Causal Discovery with Confounding Cascade Nonlinear Additive Noise Models

Identification of causal direction between a causal-effect pair from observed data has recently attracted much attention. Various methods based on functional causal models have been proposed to solve this problem, by assuming the causal process satisfies some (structural) constraints and showing that the reverse direction violates such constraints. The nonlinear additive noise model has been demonstrated to be effective for this purpose, but the model class does not allow any confounding or intermediate variables between a cause pair–even if each direct causal relation follows this model. However, omitting the latent causal variables is frequently encountered in practice. After the omission, the model does not necessarily follow the model constraints. As a consequence, the nonlinear additive noise model may fail to correctly discover causal direction. In this work, we propose a confounding cascade nonlinear additive noise model to represent such causal influences–each direct causal relation follows the nonlinear additive noise model but we observe only the initial cause and final effect. We further propose a method to estimate the model, including the unmeasured confounding and intermediate variables, from data under the variational auto-encoder framework. Our theoretical results show that with our model, the causal direction is identifiable under suitable technical conditions on the data generation process. Simulation results illustrate the power of the proposed method in identifying indirect causal relations across various settings, and experimental results on real data suggest that the proposed model and method greatly extend the applicability of causal discovery based on functional causal models in nonlinear cases.

Statistical estimates bias for data with missing values: Nonresponse study: انحياز التقديرات الإحصائية للبيانات التي تحوي قيماً مفقودة: دراسة حالة عدم الاستجابة

Statistical surveys are usually conducted to obtain data describing a problem in a studied society, and many surveys experience a rise in nonresponse rates, as the rate of nonresponse may affect the bias of the nonresponse in survey estimates. Recent empirical results show instances of nonresponse rate correlation with nonresponse bias, we attempt to translate statistical experiences of nonresponse bias in newly published studies and research into causal models that lead to assumptions about when a lack of response causes bias in estimates. Research studies of the estimates of nonresponse bias show that this bias often exists. The logical question is: what is the advantage of surveys if they suffer from high rates of nonresponse, since post-survey adjustments for nonresponse require additional variables, the answer depends on the nature of the design and the quality of the additional variables.

The demands of comorbidity: Implications for the explanation and classification of mental disorder

<p>A central goal of psychiatric classification is to assist in the assessment and treatment of those who experience mental disorder. This challenge takes on greater significance in complex cases, especially given the high prevalence of psychiatric comorbidity. High rates of comorbidity also challenge the validity of current psychiatric nosology. Etiological classification has been promoted as an alternative to improve the state of psychiatric diagnosis. However, comorbidity makes specific conceptual, explanatory and methodological demands of any such classification strategy. In this thesis, a demand for coherent and integrative explanation of comorbidity acts as a standard by which to assess the strength of different causal models of mental disorder and their resultant concepts. Integrative pluralism is presented as an epistemological framework well-suited to the complexity of this scientific challenge.</p>

The demands of comorbidity: Implications for the explanation and classification of mental disorder

<p>A central goal of psychiatric classification is to assist in the assessment and treatment of those who experience mental disorder. This challenge takes on greater significance in complex cases, especially given the high prevalence of psychiatric comorbidity. High rates of comorbidity also challenge the validity of current psychiatric nosology. Etiological classification has been promoted as an alternative to improve the state of psychiatric diagnosis. However, comorbidity makes specific conceptual, explanatory and methodological demands of any such classification strategy. In this thesis, a demand for coherent and integrative explanation of comorbidity acts as a standard by which to assess the strength of different causal models of mental disorder and their resultant concepts. Integrative pluralism is presented as an epistemological framework well-suited to the complexity of this scientific challenge.</p>

The Beneficial Learning Effects of Combining a Hypothesis-Testing Mindset with a Causal Model

Firms often use causal models to align decision-making with strategic objectives. However, firms often operate in changing environments such that an accurate causal model can become inaccurate. Prior research has not examined the consequences a change in the accuracy of causal models may have for managerial learning. Using an experiment, we predict and find that providing an accurate causal model positively affects managerial learning, and this positive effect is not reduced by encouraging a hypothesis-testing mindset (HTM). However, when the model subsequently becomes inaccurate, we predict and observe that providing a causal model alone negatively affects managerial learning, although this effect is partially mitigated by additionally encouraging a HTM. Our results can inform designers of control systems about the potential implications of providing a causal model when its accuracy changes over time and demonstrate how simple encouragement of a HTM moderates the effects of providing a causal model.

Causal inference under over-simplified longitudinal causal models

Many causal models of interest in epidemiology involve longitudinal exposures, confounders and mediators. However, repeated measurements are not always available or used in practice, leading analysts to overlook the time-varying nature of exposures and work under over-simplified causal models. Our objective is to assess whether – and how – causal effects identified under such misspecified causal models relates to true causal effects of interest. We derive sufficient conditions ensuring that the quantities estimated in practice under over-simplified causal models can be expressed as weighted averages of longitudinal causal effects of interest. Unsurprisingly, these sufficient conditions are very restrictive, and our results state that the quantities estimated in practice should be interpreted with caution in general, as they usually do not relate to any longitudinal causal effect of interest. Our simulations further illustrate that the bias between the quantities estimated in practice and the weighted averages of longitudinal causal effects of interest can be substantial. Overall, our results confirm the need for repeated measurements to conduct proper analyses and/or the development of sensitivity analyses when they are not available.