggest that a government policy that aims at protecting domestic firms through imposition of tariffs may have an adverse effect on the firms’ competitive stance in the industry, a practical message is for the government to impose only a moderate tariff at the most, if it must, especially as it relates to agricultural products.

Sample selection bias in non-traditional lending: A copula-based approach for imbalanced data

Credit scoring models for non-traditional lending channels, such as peer-to-peer (P2P) lending platforms, are usually estimated only on the sample of accepted applicants. This may lead to biased estimates of the risk drivers. This issue can be addressed using a reject inference technique that includes the characteristics of rejected applicants in the model. Due to the low numbers of accepted applicants and default records, credit scoring models usually face a class imbalance problem. However, previous literature on sample selection models for credit scoring does not address the class imbalance issue. To fill this gap, we extend the Generalised Extreme Value (GEV) regression model for binary data to the sample selection framework. We consider the quantile function of the GEV distribution as a link function in both the selection and outcome equations. We use the copula function to model the dependence structure between the two equations for its flexibility. This proposal is called the Sample Selection Generalised Extreme Value (SSGEV) model and it is implemented in the R package BivGEV. We apply this model to a comprehensive dataset provided by Lending Club, and we show that parameter estimates obtained only on accepted P2P applicants are biased and coherently with the literature. The SSGEV model achieves a higher predictive accuracy than those obtained using univariate approaches or a sample selection probit model. Our proposal also provides more conservative estimates of the Value-at-Risk and the Expected Shortfall.

The impact of financial inclusion on rural–urban households welfare inequality in Ghana: A decomposition analysis

AbstractThis article examined the impact of financial inclusion on rural–urban households' welfare inequality in Ghana using nationally representative survey data sourced from the seventh round of the Ghana Living Standard Survey. The article used a multidimensional financial exclusion index and the real per adult equivalent measures of total annual household consumption expenditure as measures of financial inclusion and welfare, respectively. The article employed the instrumental variable estimation technique to account for the issues of endogeneity and sample selectivity bias associated with measuring financial inclusion. The estimated results from recentered influenced function‐Ordinary Least Squares of the unconditional quantile regression and the Oaxaca‐Blinder techniques show significant rural–urban welfare gaps in favor of urban households at the mean and across the selected quantiles. The study also found that differences in financial inclusion between rural and urban households contribute significantly to the welfare gaps, while the economic returns to financial inclusion reduce the welfare gaps both at the mean and the selected quantiles. The study recommends that policies aimed at improving financial inclusion as well as strengthening financial institutions in rural areas be put in place to help reduce the rural–urban welfare inequality in Ghana.

Motivating for environmental protection: Evidence from county officials in China

This paper investigates the impact of changes in the officials’ performance evaluation system on ecological environment quality, as well as the effect of ecological improvements on officials’ promotion prospects. Analyses are conducted using the changes in the officials’ evaluation mechanism in China’s ecological function counties in 2013 as a quasi-natural experiment, incorporating a newly developed set of county-level comprehensive ecological environment index data and manually collated data on county leaders. Multiple methods are employed to address issues such as sample selection bias, reverse causality, and heterogeneity of treatment effects. The empirical analysis shows that the adjustment of officials’ performance evaluation indicators contributes to the improvement of ecological environment quality. This effect is more pronounced in regions where GDP evaluation is abolished, regions with lower economic development but better ecological environment foundations, regions closer to provincial capitals, and officials with shorter tenure, younger age, and male gender. The rationale behind this policy is that post-reform improvements in the ecological environment will increase the promotion prospects of officials in ecological function counties, enable these areas to secure additional ecological transfer payments, thereby enhancing their capacity for environmental expenditure, and establish a credible commitment mechanism for central-local contracts. This study not only examines the relationships between political incentives for officials and environmental protection, but also enriches the literature on environmental decentralization, multi-target governance, and environmental political economy.

Influence of educational composition on firm innovation and performance

ABSTRACT Despite a strong focus on innovation from both politicians and managers, our current understanding of the relationship between managers’ education level and the educational composition of the workforce in terms of innovation and their joint association with performance remains limited. For example, while most studies include workforce quality as a control, and recognize its importance, there is still little knowledge about how it influences the innovation process. The data and estimation framework used in this study enable for a detailed analysis of the importance of both managers’ and workers’ skill intensity and workers’ skill diversity throughout the sequential innovation process that transforms ideas into valuable innovation in three stages. In addition, the availability of panel data allows us to account for various econometric issues, such as sample selection bias, reverse causality, simultaneity, and measurement errors. We conclude that educated managers, together with a balanced workforce across education length and field enhance both innovation and performance. Even more interestingly, we show that the educational level of managers influences the innovation process primarily through the recruitment of more educated workers with diverse educations. And the importance of including the indirect effect of educational composition through R&D decisions on the likelihood of innovation.

Digital finance and MSME performance in India: evidence from World Bank Enterprise Survey data

PurposeThe impact of digitalisation on smaller firms remains sparsely studied across emerging economies. The paper aims to examine the relationship between digital adoption and multiple performance parameters of micro, small and medium enterprises (MSME) in a prominent emerging economy.Design/methodology/approachThe study employs data from the World Bank Enterprise Survey (WBES) 2022, capturing 9,024 Indian MSME firms spread across the country. Performance indicators are derived from growth in sales, employment and labour productivity (LPROD). Multiple regression estimates are derived that also correct for sample selection bias using Heckman’s two-step process.FindingsDigital proliferation is found to increase as firms mature up in terms of age, size and constitution. A significant difference could also be observed in business performance across digital and non-digital businesses, with sales growth (SG) and productivity higher for digital firms. Digital financial variables are found to have a significant impact on SG but not as much in the case of employment growth and LPROD. The results are robust to correction for sample selection bias in digital adoption using inverse mills ratio (IMR).Practical implicationsThe study highlights digital adoption gaps across various strata of MSMEs, highlighting lower adoption when firms are younger, smaller and lacking formal constitutional setup. Digital variables indicating positive association with SG highlight the need for concerted efforts at the public policy level for building appropriate skills and infrastructure for micro and small enterprises to boost their digital adoption to promote growth.Originality/valueThere is a lack of micro-level empirical evidence measuring the impact of advanced digital technology usage on multiple aspects of enterprise performance amongst micro and small firms. The study deploys unique digital variables including TReDS and use of online credit applications to assess the impact on business performance. The findings provide insights for practice and public policy, besides making the case for a higher focus on launching digital initiatives for smaller enterprises.