Agree or Disagree?

Discussion: discuss what is required to make causal statements in the context of regression analysis... In other words,what is required to be able to say that a particular independent variable, or treatment,causes the dependent variable?In your answer, discuss the role played by obtaining a random sample and random assignment of the "treatment" (in many cases, the treatment is the main independent variable).Once we obtain a satisfactory regression model, discuss potential sources of bias - e.g., not using the correct functional form, measurement error, omitted variable bias, the simultaneity problem, etc.Finally, what are some key considerations in selecting "control" variables in a multiple regression analysis.

1. Discussion: What is required to make causal statements in the context of regression analysis (In your answer, discuss the role played by obtaining a random sample and random assignment of the "treatment" (in many cases, the treatment is the main independent variable)?

Regression analysis alone cannot be used to create causality.Causality can be established with the following requirements: assuming that the variables are treatments and outcomes.Additional requirements are data on outcome, observed treatment, and unobserved treatment, covariation, temporal, and precedence.When obtaining a random sample, it is important to understand the population.The random sample should mirror the overall population and the selected subset will have an equal chance of being selected.Selecting the independent variable is important because this variable assists the user in coming up with casual assumptions.

1. Once we obtain a satisfactory regression model, discuss potential sources of bias - e.g., not using the correct functional form, measurement error, omitted variable bias, the simultaneity problem, etc.

Even though the regression model is complete there is always a chance for bias to occur that the user did not notice.Some of these biases can be population bias, cause-effect bias, confirmation bias, and confounding bias.Of the biases listed two really stuck out which are confirmation bias and confound bias.According to Alexander, Lopes, Ricchetti-Masterson, and Yeatts (2015), "Confounding is a bias because it can result in a distortion in the measure of association between an exposure and health outcome" (p. 1).I think confirmation bias is important because it can happen to the best of us.In this bias, the user continues the analysis until their assumption is correct.

1. Finally, what are some key considerations in selecting "control" variables in a multiple regression analysis?

One key consideration when selecting a control variable for multiple regression analysis is that the selected variable should influence the outcome as well as interact with the treatment.Another key consideration would be to select a control variable that stays constant throughout the analysis.Lastly selecting correct control variables help the regression because they help establish a causal relationship. Stat Help (n.d.) states, "It is however important to think through which control variables that should be included. The analysis is not better or more sophisticated just because more control variables are included. We should for example not control for variables that come after the independent variable in the causal chain" (p. 1).