Effect Estimation Research Articles

On adjustment for temperature in heatwave epidemiology: a new method and toward clarification of methods to estimate health effects of heatwaves.

Defining the effect of exposure of interest and selecting an appropriate estimation method are prerequisite for causal inference. Understanding the ways in which association between heatwaves (i.e., consecutive days of extreme high temperature) and an outcome depends on whether adjustment was made for temperature and how such adjustment was conducted, is limited. This paper aims to investigate this dependency, demonstrate that temperature is a confounder in heatwave-outcome associations, and introduce a new modeling approach to estimate a new heatwave-outcome relation: E[R(Y)|HW=1, Z]/E[R(Y)|T=OT, Z], where HW is a daily binary variable to indicate the presence of a heatwave; R(Y) is the risk of an outcome, Y; T is a temperature variable; OT is optimal temperature; and Z is a set of confounders including typical confounders but also some types of T as a confounder. We recommend characterization of heatwave-outcome relations and careful selection of modeling approaches to understand the impacts of heatwaves under climate change. We demonstrate our approach using real-world data for Seoul, which suggests that the total effect of heatwaves may be larger than what may be inferred from the extant literature. An R package, HEAT (Heatwave effect Estimation via Adjustment for Temperature), was developed and made publicly available.

Robust and efficient factorial designs under baseline parametrization

Factorial designs, traditionally based on orthogonal parametrization, are widely used to study the effects of factors on responses. While the baseline parametrization has more applicability in many cases compared to the orthogonal parametrization, constructing baseline parametrization design is still challenging. This article presents a method based on approximation theory to search for highly efficient baseline parametrization designs, enhancing the accuracy of factor effect estimations. In addition, this article employs the D-optimal minimax criterion to ensure the robustness of the design. The examples and simulation show that the constructed designs have high efficiency.

Efficient designs for three-sequence stepped wedge trials with continuous recruitment.

The standard approach to designing stepped wedge trials that recruit participants in a continuous stream is to divide time into periods of equal length. But the choice of design in such cases is infinitely more flexible: each cluster could cross from the control to the intervention at any point on the continuous time-scale. We consider the case of a stepped wedge design with clusters randomised to just three sequences (designs with small numbers of sequences may be preferred for their simplicity and practicality) and investigate the choice of design that minimises the variance of the treatment effect estimator under different assumptions about the intra-cluster correlation. We make some simplifying assumptions in order to calculate the variance: in particular that we recruit the same number of participants, , from each cluster over the course of the trial, and that participants present at regularly spaced intervals. We consider an intra-cluster correlation that decays exponentially with separation in time between the presentation of two individuals from the same cluster, from a value of for two individuals who present at the same time, to a value of for individuals presenting at the start and end of the trial recruitment interval. We restrict attention to three-sequence designs with centrosymmetry - the property that if we reverse time and swap the intervention and control conditions then the design looks the same. We obtain an expression for the variance of the treatment effect estimator adjusted for effects of time, using methods for generalised least squares estimation, and we evaluate this expression numerically for different designs, and for different parameter values. There is a two-dimensional space of possible three-sequence, centrosymmetric stepped wedge designs with continuous recruitment. The variance of the treatment effect estimator for given and can be plotted as a contour map over this space. The shape of this variance surface depends on and on the parameter , but typically indicates a broad, flat region of close-to-optimal designs. The 'standard' design with equally spaced periods and 1:1:1 allocation rarely performs well, however. In many different settings, a relatively simple design can be found (e.g. one based on simple fractions) that offers close-to-optimal efficiency in that setting. There may also be designs that are robustly efficient over a wide range of settings. Contour maps of the kind we illustrate can help guide this choice. If efficiency is offered as one of the justifications for using a stepped wedge design, then it is worth designing with optimal efficiency in mind.

Matched vs Nonmatched Placebos in a Randomized Trial of COVID-19 Treatments

Matched placebo interventions are complex and resource intensive. Recent evidence suggests matched placebos may not always be necessary. Previous studies have predominantly evaluated potential bias of nonmatched placebos (ie, differing on dose, frequency of administration, or formulation) in pain and mental health, but to date no systematic examination has been conducted in infectious disease. To test for differences between nonmatched and matched placebo arms with respect to clinical outcome measures across multiple therapeutics for COVID-19. In a comparative effectiveness research study, a post hoc analysis was conducted of data on individual patients enrolled in a large, multiarm, platform randomized clinical trial in symptomatic adult outpatients with COVID-19 between January 15, 2021, to September 28, 2023, in which the outcomes of both matched and nonmatched placebo groups were reported. Bayesian and frequentist covariate-adjusted techniques were compared with 7 intervention-placebo pairs. Seven matched and nonmatched placebo pairs (for a total of 7 comparisons) were evaluated throughout the primary platform trial. Comparisons were made between treatment and its associated matched (concurrent) placebo, as well as with nonmatched placebo (alone and in combination) assessed at a similar time point. Outcomes assessed included hospitalizations, EuroQol 5-Dimension 5-level scores, and PROMIS Global-10 scores. A total of 7 intervention-control pairs (N = 2684) were assessed, including 1620 (60.4%) women, with mean (SD) age, 47 (15.2) years; the most common comorbidities were obesity (41.9%) and hypertension (37.9%). In a meta-analysis with decoupled SEs, accounting for overlapping placebo patients, the overall odds ratio (OR) of nonmatched compared with matched placebo was 1.01 (95% credible interval, 0.77-1.32), with posterior probability of equivalence, defined as 0.8 ≤ OR ≤ 1.2 (a deviation from perfect equivalence ie, OR = 1, by no more than 0.2) of 85.4%, implying no significant difference. Unadjusted analysis of the event rate difference between all nonmatched and matched placebo groups did not identify any notable differences across all 7 treatment-placebo combinations assessed. Similar analysis that was conducted for patient-reported quality of life outcomes did not yield statistically significant differences. In this post hoc study of a randomized clinical platform trial, pooling matched and nonmatched placebo patient data did not lead to inconsistencies in treatment effect estimation for any of the investigational drugs. These findings may have significant implications for future platform trials, as the use of nonmatched placebo may improve statistical power, or reduce barriers to placebo implementation.

Validation of Abbreviated Science Anxiety Scale in the Indian Context

The abbreviated science anxiety scale1 was validated in the Indian context with 290 secondary school students of grade 8 as the sample subjects. Exploratory factor analysis revealed the original two factors explaining 54.778 % of total variance in science anxity construct. Confirmatory factor analysis validated the factor structure of the construct with excellent goodness of fit estimates like CMIN/DF = 1.830, CFI = 0.969, TLI = 0.957, RMSEA = 0.054 and SRMR = 0.0392, conducted using the estimator maximum likelihood (ML). The floor and ceiling effect estimation for content validity showed that both the effects are absent with estimates way lesser than the benchmark of 15 % at 6.55 % and 0 % respectively. The internal consistency reliability estimation using Cronbach’s alpha found that the five items of the first factor “Learning science anxiety” and four items of the second factor “Science evaluation anxiety” had this estimate at 0.803 and 0.678 respectively, both of which fairly indicate good measurement of reliability of the scale. The education implications of the study are discussed.

Hierarchical modelling of variance components makes analysis of resolvable incomplete block designs more efficient

The standard approach to variance component estimation in linear mixed models for alpha designs is the residual maximum likelihood (REML) method. One drawback of the REML method in the context of incomplete block designs is that the block variance may be estimated as zero, which can compromise the recovery of inter-block information and hence reduce the accuracy of treatment effects estimation. Due to the development of statistical and computational methods, there is an increasing interest in adopting hierarchical approaches to analysis. In order to increase the precision of the analysis of individual trials laid out as alpha designs, we here make a proposal to create an objectively informed prior distribution for variance components for replicates, blocks and plots, based on the results of previous (historical) trials. We propose different modelling approaches for the prior distributions and evaluate the effectiveness of the hierarchical approach compared to the REML method, which is classically used for analysing individual trials in two-stage approaches for multi-environment trials.

State-Building through Public Land Disposal? An Application of Matrix Completion for Counterfactual Prediction

This article examines how homestead policies, which opened vast frontier lands for settlement, influenced the development of American frontier states. It uses a treatment propensity-weighted matrix completion model to estimate the counterfactual size of these states without homesteading. In simulation studies, the method shows lower bias and variance than other estimators, particularly in higher complexity scenarios. The empirical analysis reveals that homestead policies significantly and persistently reduced state government expenditure and revenue. These findings align with continuous difference-in-differences estimates using 1.46 million land patent records. This study’s extension of the matrix completion method to include propensity score weighting for causal effect estimation in panel data, especially in staggered treatment contexts, enhances policy evaluation by improving the precision of long-term policy impact assessments.

Genetic variations in anti-diabetic drug targets and COPD risk: evidence from mendelian randomization

BackgroundPrevious research has emphasized the potential benefits of anti-diabetic medications in inhibiting the exacerbation of Chronic Obstructive Pulmonary Disease (COPD), yet the role of anti-diabetic drugs on COPD risk remains uncertain.MethodsThis study employed a Mendelian randomization (MR) approach to evaluate the causal association of genetic variations related to six classes of anti-diabetic drug targets with COPD. The primary outcome for COPD was obtained from the Global Biobank Meta-analysis Initiative (GBMI) consortium, encompassing a meta-analysis of 12 cohorts with 81,568 cases and 1,310,798 controls. Summary-level data for HbA1c was derived from the UK Biobank, involving 344,182 individuals. Positive control analysis was conducted for Type 2 Diabetes Mellitus (T2DM) to validate the choice of instrumental variables. The study applied Summary-data-based MR (SMR) and two-sample MR for effect estimation and further adopted colocalization analysis to verify evidence of genetic variations.ResultsSMR analysis revealed that elevated KCNJ11 gene expression levels in blood correlated with reduced COPD risk (OR = 0.87, 95% CI = 0.79–0.95; p = 0.002), whereas an increase in DPP4 expression corresponded with an increased COPD incidence (OR = 1.18, 95% CI = 1.03–1.35; p = 0.022). Additionally, the primary method within MR analysis demonstrated a positive correlation between PPARG-mediated HbA1c and both FEV1 (OR = 1.07, 95% CI = 1.02–1.13; P = 0.013) and FEV1/FVC (OR = 1.08, 95% CI = 1.01–1.14; P = 0.007), and a negative association between SLC5A2-mediated HbA1c and FEV1/FVC (OR = 0.86, 95% CI = 0.74–1.00; P = 0.045). No colocalization evidence with outcome phenotypes was detected (all PP.H4 < 0.7).ConclusionThis study provides suggestive evidence for anti-diabetic medications' role in improving COPD and lung function. Further updated MR analyses are warranted in the future, following the acquisition of more extensive and comprehensive data, to validate our results.

A fast bootstrap algorithm for causal inference with large data.

Estimating causal effects from large experimental and observational data has become increasingly prevalent in both industry and research. The bootstrap is an intuitive and powerful technique used to construct standard errors and confidence intervals of estimators. Its application however can be prohibitively demanding in settings involving large data. In addition, modern causal inference estimators based on machine learning and optimization techniques exacerbate the computational burden of the bootstrap. The bag of little bootstraps has been proposed in non-causal settings for large data but has not yet been applied to evaluate the properties of estimators of causal effects. In this article, we introduce a new bootstrap algorithm called causal bag of little bootstraps for causal inference with large data. The new algorithm significantly improves the computational efficiency of the traditional bootstrap while providing consistent estimates and desirable confidence interval coverage. We describe its properties, provide practical considerations, and evaluate the performance of the proposed algorithm in terms of bias, coverage of the true 95% confidence intervals, and computational time in a simulation study. We apply it in the evaluation of the effect of hormone therapy on the average time to coronary heart disease using a large observational data set from the Women's Health Initiative.

Estimators for Topic-Sampling Designs

Abstract When researchers design an experiment, they usually hold potentially relevant features of the experiment constant. We call these details the “topic” of the experiment. For example, researchers studying the impact of party cues on attitudes must inform respondents of the parties’ positions on a particular policy. In doing so, researchers implement just one of many possible designs . Clifford, Leeper, and Rainey (2023. “Generalizing Survey Experiments Using Topic Sampling: An Application to Party Cues.” Forthcoming in Political Behavior. https://doi.org/10.1007/s11109-023-09870-1) argue that researchers should implement many of the possible designs in parallel—what they call “topic sampling”—to generalize to a larger population of topics. We describe two estimators for topic-sampling designs: First, we describe a nonparametric estimator of the typical effect that is unbiased under the assumptions of the design; and second, we describe a hierarchical model that researchers can use to describe the heterogeneity. We suggest describing the heterogeneity across topics in three ways: (1) the standard deviation in treatment effects across topics, (2) the treatment effects for particular topics, and (3) how the treatment effects for particular topics vary with topic-level predictors. We evaluate the performance of the hierarchical model using the Strengthening Democracy Challenge megastudy and show that the hierarchical model works well.

Average User-Side Counterfactual Fairness for Collaborative Filtering

Recently, the user-side fairness issue in Collaborative Filtering (CF) algorithms has gained considerable attention, arguing that results should not discriminate an individual or a sub-user group based on users’ sensitive attributes (e.g., gender). Researchers have proposed fairness-aware CF models by decreasing statistical associations between predictions and sensitive attributes. A more natural idea is to achieve model fairness from a causal perspective. The remaining challenge is that we have no access to interventions, i.e., the counterfactual world that produces recommendations when each user has changed the sensitive attribute value. To this end, we first borrow the Rubin-Neyman potential outcome framework to define average causal effects of sensitive attributes. Next, we show that removing causal effects of sensitive attributes is equal to average counterfactual fairness in CF. Then, we use the propensity re-weighting paradigm to estimate the average causal effects of sensitive attributes and formulate the estimated causal effects as an additional regularization term. To the best of our knowledge, we are one of the first few attempts to achieve counterfactual fairness from the causal effect estimation perspective in CF, which frees us from building sophisticated causal graphs. Finally, experiments on three real-world datasets show the superiority of our proposed model.

TESTING LIMITED OVERLAP

Extreme propensity scores arise in observational studies when treated and control units have very different characteristics. This is commonly referred to as limited overlap. In this paper, we propose a formal statistical test that helps assess the degree of limited overlap. Rejecting the null hypothesis in our test indicates either no or very mild degree of limited overlap and hence reassures that standard treatment effect estimators will be well behaved. One distinguishing feature of our test is that it only requires the use of a few extreme propensity scores, which is in stark contrast to other methods that require consistent estimates of some tail index. Without the need to extrapolate using observations far away from the tail, our procedure is expected to exhibit excellent size properties, a result that is also borne out in our simulation study.

Agricultural carbon emission efficiency and agricultural practices: Implications for balancing carbon emissions reduction and agricultural productivity increment

The current Ukraine War underlines the importance of grain self-sufficiency. After the adoption of the Paris Agreement, two major challenges developing countries are facing in the coming decades are increasing agricultural production to ensure food security and reducing carbon emissions (CE). The key to such an “environment-development dilemma” is to improve agricultural carbon emission efficiency (CEE). Using China as the study site, we systematically analyze the impacts of agricultural management activities on agricultural CEE from 1997 to 2019. Global and local Moran's I index tests provide evidence of a positive spatial dependence of agricultural CEE. Using the LISA cluster map, we observe that high CEE regions tend to be distributed together, dominated by environmental conditions. However, with the promotion of agricultural management activities, such a clustering pattern vanished. Our spatial Durbin model (SDM) estimation results indicate that there are significant nonlinear relationships between agricultural practices and agricultural CEE. While the consumption of fertilizers and pesticides has economies of scale effects, the deployment of agricultural machinery and irrigation have diseconomies of scale effects on local CEE. Based on the SDM results, the direct and indirect effect estimation results suggest that the significant direct and spillover effects of many practices on agricultural CEE have opposite nonlinear shapes, implying a more complicated situation in promoting these activities, as the positive regional effect of an agricultural activity might have a negative impact on adjacent regions. All the results indicate that local policymakers should carefully tailor agricultural development policies based on local environmental conditions.

ESG Performance and Corporate Default Risk: Do Countries’ Shareholder Protection Levels Affect This Relationship?

This paper explores the nexus between environmental, social, and governance (ESG) performance and corporate default risk. Employing a panel dataset from 1,094 non-financial companies in 21 nations in Europe, corresponding to 9,522 firm-year observations, and using fixed effects estimations, we empirically demonstrate that corporations with higher ESG scores tend to have lower firm default risk. Among the three categories of the ESG score, both the social and the environmental categories participate in this significant association. Moreover, our study presents novel evidence that within ESGs’ ten subcategories, resource use, product responsibility, emissions, human rights, workforce, and CSR strategy significantly reduce firm default risk. Furthermore, country-level shareholder protection moderates the linkage between default risk and ESG performance, such that the negative impact of ESG on default risk is lower for corporations located in nations with higher shareholder protection. Hence, if the countries’ shareholder protection levels are high, stronger ESG would decrease firm default risk by a lesser amount than countries with lower shareholder protection levels. Our findings are robust to alternate variable measurements and alternate methodologies, capturing endogeneity issues.

The Impact of Climate Change on Work: Lessons for Developing Countries

Abstract We identify five areas where climate change may impact work and draw lessons for developing countries by reviewing the evidence. Firstly, demand for labor is unevenly affected, with agriculture, heat-exposed manufacturing, and the brown energy sector experiencing downturns, while other sectors may see a rise, resulting in an uncertain overall impact. Secondly, climate change impacts labor supply through absenteeism, shirking, and altering work-time patterns, depending on the activity and sector. Thirdly, productivity may decline, especially in heat-exposed industries, primarily due to health reasons. Fourthly, heightened earnings variability likely increases vulnerability among the self-employed. Fifthly, climate change can influence labor allocation and catalyze sectoral reallocation. Higher temperatures are also linked to increased migration. But caution is needed in interpreting these findings, as studies across these topics predominantly use fixed effect estimation and concentrate on short-term impacts, neglecting adaptation. Emerging research on adaptation indicates that workplace cooling is unappealing for firms with narrow profit margins, while coping strategies of farms and households have unclear optimality due to adoption barriers. Government responses remain understudied, with six potential areas identified: green jobs, green skills, labor-oriented adaptation, flexible work regulation, labor market integration, and social protection. We conclude by outlining future research directions.

Anorexia nervosa and bulimia nervosa: a Mendelian randomization study of gut microbiota.

Anorexia nervosa (AN) and bulimia nervosa (BN) poses a significant challenge to global public health. Despite extensive research, conclusive evidence regarding the association between gut microbes and the risk of AN and BN remains elusive. Mendelian randomization (MR) methods offer a promising avenue for elucidating potential causal relationships. Genome-wide association studies (GWAS) datasets of AN and BN were retrieved from the OpenGWAS database for analysis. Independent single nucleotide polymorphisms closely associated with 196 gut bacterial taxa from the MiBioGen consortium were identified as instrumental variables. MR analysis was conducted utilizing R software, with outlier exclusion performed using the MR-PRESSO method. Causal effect estimation was undertaken employing four methods, including Inverse variance weighted. Sensitivity analysis, heterogeneity analysis, horizontal multivariate analysis, and assessment of causal directionality were carried out to assess the robustness of the findings. A total of 196 bacterial taxa spanning six taxonomic levels were subjected to analysis. Nine taxa demonstrating potential causal relationships with AN were identified. Among these, five taxa, including Peptostreptococcaceae, were implicated as exerting a causal effect on AN risk, while four taxa, including Gammaproteobacteria, were associated with a reduced risk of AN. Similarly, nine taxa exhibiting potential causal relationships with BN were identified. Of these, six taxa, including Clostridiales, were identified as risk factors for increased BN risk, while three taxa, including Oxalobacteraceae, were deemed protective factors. Lachnospiraceae emerged as a common influence on both AN and BN, albeit with opposing effects. No evidence of heterogeneity or horizontal pleiotropy was detected for significant estimates. Through MR analysis, we revealed the potential causal role of 18 intestinal bacterial taxa in AN and BN, including Lachnospiraceae. It provides new insights into the mechanistic basis and intervention targets of gut microbiota-mediated AN and BN.

Asymmetric Exchange Rate Effects on Trade Flows in India

This paper examines the role of exchange rate changes on India’s trade. The drivers of exports and imports (income, exchange rate including sectoral differences, and exchange rate variability) are estimated for the short and long run including a structural break. Using annual data from 1994 to 2022, the results of dynamic fixed effects estimation show that both exports and imports are income-elastic in the short and long run, but income elasticity is far stronger for exports. Moreover, exports are responsive to the real effective exchange rate in the short run but not in the long run, and the reverse is true for imports. Furthermore, exchange rates have asymmetric effects for high-volume and primary sectors for exports and imports. The combined impacts show the ineffectiveness of using currency depreciation to address trade imbalances.

Evaluation of bi-directional causal association between obstructive sleep apnoea syndrome and diabetic microangiopathy: a Mendelian randomization study.

The relationship between obstructive sleep apnea syndrome (OSAS) and diabetic microangiopathy remains controversial. This study aimed to use bidirectional two-sample Mendelian Randomization (MR) to assess the causal relationship between OSAS and diabetic microangiopathy. First, we used the Linkage Disequilibrium Score Regression(LDSC) analysis to assess the genetic correlation. Then, the bidirectional two-sample MR study was conducted in two stages: OSAS and lung function-related indicators (forced vital capacity (FVC) and forced expiratory volume in 1 s (FEV1)) were investigated as exposures, with diabetic microangiopathy as the outcome in the first stage, and genetic tools were used as proxy variables for OSAS and lung function-related measures in the second step. Genome-wide association study data came from the open GWAS database. We used Inverse-Variance Weighted (IVW), MR-Egger regression, Weighted median, Simple mode, and Weighted mode for effect estimation and pleiotropy testing. We also performed sensitivity analyses to test the robustness of the results. Furthermore, we performed multivariate and mediation MR analyses. In the LDSC analysis, We found a genetic correlation between OSAS, FVC, FEV 1, and diabetic microangiopathy. In the MR analysis, based on IVW analysis, genetically predicted OSAS was positively correlated with the incidence of diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN). In the subgroup analysis of DR, there was a significant causal relationship between OSAS and background diabetic retinopathy (BDR) and proliferative diabetic retinopathy (PDR). The reverse MR did not show a correlation between the incidence of diabetic microangiopathy and OSAS. Reduced FVC had a potential causal relationship with increased incidence of DR and PDR. Reduced FEV1 had a potential causal relationship with the increased incidence of BDR, PDR, and DKD. Multivariate MR analysis showed that the association between OSAS and diabetic microangiopathy remained significant after adjusting for confounding factors. However, we did not find the significant mediating factors. Our results suggest that OSAS may be a cause of the development of diabetic microangiopathy, and OSAS may also be associated with a high risk of diabetic microangiopathy, providing a reference for a better understanding of the prevention of diabetic microangiopathy.

How the wellbeing function varies with age: the importance of income, health and social relations over the lifecycle

AbstractPrevious literature has identified income, health status and social relationships as the most important predictors of subjective wellbeing (SWB). In addition, the literature has identified a non‐linear relationship between age and SWB, with a dip in SWB in midlife. Explanations of the non‐linear age–SWB relationship include the notion of unmet aspirations and the idea that people's emotional response to the drivers of SWB changes with age. Against this background, we use representative longitudinal data for Germany (1992–2019) with about 570,000 observations for more than 88,000 individuals aged 16–105 years to investigate if and how the association between SWB and its main predictors changes over the lifecycle. Using fixed effects estimation to control for cohort effects and unobserved personal characteristics, we find that the marginal effects of income and social relationships vary with age in a wave‐like fashion, while the positive marginal effect of good health status increases monotonically and progressively with age. Our results are similar for alternative measures of SWB (life satisfaction and living in misery), and for men and women separately. The age‐related changes in the importance of income and social relationships for SWB found in this paper help to explain the relationship between age and SWB found in previous literature.

The Impact of Electronic Management on Customer Experience in Vehicle Insurance Companies within the Riyadh Region

Electronic management and electronic provision of insurance services are considered among the challenges facing the insurance sector in the Kingdom of Saudi Arabia to keep pace with the Kingdom’s Vision 2030. Therefore, the reality of this transformation and the factors affecting it were studied by surveying the opinions of insurance policyholders about the quality of electronic services provided by insurance companies and their impact on the extent of their benefit. Regression analysis, effect estimation using structural models, and analysis of variance were used to test the study hypotheses. The results showed that electronic transformation in the provision of insurance services by Saudi insurance companies still requires significant development in terms of comprehensiveness and diversity of services, and that the success of this is linked to the quality of electronic service from an insurance point of view. The most important recommendations were the need for Saudi insurance companies to pay attention to spreading the culture of electronic transformation among their subordinates, expanding the scope of electronic services, and raising their quality in accordance with the priorities revealed by the study, especially with regard to ensuring that the content of the website is up-to-date and comprehensive, and that the use of the website is safe and reliable for the customer. Adequate technical support must be provided to serve customers who benefit from the insurance company’s electronic services.