Counterfactual Framework Research Articles

Mitigating Confounding Bias in Practical Recommender Systems With Partially Inaccessible Exposure Status.

To improve user experience, recommender systems have been widely used on many online platforms. In these systems, recommendation models are typically learned from positive/negative feedback that are collected automatically. Notably, recommender systems are a little different from general supervised learning tasks. In recommender systems, there are some factors (e.g., previous recommendation models or operation strategies of a online platform) that determine which items can be exposed to each individual user. Normally, the previous exposure results are not only relevant to the instances' features (i.e., user or item), but also affect their feedback ratings, thus leading to confounding bias in the recommendation models. To mitigate this bias, researchers have already provided a variety of strategies. However, there are still two issues that are underappreciated: 1) previous debiased RS approaches cannot effectively capture recommendation-specific, exposure-specific and their common knowledge simultaneously; 2) the true exposure results of the user-item pairs are partially inaccessible, so there would be some noises if we use their observability to approximate it as existing approaches. Motivated by this, we develop a novel debiasing recommendation approach. More specifically, we first propose a mutual information-based counterfactual learning framework based on the causal relationship among the instance features, exposure status, and ratings. This framework can 1) capture recommendation-specific, exposure-specific and their common knowledge by explicitly modeling the relationship among the causal factors, and 2) achieve robustness towards partially inaccessible exposure results by a pairwise learning strategy. Under such a framework, we implement an optimizable loss function with theoretical analysis. By minimizing this loss, we expect to obtain an unbiased recommendation model that reflects the users' real interests. Meanwhile, we also prove that our loss function has robustness towards the partial inaccessibility of the exposure status. Finally, extensive experiments on public datasets manifest the superiority of our proposed method in boosting the recommendation performance.

Assessing the impact of COVID-19 interventions on the hand, foot and mouth disease in Guangdong Province, China: a Bayesian modeling study.

The non-pharmaceutical interventions (NPIs) against COVID-19 may have affected the transmission of hand, foot and mouth disease (HFMD). We aimed to assess the impact of the NPIs on HFMD in the high epidemic area of HFMD, Guangdong Province. The data of HFMD cases, etiological information, and meteorological factors in Guangdong from January 1, 2012, to December 31, 2021, were collected. Using a Bayesian structural time series (BSTS) model integrated counterfactual framework, we assessed the effect of NPIs on HFMD by different intervention periods, populations (gender, age, occupation), and cities. We further explored the correlation between the reduction of HFMD and socioeconomic factors in 21 cities. A total of 351,217 HFMD cases were reported and 455,327 cases were averted in Guangdong Province during 2020-2021 with a reduction of 84.94% (95%CI: 81.63-87.22%) in 2020 and 29.49% (95%CI: 15.26-39.54%) in 2021. The impact of NPIs on HFMD differed by age and gender. The effects of NPIs were more remarkable for children aged 0-2 years and scattered children. We found that the relative reductions in 21 cities were related to the composition ratio of children and COVID-19 incidence. The reduction of HFMD incidence was significantly associated with COVID-19 NPIs, and school closure was an effective intervention to prevent HFMD outbreaks. Our findings will contribute to the development of HFMD prevention and control measures.

The Mediating Role of Digital Competence in the Associations Between the Factors Affecting Healthcare Utilization and Access to Care.

Objectives: To examine with a population-based longitudinal survey design whether poor health, longstanding activity limitation, impaired cognitive functioning, mental distress, or loneliness predict poor access to healthcare and whether digital competence mediates these associations. Methods: The data were from the longitudinal FinHealth -survey gathered in Finland in 2017 and 2020 including 3,771 respondents (57.1% women). Linear regression analyses were used to examine the associations of factors affecting healthcare utilization with access to care adjusted for age, sex, and education. Counterfactual causal mediation framework was used to examine the mediating role of digital competence in the relationships among these factors and access to healthcare. Results: Factors affecting healthcare utilization were associated with poor access to care and these associations were partly mediated by low digital competence. Low digital competence mediated 12%, 9% and 8%, of the associations of impaired cognitive functioning, longstanding activity limitation, and loneliness with poor access to care, respectively. Conclusion: According to our results, one way to improve the access to healthcare among vulnerable groups could be to improve their digital competence.

Can internet use promote farmers to adopt chemical fertilizer reduction and efficiency enhancement technology in China?-an empirical analysis based on endogenous switching probit model.

This study examines the impact of internet usage on farmer's adoption behavior of fertilizer reduction and efficiency enhancement technologies in China. Based on 1,295 questionnaires in Henan Province, this study constructs a counterfactual analysis framework and used endogenous switching probit model to analyze the effects and pathways of internet usage on farmer's adoption behavior of chemical fertilizer reduction and efficiency enhancement technologies. The results indicate that. (1) The proportion of farmers adopting chemical fertilizer reduction and efficiency enhancement technologies is 60.15%, while the proportion of farmers not adopting these technologies is 39.85%. (2) Internet usage directly influences farmers' adoption of fertilizer reduction and efficiency enhancement technologies. According to counterfactual assumption analysis, if farmers who currently use the Internet were to stop using it, the probability of them adopting these technologies would decrease by 28.09%. Conversely, for farmers who do not currently use the Internet, if they were to start using it, the probability of them adopting fertilizer reduction and efficiency enhancement technologies would increase by 40.67%. (3) Internet usage indirectly influences farmers' adoption behavior through mediating pathways of expected benefits and risk perception. In addition, social networks negatively moderate the impact of internet usage on farmers' behavior of chemical fertilizer reduction and efficiency enhancement technologies.

A Meta-Learner Framework to Estimate Individualized Treatment Effects for Survival Outcomes

One crucial aspect of precision medicine is to allow physicians to recommend the most suitable treatment for their patients. This requires understanding the treatment heterogeneity from a patient-centric view, quantified by estimating the individualized treatment effect (ITE). With a large amount of genetics data and medical factors being collected, a complete picture of individuals’ characteristics is forming, which provides more opportunities to accurately estimate ITE. Recent development using machine learning methods within the counterfactual outcome framework shows excellent potential in analyzing such data. In this research, we propose to extend meta-learning approaches to estimate individualized treatment effects with survival outcomes. Two meta-learning algorithms are considered, T-learner and X-learner, each combined with three types of machine learning methods: random survival forest, Bayesian accelerated failure time model and survival neural network. We examine the performance of the proposed methods and provide practical guidelines for their application in randomized clinical trials (RCTs). Moreover, we propose to use the Boruta algorithm to identify risk factors that contribute to treatment heterogeneity based on ITE estimates. The finite sample performances of these methods are compared through extensive simulations under different randomization designs. The proposed approach is applied to a large RCT of eye disease, namely, age-related macular degeneration (AMD), to estimate the ITE on delaying time-to-AMD progression and to make individualized treatment recommendations.

Causal inference in misinformation and conspiracy research

Psychological research has provided important insights into the processing of misinformation and conspiracy theories. Traditionally, this research has focused on randomized laboratory experiments and observational (non-experimental) studies seeking to establish causality via third-variable adjustment. However, laboratory experiments will always be constrained by feasibility and ethical considerations, and observational studies can often lead to unjustified causal conclusions or confused analysis goals. We argue that research in this field could therefore benefit from clearer thinking about causality and an expanded methodological toolset that includes natural experiments. Using both real and hypothetical examples, we offer an accessible introduction to the counterfactual framework of causality and highlight the potential of instrumental variable analysis, regression discontinuity design, difference-in-differences, and synthetic control for drawing causal inferences. We hope that such an approach to causality will contribute to greater integration amongst the various misinformation- and conspiracy- adjacent disciplines, thereby leading to more complete theories and better applied interventions.

FGF-23, Left Ventricular Hypertrophy, and Mortality in Patients With CKD: A Revisit With Mediation Analysis

BackgroundIn patients with chronic kidney disease (CKD), fibroblast growth factor (FGF)-23 is suspected to cause death or cardiovascular disease by inducing left ventricular hypertrophy (LVH). ObjectivesThis study aims to quantify the mediational effect of LVH in the hypothetical causal pathway from FGF-23 to long-term adverse outcomes. MethodsFrom 3,939 adults with CKD stages 2 to 4 enrolled in the CRIC (Chronic Renal Insufficiency Cohort) study, 2,368 participants with available data of FGF-23, left ventricular mass index at 1 year, and covariates were included. We employed linear and Cox proportional hazards regression models to investigate the association between FGF-23 and LVH, all-cause mortality, atrial fibrillation (AF), or congestive heart failure (CHF). Mediation analysis was used within a counterfactual framework to decompose the effect of FGF-23 into natural direct and indirect effects. ResultsAmong 2,368 participants (mean age: 57.7 years, 1,252 males, median FGF-23 level: 138.8 RU/mL), left ventricular mass index was positively correlated with FGF-23. During a median of 12.0, 11.1, and 11.1 years, FGF-23 was associated with all-cause mortality (HR: 1.62, 95% CI: 1.24-2.12), AF (HR: 1.58, 95% CI: 1.12-2.24), and CHF (HR: 1.32, 95% CI: 0.95-1.84) when the highest quartile was compared to the lowest quartile. LVH mediated 7.4%, 11.2%, and 21.9% of the effect of FGF-23 on all-cause mortality, AF, and CHF, respectively. ConclusionsIn CKD patients, FGF-23 had a minor effect on the development of long-term adverse outcomes through LVH. Other potential mediators and the validity of negative effect of FGF-23 should be explored.

Can cognitive inflexibility reduce symptoms of anxiety and depression? Promoting the structural nested mean model in psychotherapy research

ABSTRACT Objective To estimate the causal effect of executive functioning on the remission of depression and anxiety symptoms in an observational dataset from a vocational rehabilitation program. It is also an aim to promote a method from the causal inference literature and to illustrate its value in this setting. Method With longitudinal (four-time points over 13 months) data from four independent sites, we compiled a dataset with 390 participants. At each time point, participants were tested on executive function and self-reported symptoms of anxiety and depression. We used g-estimation to evaluate whether objectively tested cognitive flexibility affected depressive/anxious symptoms and tested for moderation. Multiple imputations were used to handle missing data. Results The g-estimation showed a strong causal effect of cognitive inflexibility reducing depression and anxiety and modified by education level. In a counterfactual framework, a hypothetical intervention that could lower cognitive flexibility seemed to cause improvement in mental distress at the subsequent time-point (negative sign) for low education. The less flexibility, the larger improvement. For high education, the same but weaker effect was found, with a change in sign, negative during the intervention and positive during follow-up. Discussion An unexpected and strong effect was found from cognitive inflexibility on symptom improvement. This study demonstrates how to estimate causal psychological effects with standard software in an observational dataset with substantial missing and shows the value of such methods.

Potential Mediating Roles of Children's Health-Related Quality of Life and Weight-Related Behaviors in the Relationship Between Socio-Educational Advantage and Weight Status.

Background: Socioeconomic status is inversely associated with weight status in developed countries. Underlying mechanisms are still to be clarified. Our aim was to determine if weight-related behaviors and health-related quality of life (HRQoL) mediate the relationship between socio-educational advantage and weight status in Australian children 9 to 13 years of age. Methods: Secondary analysis of data collected by two cluster randomized trials (2019 wave). We measured children's (n = 3978) height, weight, diet, physical activity, sedentary behavior, and HRQoL. Socio-.educational advantage was assessed at school level using the Index of Community Socio-Educational Advantage (ICSEA). A counterfactual framework was used to explore potential mediators in the relationship between socio-educational disadvantage and (1) overweight/obesity and (2) BMI z-score (BMIz). Results: Low socio-educational advantage was associated with increased overweight/obesity and BMIz. The overweight/obesity association was mediated by sedentary behavior (natural indirect effect as a proportion of total, 7.5%) sugar-sweetened beverage (SSB) consumption (12.7%), physical functioning (11.9%), psychosocial health (10.9%), school (6.8%) and social functioning (15.6%), and total HRQoL score (13.8%). The ICSEA-BMIz relationship was mediated by sedentary behavior (5.7%), sleep duration (4.1%), SSB (10.6%), physical functioning (9.9%), psychosocial health (9.1%), school (5.5%) and social (13.7%) functioning, and total HRQoL score (11.7%). Conclusion: Victorian Children with low socio-educational advantage were more likely to be living with overweight or obesity. This relationship was mediated by children's sedentary behavior, SSB consumption, and HRQoL. Trial Registration: Australian New Zealand Clinical Trials Registry (ANZCTR): ACTRN12616000980437 (registered July 26, 2016, retrospectively registered) and ACTRN12618001986268 (registered December 11, 2018, prospectively registered). https://www.anzctr.org.au/Trial/Registration.

Avoided wildfire impact modeling with counterfactual probabilistic analysis.

Assessing the effectiveness and measuring the performance of fuel treatments and other wildfire risk mitigation efforts are challenging endeavors. Perhaps the most complicated is quantifying avoided impacts. In this study, we show how probabilistic counterfactual analysis can help with performance evaluation. We borrow insights from the disaster risk mitigation and climate event attribution literature to illustrate a counterfactual framework and provide examples using ensemble wildfire simulations. Specifically, we reanalyze previously published fire simulation data from fire-prone landscapes in New Mexico, USA, and show applications for post-event analysis as well as pre-event evaluation of fuel treatment scenarios. This approach found that treated landscapes likely would have reduced fire risk compared to the untreated scenarios. To conclude, we offer ideas for future expansions in theory and methods.

3 Fluoride Exposure and Hypothyroidism in Pregnant Women: A Potential Mechanism of Fluoride Neurotoxicity

Objective:Fluoride exposure has been associated with thyroid dysfunction, but fluoride's impact on thyroid function in pregnancy is unclear, especially during early gestation when the fetus is dependent on maternal thyroid hormone. We examined the potential thyroid-disrupting effects of maternal fluoride exposure in pregnancy and tested whether thyroid disruption in pregnancy mediates the association between maternal fluoride exposure and child intelligence quotient (IQ) among Canadian mother-child dyads living in areas with optimal fluoridation.Participants and Methods:We measured fluoride concentrations in drinking water and in spot urine samples collected in each trimester from pregnant women enrolled in the Maternal-Infant Research on Environmental Chemicals study. We also measured thyroid hormone (thyroid stimulating hormone [TSH], free thyroxine [FT4], and total thyroxine [TT4]) levels during the first trimester of pregnancy and categorized women as euthyroid (n=1301), subclinical hypothyroid (n=100), or primary hypothyroid (n=28). Those categorized as primary hypothyroid were combined with an additional 79 women who reported clinical diagnoses at time of study enrolment (total n=107). In a sample of 1508 women, we used logistic regression to estimate the association between fluoride exposure and risk of either subclinical or primary hypothyroidism, separately, and linear regression to estimate associations between fluoride exposure and women's thyroid hormone levels (TSH, FT4, TT4). We tested effect modification by child sex and thyroid peroxidase (TPO) antibody status. In a subsample of 439 mother-child pairs, we measured child Full-Scale IQ (FSIQ) at 3-4 years of age using the Wechsler Preschool and Primary Scale of Intelligence. We used linear regression to test associations between maternal hypothyroidism or thyroid hormone levels, and children's FSIQ scores. Finally, mediation analysis in the counterfactual framework was used to estimate the proportion of the effect of maternal fluoride exposure on child FSIQ mediated by maternal hypothyroidism, through evaluation of the natural direct (not through hypothyroidism) and indirect (through hypothyroidism) effects.Results:Using categorical measures of thyroid status, a 0.5 mg/L increase in water fluoride concentration was associated with a 1.64 (95% confidence interval [CI], 1.04 to 2.58) increased odds of primary hypothyroidism. This association was stronger among women with normal TPO antibody levels (< 5.61 IU/mL) (odds ratio, 2.80; 95% CI, 1.24 to 6.36). In contrast, we did not find a significant association between maternal urinary fluoride and hypothyroidism. For continuous measures of thyroid hormone levels, a 1 mg/L increase in maternal urinary fluoride was associated with a 35% (p=0.01) increase in TSH among women pregnant with a female fetus. In our subsample analyses, children born to women with primary hypothyroidism had lower FSIQ than children of euthyroid women, especially among boys (B, 8.78; 95% CI, -16.78 to -0.79). In contrast, maternal TSH, FT4, and TT4 levels were not significantly associated with child FSIQ scores. Maternal primary hypothyroidism did not significantly mediate the relationship between maternal water fluoride concentration and child FSIQ (p natural indirect effect= .35).Conclusions:Fluoride in drinking water may increase the risk of hypothyroidism in pregnancy. Thyroid dysfunction in pregnancy may be one mechanism underlying developmental neurotoxicity of fluoride.

Socioeconomic inequalities in type 2 diabetes and job demands/control/support - The Maastricht Study

Abstract Background Low socioeconomic position (SEP) is an important determinant of Type 2 Diabetes Mellitus (T2DM). Adverse environments in the exposome might be involved; however, the environmental factors are under-studied compared to lifestyle. We explored low job control, high job demands, and low job support as pathways between SEP and T2DM. Methods Cross-sectional and longitudinal data from 8,090 participants of The Maastricht Study were used. Prevalent T2DM was measured by an oral glucose tolerance test and incident T2DM was self-reported in annual follow-up questionnaires. SEP was operationalized by baseline measures of education, occupation, and income. The work stressors were measured by questionnaires at baseline. For Cox regression, the survival time was computed by midpoint imputation. The associations of SEP, job demands, control, and support with T2DM were examined as well as the mediating role of the work stressors by using a counterfactual framework. Results 2.8% (N = 172) of the participants without T2DM at baseline reported incident T2DM. People with lower SEP were more likely to report T2DM during the follow-up course (e.g.; education HR = 2.21, 95%CI: 1.53-3.20) and more often had prevalent T2DM. Low job control was associated with prevalent T2DM (OR = 1.44 95%CI: 1.25-1.67), but not with incident T2DM. Job control explained 7.23% of the relationship between income and prevalent T2DM. Job demand suppressed the relationship of education (3.65%) and occupation (3.72%) with prevalent T2DM. Conclusions Our findings provide modest evidence for environmental injustice in T2DM exposome. The substantial higher risks of diabetes in low SEP is to a small extent explained by lower control at work. Furthermore, by having lower psychosocial job demands, they are protected against T2DM. Key messages • Job demands and control play a role in SEP and prevalent T2DM relationship. • Work stressors might not be a major target for tackling socioeconomic inequalities in type 2 diabetes.

An in-depth examination of requirements for disclosure risk assessment

The use of formal privacy to protect the confidentiality of responses in the 2020 Decennial Census of Population and Housing has triggered renewed interest and debate over how to measure the disclosure risks and societal benefits of the published data products. We argue that any proposal for quantifying disclosure risk should be based on prespecified, objective criteria. We illustrate this approach to evaluate the absolute disclosure risk framework, the counterfactual framework underlying differential privacy, and prior-to-posterior comparisons. We conclude that satisfying all the desiderata is impossible, but counterfactual comparisons satisfy the most while absolute disclosure risk satisfies the fewest. Furthermore, we explain that many of the criticisms levied against differential privacy would be levied against any technology that is not equivalent to direct, unrestricted access to confidential data. More research is needed, but in the near term, the counterfactual approach appears best-suited for privacy versus utility analysis.

The role of differential exposure and susceptibility to heavy drinking linking income inequalities and tooth loss: Aninvestigation of the alcohol harm paradox using a four-way decomposition analysis.

To examine the extent to which the effect of income inequalities on tooth loss is attributable to differential exposure and susceptibility to heavy drinking in older Brazilian adults. We conducted a secondary analysis using data from The Brazilian Longitudinal Study of Ageing (ELSI-Brazil 2015-2016), a nationally representative sample of community-dwelling people aged 50 years and over. Causal mediation analysis based on the counterfactual outcome framework decomposed the effect of income on tooth loss mediated by heavy drinking into four components (four-way decomposition): controlled direct effect (neither mediation nor interaction), reference interaction (interaction only), mediated interaction (both mediation and interaction) and pure indirect effect (mediation only). Proportions of effect attributable to each component were calculated to estimate the differential exposure (the sum of the third and fourth components) and differential susceptibility (the sum of the second and third components) to heavy drinking. The analytical sample comprised 8114 participants. After adjusting for covariates, 7.3% (95% CI: 3.8%; 10.9%) and -39.5% (95% CI: -75.8%; -3.3%) of the effects of income on tooth loss were attributable to differential exposure and susceptibility to heavy drinking, respectively, consistent with the alcohol harm paradox. When setting non-functional dentition as outcome, only the effect of differential susceptibility remained (-81.7% [95% CI: -128.2%; -35.2%]). Our findings suggest that individuals of low-income groups appear to be more susceptible to the effects of heavy drinking on tooth loss.

CLICK: Integrating Causal Inference and Commonsense Knowledge Incorporation for Counterfactual Story Generation

Counterfactual reasoning explores what could have happened if the circumstances were different from what actually occurred. As a crucial subtask, counterfactual story generation integrates counterfactual reasoning into the generative narrative chain, which requires the model to preserve minimal edits and ensure narrative consistency. Previous work prioritizes conflict detection as a first step, and then replaces conflicting content with appropriate words. However, these methods mainly face two challenging issues: (a) the causal relationship between story event sequences is not fully utilized in the conflict detection stage, leading to inaccurate conflict detection, and (b) the absence of proper planning in the content rewriting stage results in a lack of narrative consistency in the generated story ending. In this paper, we propose a novel counterfactual generation framework called CLICK based on causal inference in event sequences and commonsense knowledge incorporation. To address the first issue, we utilize the correlation between adjacent events in the story ending to iteratively calculate the contents from the original ending affected by the condition. The content with the original condition is then effectively prevented from carrying over into the new story ending, thereby avoiding causal conflict with the counterfactual conditions. Considering the second issue, we incorporate structural commonsense knowledge about counterfactual conditions, equipping the framework with comprehensive background information on the potential occurrence of counterfactual conditional events. Through leveraging a rich hierarchical data structure, CLICK gains the ability to establish a more coherent and plausible narrative trajectory for subsequent storytelling. Experimental results show that our model outperforms previous unsupervised state-of-the-art methods and achieves gains of 2.65 in BLEU, 4.42 in ENTScore, and 3.84 in HMean on the TIMETRAVEL dataset.

The shift in ideal family size: Examining the impact of marriage and parenthood

Motivated by role theory and the concept of the “self-fulfilling prophecy”, this study examines how entries into marriage and parenthood affect the fertility ideals of men and women in China. To address this question, we apply propensity score matching estimators to data from the China Family Panel Studies (CFPS) within a counterfactual framework. We find that marriage and parenthood have a positive effect on fertility ideals, and this result remains robust when we apply difference-in-differences matching estimates. In terms of gender asymmetry in marriage, men and women respond differently to marriage and parenthood. Entry into marriage has a positive effect on men's fertility ideals, while parenthood influences women's ideals. Beyond the average treatment effect, we further examine heterogeneous treatment effects as a function of estimated propensity scores. The study reveals that the life transition treatment effect is the highest among those with a moderate propensity for entering into marriage and parenthood.

Creation or disruption? Doubts from the internet applications in China's rural sector

To address the current large gap in research on the Internet applications in the Chinese rural sector, this paper explores the effect of these applications on the labor productivity of Chinese farmers from a creative destruction perspective. First, we construct a model to analyze the direct and indirect paths of the Internet applications impact on the productivity of farm households at the theoretical level; second, we conduct an empirical study corresponding to the theory based on micro-survey data obtained from China's first nationwide large-scale social survey project. Specifically, we verified the Internet applications direct effect on farm household labor productivity through the mean treatment effect approach and explored the efficiency and mechanism of action of the Internet productivity effect in the rural sector using the mediating effect model, Probit model, and the counterfactual analysis framework. The study finds that the productivity effect of the rural Internet applications still has a certain gap compared with the urban sector, although it is not at the "Solow's paradox" stage. Further discussion reveals that the Internet adoption in rural areas is a process of "creative destruction", and its destructive effects are dominant at this stage, while the creative effects still need to be further explored. This paper emphasizes that, for developing countries, accurately identifying the development stage of the Internet applications and further exploring its creative role is an important way to improve labor productivity in rural areas, and it is also an important step to promote the construction of digital villages.

Tesla under the Russia-Ukraine Conflict: A Short-term Perspective Based on Counterfactual Framework

The ARIMA model has found extensive applications across various domains, including financial time series analysis, weather forecasting, epidemiological forecasting, and market research. Despite its versatility, little attention has been paid to the impact of the ongoing Russia-Ukraine conflict on Tesla Motors. Given the significant influence of Tesla, as a major player in the electric drive vehicle industry, on the global energy landscape, this study aims to utilize the ARIMA model to examine the effect of the Russia-Ukraine conflict on Tesla's sales volume and stock price. The findings of this study may contribute towards mitigating global warming and inspire investment in sustainable energy solutions, including electric vehicles and energy storage issues. Additionally, this study will highlight Tesla's contribution to the global energy landscape and provide a quantitative analysis of investors' preferences for Tesla. Results indicate that the Russia-Ukraine war caused a significant short-term impact on Tesla's stock price. A counterfactual framework was used to compare control and actual sets, revealing a disparity between ideal predictions and the real world. However, Tesla's stock price rebounded in the second month of the war, signifying that this will not significantly affect Tesla's future development. The study also suggests that the disruption of the global supply chain caused by the war and Russia's energy export restrictions resulted in a sharp increase in global oil prices, thereby escalating the cost of gasoline vehicles and leading to a considerable surge in Tesla's sales.

The Impact Caused by COVID-19 Pandemic on Pfizer Inc. Stock Price: Based on a Counterfactual Framework

As the coronavirus pandemic spreads worldwide, many nations have implemented social distance regulations and quarantine measures to stop the spread of the COVID-19 epidemic. During this period, people's consumption levels dropped all over the world, resulting in a decrease in the capacity of the entire society to produce goods and services. As a result, thousands of workers lost their jobs and numerous manufacturing plants, entertainment companies struggled financially until going out of business. However, the value of some biopharmaceutical firms' shares has climbed rather than fallen due to some of these businesses made great contribution on preventing the spread of the pandemic by developing vaccines and useful medications. In this article, an American multinational pharmaceutical and biotechnology corporation, Pfizer Inc. was selected and daily stock data from February 2009 to December 2022 was extracted. The ARIMA model was applied to forecast the stock price of Pfizer Inc. without the Covid-19 pandemic. This study focuses on comparing the forecasted stock price with actual stock price and explores the possible reasons for this difference.

New Energy Vehicles under the Volatility of International Energy Prices: Evidence from Regional Conflict

Russia and Ukraine engaged in a military battle on February 24, 2022. Russia's military actions are viewed as an act of aggression toward Ukraine by the United States, the United Kingdom, the European Union, and other nations. The global energy crisis brought on by the onset of conflict and international sanctions is unavoidably having an influence on the new energy vehicle industry because Russia is the most significant producer and exporter of oil in the world. This article will use the counterfactual framework built by ARIMA model to study and analyze the impact of the Russian-Ukrainian conflict on the new energy vehicle industry. In conclusion, in short term, the cost effect dominates, and in long term, substitution effect dominates. This paper innovatively uses an index to examine the relationship between the Russian-Ukrainian conflict and the new energy vehicle industry. And it provides reference advice for government policy-making and investor portfolio selection. Government should vigorously develop the new energy industry, while investors should consider increasing the proportion of investment in new energy vehicles.