Biomaterial Database

Inference for causal interactions for continuous exposures under dichotomization. 2011

Tyler J VanderWeele, and Yu Chen, and Habibul Ahsan

Department of Epidemiology, Harvard School of Public Health, 677 Huntington Avenue, Boston, Massachusetts 02115, USA. tvanderw@hsph.harvard.edu

Dichotomization of continuous exposure variables is a common practice in medical and epidemiological research. The practice has been cautioned against on the grounds of efficiency and bias. Here we consider the consequences of dichotomization of a continuous covariate for the study of interactions. We show that when a continuous exposure has been dichotomized certain inferences concerning causal interactions can be drawn with regard to the original continuous exposure scale. Within the context of interaction analyses, dichotomization and the use of the results in this article can furthermore help prevent incorrect conclusions about the presence of interactions that result simply from erroneous modeling of the exposure variables. By considering different dichotomization points one can gain considerable insight concerning the presence of causal interaction between exposures at different levels. The results in this article are applied to a study of the interactive effects between smoking and arsenic exposure from well water in producing skin lesions.

UI	MeSH Term	Description	Entries
D010349	Patient Compliance	Voluntary cooperation of the patient in following a prescribed regimen.	Client Adherence,Client Compliance,Non-Adherent Patient,Patient Adherence,Patient Cooperation,Patient Noncompliance,Patient Non-Adherence,Patient Non-Compliance,Patient Nonadherence,Therapeutic Compliance,Treatment Compliance,Adherence, Client,Adherence, Patient,Client Compliances,Compliance, Client,Compliance, Patient,Compliance, Therapeutic,Compliance, Treatment,Cooperation, Patient,Non Adherent Patient,Non-Adherence, Patient,Non-Adherent Patients,Non-Compliance, Patient,Nonadherence, Patient,Noncompliance, Patient,Patient Non Adherence,Patient Non Compliance,Patient, Non-Adherent,Therapeutic Compliances,Treatment Compliances
D011379	Prognosis	A prediction of the probable outcome of a disease based on a individual's condition and the usual course of the disease as seen in similar situations.	Prognostic Factor,Prognostic Factors,Factor, Prognostic,Factors, Prognostic,Prognoses
D001943	Breast Neoplasms	Tumors or cancer of the human BREAST.	Breast Cancer,Breast Tumors,Cancer of Breast,Breast Carcinoma,Cancer of the Breast,Human Mammary Carcinoma,Malignant Neoplasm of Breast,Malignant Tumor of Breast,Mammary Cancer,Mammary Carcinoma, Human,Mammary Neoplasm, Human,Mammary Neoplasms, Human,Neoplasms, Breast,Tumors, Breast,Breast Carcinomas,Breast Malignant Neoplasm,Breast Malignant Neoplasms,Breast Malignant Tumor,Breast Malignant Tumors,Breast Neoplasm,Breast Tumor,Cancer, Breast,Cancer, Mammary,Cancers, Mammary,Carcinoma, Breast,Carcinoma, Human Mammary,Carcinomas, Breast,Carcinomas, Human Mammary,Human Mammary Carcinomas,Human Mammary Neoplasm,Human Mammary Neoplasms,Mammary Cancers,Mammary Carcinomas, Human,Neoplasm, Breast,Neoplasm, Human Mammary,Neoplasms, Human Mammary,Tumor, Breast
D003627	Data Interpretation, Statistical	Application of statistical procedures to analyze specific observed or assumed facts from a particular study.	Data Analysis, Statistical,Data Interpretations, Statistical,Interpretation, Statistical Data,Statistical Data Analysis,Statistical Data Interpretation,Analyses, Statistical Data,Analysis, Statistical Data,Data Analyses, Statistical,Interpretations, Statistical Data,Statistical Data Analyses,Statistical Data Interpretations
D005260	Female		Females
D006801	Humans	Members of the species Homo sapiens.	Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D012307	Risk Factors	An aspect of personal behavior or lifestyle, environmental exposure, inborn or inherited characteristic, which, based on epidemiological evidence, is known to be associated with a health-related condition considered important to prevent.	Health Correlates,Risk Factor Scores,Risk Scores,Social Risk Factors,Population at Risk,Populations at Risk,Correlates, Health,Factor, Risk,Factor, Social Risk,Factors, Social Risk,Risk Factor,Risk Factor Score,Risk Factor, Social,Risk Factors, Social,Risk Score,Score, Risk,Score, Risk Factor,Social Risk Factor
D015982	Bias	Any deviation of results or inferences from the truth, or processes leading to such deviation. Bias can result from several sources: one-sided or systematic variations in measurement from the true value (systematic error); flaws in study design; deviation of inferences, interpretations, or analyses based on flawed data or data collection; etc. There is no sense of prejudice or subjectivity implied in the assessment of bias under these conditions.	Aggregation Bias,Bias, Aggregation,Bias, Ecological,Bias, Statistical,Bias, Systematic,Ecological Bias,Outcome Measurement Errors,Statistical Bias,Systematic Bias,Bias, Epidemiologic,Biases,Biases, Ecological,Biases, Statistical,Ecological Biases,Ecological Fallacies,Ecological Fallacy,Epidemiologic Biases,Experimental Bias,Fallacies, Ecological,Fallacy, Ecological,Scientific Bias,Statistical Biases,Truncation Bias,Truncation Biases,Bias, Experimental,Bias, Scientific,Bias, Truncation,Biase, Epidemiologic,Biases, Epidemiologic,Biases, Truncation,Epidemiologic Biase,Error, Outcome Measurement,Errors, Outcome Measurement,Outcome Measurement Error
D015984	Causality	The relating of causes to the effects they produce. Causes are termed necessary when they must always precede an effect and sufficient when they initiate or produce an effect. Any of several factors may be associated with the potential disease causation or outcome, including predisposing factors, enabling factors, precipitating factors, reinforcing factors, and risk factors.	Causation,Enabling Factors,Multifactorial Causality,Multiple Causation,Predisposing Factors,Reinforcing Factors,Causalities,Causalities, Multifactorial,Causality, Multifactorial,Causation, Multiple,Causations,Causations, Multiple,Enabling Factor,Factor, Enabling,Factor, Predisposing,Factor, Reinforcing,Factors, Enabling,Factors, Predisposing,Factors, Reinforcing,Multifactorial Causalities,Multiple Causations,Predisposing Factor,Reinforcing Factor
D015986	Confounding Factors, Epidemiologic	Factors that can cause or prevent the outcome of interest but are not intermediate variables of the factor(s) under investigation.	Confounding Factor, Epidemiologic,Confounding Factors, Epidemiological,Confounding Factors, Epidemiology,Confounding Variables,Confounding Variables, Epidemiologic,Confounding Variables, Epidemiological,Confounding Factor, Epidemiological,Confounding Factor, Epidemiology,Confounding Variable,Confounding Variable, Epidemiologic,Confounding Variable, Epidemiological,Epidemiologic Confounding Factor,Epidemiologic Confounding Factors,Epidemiologic Confounding Variable,Epidemiologic Confounding Variables,Epidemiological Confounding Factor,Epidemiological Confounding Factors,Epidemiological Confounding Variable,Epidemiological Confounding Variables,Epidemiology Confounding Factor,Epidemiology Confounding Factors,Variable, Confounding,Variable, Epidemiologic Confounding,Variable, Epidemiological Confounding,Variables, Confounding,Variables, Epidemiologic Confounding,Variables, Epidemiological Confounding