# 1569.18 | ResearchBox

ResearchBox # 1569 - 'Interacting 2023'

You requested File #18 but it does not exist in Box #1569. Recall that authors may delete files before making a box public and file id's are not re-assigned


Bingo Table
  Show file names
  Show file IDs
  Show timestamps
A. Supplement


  Supplement - Interacting 2023 11 21.pdf


Fig 1 - Weight
  


  Fig 1 - Weight - Data weight and height.csv


  Fig 1 - Weight.r



  Fig 1 - Weight - Figure 1.png


Fig 2 - Examples (4)
  


  Fig 2 - Examples 4 - Fernbach.csv


  


  Fig 2 - Examples 4 - Preacher Curran Bauer.csv


  


  Fig 2 - Examples 4 - Simonsohn Gino.csv


  


  Fig 2 - Examples 4 - GSS.dta


  Fig 2 - Examples 4.r



  Fig 2 - Examples 4 - Figure 2.png


Fig 3 - GAM Examples


  Fig 3 - GAM Examples.r



  Fig 3 - GAM Examples - Figure 3.png


Fig 4, S1, S2


  Figure4 and Figure S2 .r



  Fig 4 Fig S1 - Johnsohn Neyman.r



  Figure 5.svg



  Figure 4.svg


Fig 5 - Conservatives


  Fig 5 - Conservatives.r



  Fig 5 - Conservatives - Figure 5.svg


Fig 6 - FPR


  Fig 6 - FPR - 1 - Simulate Ceiling.r



  Fig 6 - FPR - 2 - Simulate smooth.r



  Fig 6 - FPR - 3 - Make figure.r



  Fig 6 - FPR - Figure 6.svg


Fig 7 - Example


  Fig 7 - Example.r



  Fig 7 - Example - Figure 7.png


Fig 8 - Power


  Fig 8 - Power - 1. Simulations.r



  Fig 8 - Power - 2. Figure.r



  Fig 8 - Power - Figure 8 .svg


Fig 9 - Preacher et al


  Fig 9 - Preacher et al - 1. Analysis.r



  Fig 9 - Preacher et al - 2. Make figure.r



  Figure 9.png


Fig 10 - Parameters


  Fig 10 - Parameters.r



  Fig 10 - Parameters - Figure 10.png


Fig 11 - FPR


  Fig 11 - FPR - 1. Parameters.r



  Fig 11 - FPR - 2. Simulate.r



  Fig 11 - FPR - 3. Add GAM bootstrap.r



  Fig 11 - FPR - 4. Make figure.r



  Fig 11 - FPR - Figure 11.png


Fig 12 - Power


  Fig 12 - Power - 1. Simulations.r



  Fig 12 - Power - 2. Make figures.r



  Fig 12 - Power - 12A results .rds



  Fig 12 - Power - 12B results .rds



  Fig 12 - Power - 12C results .rds



  Fig 12 - Power - Figure - 12 A.svg



  Fig 12 - Power - Figure - 12B.svg


This cell has more files.


  Fig 12 - Power - Figure - 12C.svg


Fig S3


  Fig S3 - 1. Functions.r



  Fig S3 - 2. Resampling Horse Race.r



  Fig S3 - 3. Make figure.r



  Figure S3.svg


Fig S4


  Fig S4.r



  Fig S4 - Figure S4.svg


Fig S5


  Fig S5.r



  Fig S5 - Figure S5.svg


Fig S6


  Fig S6.r



  Fig S6 - Figure S6.svg


General


  General - Functions.r


Previewing files
Files can be previewed by clicking on descriptions.
Codebooks can be previewed by clicking on


  

Tell us if something is wrong with this Box



BOX INFORMATION

SUPPLEMENTARY FILES FOR
Uri Simonsohn, 'Interacting With Curves: How to Validly Test and Probe Interactions in the Real (Non-linear) World ', AMPPS
https://urisohn.com/42

LICENSE FOR USE
All content posted to ResearchBox is under a CC By 4.0 License (all use is allowed as long as authorship of the content is attributed). When using content from ResearchBox please cite the original work, and provide a link to the URL for this box (https://researchbox.org/1569).

BOX PUBLIC SINCE
November 21, 2023   (files may not be changed, deleted, or added)

BOX CREATORS
Uri Simonsohn (urisohn@gmail.com)

ABSTRACT
Hypotheses involving interactions, where one variable modifies the association between another two, are very common. They are typically tested relying on models that assume effects are linear, e.g., with a regression like y=a+bx+cz+dx·z. In the real world, however, few effects are linear, invalidating inferences about interactions. For instance, in realistic situations, the false-positive rate can be 100% for detecting an interaction, and a probed interaction can reliably produce estimated effects of the wrong sign. This paper proposes a revised toolbox for studying interactions in a curvilinear-robust manner, giving correct answers 'even' when effects aren't linear. It's applicable to most study designs, and produces results that are analogous to those of current -often invalid- practices. The presentation combines statistical intuition, demonstrations with published results, and simulations.