Skip to main content
Cross Validated

Return to Question

clarified issue in title; added tags; light editing
Source Link
gung - Reinstate Monica
gung - Reinstate Monica
  • 147.5k
  • 89
  • 406
  • 717

Adding both Either quadratic andor interaction terms to the model affects significanceterm is significant in isolation, but neither are together

As part of an assignment, I had to fit a model with two predictor variables. I then had to draw a plot of the models' residuals against one of the included predictors and make changes based on that. The plot showed a curvilinear trend and so I included a quadratic term for that predictor. The new model showed the quadratic term to be significant. All good so far.

However, the data suggest that an interaction makes sense, too. Adding an interaction term to the original model also 'fixed' the curvilinear trend and was also significant when added to the model (without the quadratic term). The problem is, when both the quadratic and the interaction term are added to the model, one of them is not significant.

Which term (the quadratic or the interaction) should I include in the model and why? (Quadratic or interaction)

Adding both quadratic and interaction terms to the model affects significance

As part of an assignment, I had to fit a model with two predictor variables. I then had to draw a plot of the models' residuals against one of the included predictors and make changes based on that. The plot showed a curvilinear trend and so I included a quadratic term for that predictor. The new model showed the quadratic term to be significant. All good so far.

However, the data suggest that an interaction makes sense, too. Adding an interaction term to the original model also 'fixed' the curvilinear trend and was also significant when added to the model (without the quadratic term). The problem is, when both the quadratic and the interaction term are added to the model, one of them is not significant.

Which term should I include in the model and why? (Quadratic or interaction)

Either quadratic or interaction term is significant in isolation, but neither are together

As part of an assignment, I had to fit a model with two predictor variables. I then had to draw a plot of the models' residuals against one of the included predictors and make changes based on that. The plot showed a curvilinear trend and so I included a quadratic term for that predictor. The new model showed the quadratic term to be significant. All good so far.

However, the data suggest that an interaction makes sense, too. Adding an interaction term to the original model also 'fixed' the curvilinear trend and was also significant when added to the model (without the quadratic term). The problem is, when both the quadratic and the interaction term are added to the model, one of them is not significant.

Which term (the quadratic or the interaction) should I include in the model and why?

Tweeted twitter.com/#!/StackStats/status/236521819606237184
Removed signature, added more detail to title
Source Link
edit approved Aug 17, 2012 at 1:07
jonsca
edit approved Aug 17, 2012 at 1:07
jonsca
  • 1.8k
  • 3
  • 20
  • 30

Quadratic Adding both quadratic and interaction terms vs interactionsto the model affects significance

As part of an assignment, I had to fit a model with two predictor variables. I then had to draw a plot of the models' residuals against one of the included predictors and make changes based on that. The plot showed a curvilinear trend and so I included a quadratic term for that predictor. The new model showed the quadratic term to be significant. All good so far.

However, the data suggestssuggest that an interaction makes sense, too. Adding an interaction term to the original model also 'fixed' the curvilinear trend and was also significant when added to the model (without the quadratic term). The problem is that, when both the quadratic and the interaction term are added to the model, one of them is not significant.

Which term should I include in the model and why? (Quadratic or interaction)

Thank you very much, Tal

Quadratic terms vs interactions

As part of an assignment I had to fit a model with two predictor variables. I then had to draw a plot of the models' residuals against one of the included predictors and make changes based on that. The plot showed a curvilinear trend and so I included a quadratic term for that predictor. The new model showed the quadratic term to be significant. All good so far.

However, the data suggests that an interaction makes sense too. Adding an interaction term to the original model also 'fixed' the curvilinear trend and was also significant when added to the model (without the quadratic term). The problem is that when both the quadratic and the interaction term are added to the model, one of them is not significant.

Which term should I include in the model and why? (Quadratic or interaction)

Thank you very much, Tal

Adding both quadratic and interaction terms to the model affects significance

As part of an assignment, I had to fit a model with two predictor variables. I then had to draw a plot of the models' residuals against one of the included predictors and make changes based on that. The plot showed a curvilinear trend and so I included a quadratic term for that predictor. The new model showed the quadratic term to be significant. All good so far.

However, the data suggest that an interaction makes sense, too. Adding an interaction term to the original model also 'fixed' the curvilinear trend and was also significant when added to the model (without the quadratic term). The problem is, when both the quadratic and the interaction term are added to the model, one of them is not significant.

Which term should I include in the model and why? (Quadratic or interaction)

Source Link
Tal Bashan
Tal Bashan
  • 151
  • 1
  • 1
  • 3

Quadratic terms vs interactions

As part of an assignment I had to fit a model with two predictor variables. I then had to draw a plot of the models' residuals against one of the included predictors and make changes based on that. The plot showed a curvilinear trend and so I included a quadratic term for that predictor. The new model showed the quadratic term to be significant. All good so far.

However, the data suggests that an interaction makes sense too. Adding an interaction term to the original model also 'fixed' the curvilinear trend and was also significant when added to the model (without the quadratic term). The problem is that when both the quadratic and the interaction term are added to the model, one of them is not significant.

Which term should I include in the model and why? (Quadratic or interaction)

Thank you very much, Tal