scholarly journals A Warning About Using Predicted Values From Regression Models for Epidemiologic Inquiry

2020 ◽  
Author(s):  
Elizabeth L Ogburn ◽  
Kara E Rudolph ◽  
Rachel Morello-Frosch ◽  
Amber Khan ◽  
Joan A Casey
Keyword(s):  
Observational Data ◽  
Treatment Effect ◽  
Regression Models ◽  
Original Data ◽  
Average Treatment Effect ◽  
Direct Access ◽  
Auxiliary Model ◽  
Alternative Hypotheses ◽  
Predicted Values ◽  
Access To Data

Abstract In many settings researchers may not have direct access to data on one or more variables needed for an analysis, and instead may use regression-based estimates of those variables. Using such estimates in place of original data, however, introduces complications and can result in uninterpretable analyses. In simulations and observational data we illustrate the issues that arise when an average treatment effect is estimated from data where the outcome of interest is a prediction from an auxiliary model. We show that bias in any direction can result, both under the null and alternative hypotheses.

scholarly journals Treatment Interactions with Nonexperimental Data in Stata

2011 ◽  
Vol 11 (4) ◽  
pp. 545-555 ◽  
Author(s):  
Graham K. Brown ◽  
Thanos Mergoupis
Keyword(s):  
Experimental Data ◽  
Observational Data ◽  
Treatment Effect ◽  
Treatment Effects ◽  
Average Treatment Effect ◽  
Interaction Parameters ◽  
Average Treatment ◽  
Interaction Terms ◽  
Treatment Interaction ◽  
Predicted Values

Treatment effects may vary with the observed characteristics of the treated, often with important implications. In the context of experimental data, a growing literature deals with the problem of specifying treatment interaction terms that most effectively capture this variation. Some results of this literature are now implemented in Stata. With nonexperimental (observational) data, and in particular when selection into treatment depends on unmeasured factors, treatment effects can be estimated using Stata's treatreg command. Though not originally designed for this purpose, treatreg can be used to consistently estimate treatment interaction parameters. With interactions, however, adjustments are required to generate predicted values and estimate the average treatment effect. In this article, we introduce commands that perform this adjustment for multiplicative interactions, and we show the required adjustment for more complicated interactions.

scholarly journals Quantifying the Treatment Effect of Kidney Transplantation Relative to Dialysis on Survival Time: New Results Based on Propensity Score Weighting and Longitudinal Observational Data from Sweden

2020 ◽  
Vol 17 (19) ◽  
pp. 7318
Author(s):  
Ye Zhang ◽  
Ulf-G. Gerdtham ◽  
Helena Rydell ◽  
Johan Jarl
Keyword(s):  
Kidney Transplantation ◽  
Renal Replacement Therapy ◽  
Propensity Score ◽  
Survival Time ◽  
Replacement Therapy ◽  
Observational Data ◽  
Treatment Effect ◽  
Average Treatment Effect ◽  
Survival Advantage ◽  
Propensity Score Weighting

Using observational data to assess the treatment effects on outcomes of kidney transplantation relative to dialysis for patients on renal replacement therapy is challenging due to the non-random selection into treatment. This study applied the propensity score weighting approach in order to address the treatment selection bias of kidney transplantation on survival time compared with dialysis for patients on the waitlist. We included 2676 adult waitlisted patients who started renal replacement therapy in Sweden between 1 January 1995, and 31 December 2012. Weibull and logistic regression models were used for the outcome and treatment models, respectively. The potential outcome mean and the average treatment effect were estimated using an inverse-probability-weighted regression adjustment approach. The estimated survival times from start of renal replacement therapy were 23.1 years (95% confidence interval (CI): 21.2−25.0) and 9.3 years (95% CI: 7.8−10.8) for kidney transplantation and dialysis, respectively. The survival advantage of kidney transplantation compared with dialysis was estimated to 13.8 years (95% CI: 11.4−16.2). There was no significant difference in the survival advantage of transplantation between men and women. Controlling for possible immortality bias reduced the survival advantage to 9.1–9.9 years. Our results suggest that kidney transplantation substantially increases survival time compared with dialysis in Sweden and that this consequence of treatment is equally distributed over sex.

scholarly journals Evaluación de impacto académico y social en egresados universitarios

2019 ◽  
Vol 30 (3) ◽  
pp. 695-712
Author(s):  
Gabriel González ◽  
Luisa Díez-Echavarría ◽  
Elkin Zapa ◽  
Danilo Eusse
Keyword(s):  
Treatment Effect ◽  
Average Treatment Effect ◽  
Educación Superior ◽  
Educacion Superior ◽  
Average Treatment

Las instituciones de educación superior deben formar a sus estudiantes según requerimientos del contexto en que se desenvuelven, ya que, sobre la base de su desempeño, es donde se medirá si las políticas de desarrollo socioeconómico son efectivas. Para lograrlo, es necesario identificar el impacto de esa educación en sus egresados, y hacer los ajustes necesarios que generen mejora continua. El objetivo de este artículo es estimar el impacto académico y social de egresados del Instituto Tecnológico Metropolitano – Medellín, a través de un análisis multivariado y la estimación del modelo Average Treatment Effect (ATE). Se encontró que la educación ofrecida a esta población ha generado un impacto académico, asociado a los estudios de actualización, y dos impactos sociales, asociados a la situación laboral y al nivel de ingresos percibidos por los egresados. Se recomienda usar esta metodología en otras instituciones, ya que suele arrojar resultados más informativos y precisos que los estudios tradicionales de caracterización, y se puede medir el efecto de cualquier estrategia.

The Effect of Extension Services and Credit on Agricultural Production in Bolivia, Peru, and Colombia

2021 ◽  
Author(s):  
Mateus C. R. Neves ◽  
Felipe De Figueiredo Silva ◽  
Carlos Otávio Freitas
Keyword(s):  
Travel Time ◽  
Treatment Effect ◽  
Agricultural Production ◽  
Treatment Effects ◽  
Geographic Information ◽  
Average Treatment Effect ◽  
Extension Services ◽  
Average Treatment ◽  
Andean Countries ◽  
Average Treatment Effects

In this paper we estimate the average treatment effect from access to extension services and credit on agricultural production in selected Andean countries (Bolivia, Peru, and Colombia). More specifically, we want to identify the effect of accessibility, here represented as travel time to the nearest area with 1,500 or more inhabitants per square kilometer or at least 50,000 inhabitants, on the likelihood of accessing extension and credit. To estimate the treatment effect and identify the effect of accessibility on these variables, we use data from the Colombian and Bolivian Agricultural Censuses of 2013 and 2014, respectively; a national agricultural survey from 2017 for Peru; and geographic information on travel time. We find that the average treatment effect for extension is higher compared to that of credit for farms in Bolivia and Peru, and lower for Colombia. The average treatment effects of extension and credit for Peruvian farms are $2,387.45 and $3,583.42 respectively. The average treatment effect for extension and credit are $941.92 and $668.69, respectively, while in Colombia are $1,365.98 and $1,192.51, respectively. We also find that accessibility and the likelihood of accessing these services are nonlinearly related. Results indicate that higher likelihood is associated with lower travel time, especially in the analysis of credit.

How local personal vote-earning attributes affect the aggregate party vote share: Evidence from the Belgian flexible-list PR system (2003–2014)

Politics ◽  
2018 ◽  
Vol 39 (4) ◽  
pp. 464-479
Author(s):  
Gert-Jan Put ◽  
Jef Smulders ◽  
Bart Maddens
Keyword(s):  
Regression Models ◽  
Empirical Test ◽  
Original Data ◽  
Ordinary Least Squares ◽  
Vote Share ◽  
District Level ◽  
National Party ◽  
Data Set ◽  
Geographically Distributed ◽  
Party Vote Shares

This article investigates the effect of candidates exhibiting local personal vote-earning attributes (PVEA) on the aggregate party vote share at the district level. Previous research has often assumed that packing ballot lists with localized candidates increases the aggregate party vote and seat shares. We present a strict empirical test of this argument by analysing the relative electoral swing of ballot lists at the district level, a measure of change in party vote shares which controls for the national party trend and previous party results in the district. The analysis is based on data of 7527 candidacies during six Belgian regional and federal election cycles between 2003 and 2014, which is aggregated to an original data set of 223 ballot lists. The ordinary least squares (OLS) regression models do not show a significant effect of candidates exhibiting local PVEA on relative electoral swing of ballot lists. However, the results suggest that ballot lists do benefit electorally if candidates with local PVEA are geographically distributed over different municipalities in the district.

Sign in / Sign up

Export Citation Format

Share Document