Events

content/en/event/propensity-techniques-and-matching-algorithms/index.md

@@ -58,17 +58,17 @@ slides:
 projects:
 ---
 
-In the context of analysis with observational data, causal identification and inference are common challenges faced by researchers and statisticians. In this sense, the Foundation Analytics workshop ‘Propensity techniques and matching algorithms for observational data’ given by our research associate, Bastián González-Bustamante, was an invaluable space to address these issues and share knowledge with the academic community.
+In the context of analysis with observational data, causal identification and inference are common challenges faced by researchers and statisticians. In this sense, the Foundation Analítica workshop "Propensity techniques and matching algorithms for observational data" given by our research associate, [Bastián González-Bustamante]({{< relref "../authors/bgonzalezbustamante" >}}), was an invaluable space to address these issues and share knowledge with the academic community.
 
-The workshop focused on the basics of propensity score analysis, matching techniques to correct for bias in observational data and models. Propensity scoring is a widely used method for estimating causality between variables in observational studies, where causes cannot be directly controlled for. However, this technique can also be subject to biases and limitations that affect the predictive power of the models.
+The workshop focused on the basics of propensity score analysis and matching techniques to correct for bias in observational data and models. Propensity scoring is a widely used method for estimating causality between variables in observational studies, where causes cannot be directly controlled for. However, this technique can also be subject to biases and limitations that affect the predictive power of the models.
 
-During the workshop, our research associate explored the main challenges posed by propensity score matching, such as the selection of relevant variables for the model, data treatment and the assessment of residual bias. In addition, ways to address these challenges to strengthen causal identification and causal inference strategies were presented.
+During the workshop, our research associate explored the main challenges posed by propensity score matching, such as selecting relevant variables for the model, data treatment, and assessing residual bias. In addition, ways to address these challenges to strengthen causal identification and causal inference strategies were presented.
 
-Among the matching techniques discussed was propensity scores matching. This involves assigning observations with similar characteristics to a control group and assigning weights to each observation according to its propensity score. This technique can be used to correct for selection bias and reduce the distortion caused by differences between groups.
+Among the matching techniques discussed was propensity score matching. This involves assigning observations with similar characteristics to a control group and assigning weights to each observation according to its propensity score. This technique can be used to correct for selection bias and reduce the distortion caused by differences between groups.
 
 The abbreviated demonstration on Posit Cloud, a data analytics and visualisation platform, allowed participants to experience the techniques presented. Attendees were able to see how these matching algorithms can be implemented.
 
-In summary, the workshop "Propensity Techniques and Matching Algorithms for Observational Data" was a success in terms of sharing knowledge and experience in causal identification and inference. Our research associate provided a clear and accessible overview of propensity and matching techniques, and participants benefited from the hands-on demonstration of propensity and matching algorithms for observational data. participants benefited from the hands-on demonstration in Posit Cloud. We hope this experience has inspired our colleagues to explore new ways of approaching analysis with observational data. to approach analysis with observational data and improve their causal identification and inference strategies.
+In summary, the workshop "Propensity techniques and matching algorithms for observational data" was a success in terms of sharing knowledge and experience in causal identification and inference. Our research associate provided a clear and accessible overview of propensity and matching techniques, and participants benefited from the hands-on demonstration on Posit Cloud. We hope this experience has inspired our colleagues to explore new approaches to analysis with observational data and improve their causal identification and inference strategies.
 
 _* AI-generated text_ <br>
 [_Read more about how we generate our content_]({{< relref "../post/2024-08-30-a-shift-in-our-communication-strategy" >}})

content/es/event/propensity-techniques-and-matching-algorithms/index.md

@@ -12,7 +12,7 @@ address:
   ## postcode: ''
   country: 
 
-summary: 'En el contexto del análisis con datos observacionales, la identificación e inferencia causal son desafíos comunes que enfrentan los investigadores y estadísticos. En este sentido, el taller de Analítica Fundación "Técnicas de propensión y algoritmos de emparejamiento para datos observacionales" dictado por nuestro investigador asociado, Bastián González-Bustamante, fue un espacio invaluable para abordar estos temas y compartir conocimientos con la comunidad académica.'
+summary: 'En el contexto del análisis con datos observacionales, la identificación e inferencia causal son desafíos comunes que enfrentan los investigadores y estadísticos. En este sentido, el taller de Analítica Fundación "Técnicas de propensión y algoritmos de emparejamiento para datos observacionales" dictado por nuestro investigador asociado, [Bastián González-Bustamante]({{< relref "../authors/bgonzalezbustamante" >}}), fue un espacio invaluable para abordar estos temas y compartir conocimientos con la comunidad académica.'
 abstract: ''
 
 # Talk start and end times.
@@ -58,7 +58,7 @@ slides:
 projects:
 ---
 
-En el contexto del análisis con datos observacionales, la identificación e inferencia causal son desafíos comunes que enfrentan los investigadores y estadísticos. En este sentido, el taller de Analítica Fundación "Técnicas de propensión y algoritmos de emparejamiento para datos observacionales" dictado por nuestro investigador asociado, Bastián González-Bustamante, fue un espacio invaluable para abordar estos temas y compartir conocimientos con la comunidad académica.
+En el contexto del análisis con datos observacionales, la identificación e inferencia causal son desafíos comunes que enfrentan los investigadores y estadísticos. En este sentido, el taller de Analítica Fundación "Técnicas de propensión y algoritmos de emparejamiento para datos observacionales" dictado por nuestro investigador asociado, [Bastián González-Bustamante]({{< relref "../authors/bgonzalezbustamante" >}}), fue un espacio invaluable para abordar estos temas y compartir conocimientos con la comunidad académica.
 
 El taller se centró en los fundamentos del análisis con puntuación de propensión, técnicas de emparejamiento para corregir el sesgo en datos y modelos observacionales. La propensión es un método ampliamente utilizado para estimar la causalidad entre variables en estudios observacionales, donde no se puede controlar directamente las causas. Sin embargo, esta técnica también puede estar sujeta a sesgos y limitaciones que afectan el poder predictivo de los modelos.