Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

How to make causal inferences using texts.

ABSTRACT: Text as data techniques offer a great promise: the ability to inductively discover measures that are useful for testing social science theories with large collections of text. Nearly all text-based causal inferences depend on a latent representation of the text, but we show that estimating this latent representation from the data creates underacknowledged risks: we may introduce an identification problem or overfit. To address these risks, we introduce a split-sample workflow for making rigorous causal inferences with discovered measures as treatments or outcomes. We then apply it to estimate causal effects from an experiment on immigration attitudes and a study on bureaucratic responsiveness.

SUBMITTER: Egami N

PROVIDER: S-EPMC9581481 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

How to make causal inferences using texts.

Egami Naoki N Fong Christian J CJ Grimmer Justin J Roberts Margaret E ME Stewart Brandon M BM

Science advances 20221019 42

Text as data techniques offer a great promise: the ability to inductively discover measures that are useful for testing social science theories with large collections of text. Nearly all text-based causal inferences depend on a latent representation of the text, but we show that estimating this latent representation from the data creates underacknowledged risks: we may introduce an identification problem or overfit. To address these risks, we introduce a split-sample workflow for making rigorous ...[more]

PMID: 36260669

Similar Datasets

Neurofind: using deep learning to make individualised inferences in brain-based disorders.

Project description:Within precision psychiatry, there is a growing interest in normative models given their ability to parse heterogeneity. While they are intuitive and informative, the technical expertise and resources required to develop normative models may not be accessible to most researchers. Here we present Neurofind, a new freely available tool that bridges this gap by wrapping sound and previously tested methods on data harmonisation and advanced normative models into a web-based platform that requires minimal input from the user. We explain how Neurofind was developed, how to use the Neurofind website in four simple steps ( www.neurofind.ai ), and provide exemplar applications. Neurofind takes as input structural MRI images and outputs two main metrics derived from independent normative models: (1) Outlier Index Score, a deviation score from the normative brain morphology, and (2) Brain Age, the predicted age based on an individual's brain morphometry. The tool was trained on 3362 images of healthy controls aged 20-80 from publicly available datasets. The volume of 101 cortical and subcortical regions was extracted and modelled with an adversarial autoencoder for the Outlier index model and a support vector regression for the Brain age model. To illustrate potential applications, we applied Neurofind to 364 images from three independent datasets of patients diagnosed with Alzheimer's disease and schizophrenia. In Alzheimer's disease, 55.2% of patients had very extreme Outlier Index Scores, mostly driven by larger deviations in temporal-limbic structures and ventricles. Patients were also homogeneous in how they deviated from the norm. Conversely, only 30.1% of schizophrenia patients were extreme outliers, due to deviations in the hippocampus and pallidum, and patients tended to be more heterogeneous than controls. Both groups showed signs of accelerated brain ageing.

| S-EPMC11868583 | biostudies-literature

Using hospital-based studies of community-onset bloodstream infections to make inferences about typhoid fever incidence.

Project description:OBJECTIVES:Hospital-based studies of community-onset bloodstream infections (CO-BSI) are less resource-intensive to carry out than population-based incidence studies. We examined several metrics capturing the potential role of Salmonella Typhi as a cause of CO-BSI for making inferences about incidence. METHODS:We systematically reviewed three databases for hospital-based studies of CO-BSI. We determined, by study, the prevalence and rank order of Salmonella among pathogenic bloodstream isolates, and the prevalence ratio of Salmonella Typhi to Escherichia coli (S:E ratio). We then describe these hospital-based study metrics in relation to population-based typhoid fever incidence data from a separate systematic review. RESULTS:Forty-four studies met the inclusion criteria, of which 23 (52.3%) isolated Salmonella Typhi at least once. Among studies isolating Salmonella Typhi, the median (interquartile range) prevalence and rank order of Salmonella Typhi compared to other pathogens isolated in BSI was 8.3% (3.2-37.9%) and 3 (1-6), respectively. The median (interquartile range) S:E ratio was 1.0 (0.4-3.0). With respect to incidence, in Pemba Island, Tanzania, prevalence, rank order, S:E ratio, and incidence was 64.8%, 1, 9.2 and 110 cases per 100 000, respectively, and in Boulkiemdé, Burkina Faso, was 13.3%, 3, 2.3 and 249 cases per 100 000. CONCLUSIONS:We describe considerable variation in place and time for Salmonella Typhi prevalence, rank order, and S:E ratio among hospital-based studies of CO-BSI. Data from simultaneous typhoid prevalence and incidence studies are limited. We propose that hospital-based study metrics warrant evaluation for making inference about typhoid incidence and as covariates in typhoid incidence models.

| S-EPMC6916262 | biostudies-literature

Children use nonverbal cues to make inferences about social power.

Project description:Four studies (N = 192) tested whether young children use nonverbal information to make inferences about differences in social power. Five- and six-year-old children were able to determine which of two adults was "in charge" in dynamic videotaped conversations (Study 1) and in static photographs (Study 4) using only nonverbal cues. Younger children (3-4 years) were not successful in Study 1 or Study 4. Removing irrelevant linguistic information from conversations did not improve the performance of 3- to 4-year-old children (Study 3), but including relevant linguistic cues did (Study 2). Thus, at least by 5 years of age, children show sensitivity to some of the same nonverbal cues adults use to determine other people's social roles.

| S-EPMC4795924 | biostudies-literature

Form and function: Optional complementizers reduce causal inferences.

Project description:Many factors are known to influence the inference of the discourse coherence relationship between two sentences. Here, we examine the relationship between two conjoined embedded clauses in sentences like The professor noted that the student teacher did not look confident and (that) the students were poorly behaved. In two studies, we find that the presence of that before the second embedded clause in such sentences reduces the possibility of a forward causal relationship between the clauses, i.e., the inference that the student teacher's confidence was what affected student behavior. Three further studies tested the possibility of a backward causal relationship between clauses in the same structure, and found that the complementizer's presence aids that relationship, especially in a forced-choice paradigm. The empirical finding that a complementizer, a linguistic element associated primarily with structure rather than event-level semantics, can affect discourse coherence is novel and illustrates an interdependence between syntactic parsing and discourse parsing.

| S-EPMC5552188 | biostudies-literature

Leveraging summary statistics to make inferences about complex phenotypes in large biobanks.

Project description:As genetic sequencing becomes less expensive and data sets linking genetic data and medical records (e.g., Biobanks) become larger and more common, issues of data privacy and computational challenges become more necessary to address in order to realize the benefits of these datasets. One possibility for alleviating these issues is through the use of already-computed summary statistics (e.g., slopes and standard errors from a regression model of a phenotype on a genotype). If groups share summary statistics from their analyses of biobanks, many of the privacy issues and computational challenges concerning the access of these data could be bypassed. In this paper we explore the possibility of using summary statistics from simple linear models of phenotype on genotype in order to make inferences about more complex phenotypes (those that are derived from two or more simple phenotypes). We provide exact formulas for the slope, intercept, and standard error of the slope for linear regressions when combining phenotypes. Derived equations are validated via simulation and tested on a real data set exploring the genetics of fatty acids.

| S-EPMC6417828 | biostudies-literature

Case selection and causal inferences in qualitative comparative research.

Project description:Traditionally, social scientists perceived causality as regularity. As a consequence, qualitative comparative case study research was regarded as unsuitable for drawing causal inferences since a few cases cannot establish regularity. The dominant perception of causality has changed, however. Nowadays, social scientists define and identify causality through the counterfactual effect of a treatment. This brings causal inference in qualitative comparative research back on the agenda since comparative case studies can identify counterfactual treatment effects. We argue that the validity of causal inferences from the comparative study of cases depends on the employed case-selection algorithm. We employ Monte Carlo techniques to demonstrate that different case-selection rules strongly differ in their ex ante reliability for making valid causal inferences and identify the most and the least reliable case selection rules.

| S-EPMC6655636 | biostudies-literature

A guide to improve your causal inferences from observational data.

Project description:True causality is impossible to capture with observational studies. Nevertheless, within the boundaries of observational studies, researchers can follow three steps to answer causal questions in the most optimal way possible. Researchers must: (a) repeatedly assess the same constructs over time in a specific sample; (b) consider the temporal sequence of effects between constructs; and (c) use an analytical strategy that distinguishes within from between-person effects. In this context, it is demonstrated how the random intercepts cross-lagged panel model can be a useful statistical technique. A real-life example of the relationship between loneliness and quality of life in adolescents with congenital heart disease is provided to show how the model can be practically implemented.

| S-EPMC7817987 | biostudies-literature

Shared polygenic risk and causal inferences in amyotrophic lateral sclerosis.

Project description:ObjectiveTo identify shared polygenic risk and causal associations in amyotrophic lateral sclerosis (ALS).MethodsLinkage disequilibrium score regression and Mendelian randomization were applied in a large-scale, data-driven manner to explore genetic correlations and causal relationships between >700 phenotypic traits and ALS. Exposures consisted of publicly available genome-wide association studies (GWASes) summary statistics from MR Base and LD-hub. The outcome data came from the recently published ALS GWAS involving 20,806 cases and 59,804 controls. Multivariate analyses, genetic risk profiling, and Bayesian colocalization analyses were also performed.ResultsWe have shown, by linkage disequilibrium score regression, that ALS shares polygenic risk genetic factors with a number of traits and conditions, including positive correlations with smoking status and moderate levels of physical activity, and negative correlations with higher cognitive performance, higher educational attainment, and light levels of physical activity. Using Mendelian randomization, we found evidence that hyperlipidemia is a causal risk factor for ALS and localized putative functional signals within loci of interest.InterpretationHere, we have developed a public resource (https://lng-nia.shinyapps.io/mrshiny) which we hope will become a valuable tool for the ALS community, and that will be expanded and updated as new data become available. Shared polygenic risk exists between ALS and educational attainment, physical activity, smoking, and tenseness/restlessness. We also found evidence that elevated low-desnity lipoprotein cholesterol is a causal risk factor for ALS. Future randomized controlled trials should be considered as a proof of causality. Ann Neurol 2019;85:470-481.

| S-EPMC6450729 | biostudies-literature

Genetic overlap and causal inferences between kidney function and cerebrovascular disease.

Project description:ObjectiveLeveraging large-scale genetic data, we aimed to identify shared pathogenic mechanisms and causal relationships between impaired kidney function and cerebrovascular disease phenotypes.MethodsWe used summary statistics from genome-wide association studies (GWAS) of kidney function traits (chronic kidney disease diagnosis, estimated glomerular filtration rate [eGFR], and urinary albumin-to-creatinine ratio [UACR]) and cerebrovascular disease phenotypes (ischemic stroke and its subtypes, intracerebral hemorrhage [ICH], and white matter hyperintensities [WMH] on brain MRI). We (1) tested the genetic overlap between them with polygenic risk scores (PRS), (2) searched for common pleiotropic loci with pairwise GWAS analyses, and (3) explored causal associations by employing 2-sample Mendelian randomization.ResultsA PRS for lower eGFR was associated with higher large artery stroke (LAS) risk (p = 1 × 10-4). Multiple pleiotropic loci were identified between kidney function traits and cerebrovascular disease phenotypes, with 12q24 associated with eGFR and both LAS and small vessel stroke (SVS), and 2q33 associated with UACR and both SVS and WMH. Mendelian randomization revealed associations of both lower eGFR (odds ratio [OR] per 1-log decrement, 2.10; 95% confidence interval [CI], 1.38-3.21) and higher UACR (OR per 1-log increment, 2.35; 95% CI, 1.12-4.94) with a higher risk of LAS, as well as between higher UACR and higher risk of ICH.ConclusionsImpaired kidney function, as assessed by decreased eGFR and increased UACR, may be causally involved in the pathogenesis of LAS. Increased UACR, previously proposed as a marker of systemic small vessel disease, is involved in ICH risk and shares a genetic risk factor at 2q33 with manifestations of cerebral small vessel disease.

| S-EPMC7455337 | biostudies-literature

Causa Nostra: The Potentially Legitimate Business of Drawing Causal Inferences From Observational Data.

Project description: Not available

| S-EPMC6539667 | biostudies-literature