10 votes
Accepted

Interaction term switching sign of main effect

When the interaction (product term) is in the model, the coefficient for the "main effect" (lower-order term) of grid size (0.00774) gives you the expected slope when the number of ...
Christian Geiser's user avatar
7 votes
Accepted

Variable selection in logistic regression

The problem with your proposed approach is that every predictor in itself may not correlate with the outcome, but interactions between them might. Or you might have a curvilinear relationship between ...
Stephan Kolassa's user avatar
4 votes

Variable selection in logistic regression

Adding to Stephen's excellent answer, there are lots of reasons not to do automatic variable selection. He covers some of them. But there are others: A variable could be a mediator without being ...
Peter Flom's user avatar
  • 110k
3 votes

Poisson regression for rare events?

Welcome to CV. Poisson regression is fine for rare events. In fact, it got started with modeling the number of soldiers kicked to death by the horses --- not common, even in the days of large cavalry ...
Peter Flom's user avatar
  • 110k
2 votes
Accepted

Prove that OLS estimated coefficients are independent from other variables

In matrix notation you have $Y=X\beta + U$ and OLS provides $$\widehat{\beta} = \left(X'X\right)^{-1}X'Y = \beta + \left(X'X\right)^{-1}X'U. $$ As long as $X$ and $U$ are the same, $\widehat{\beta}-\...
Math-fun's user avatar
  • 405
1 vote

Prove that OLS estimated coefficients are independent from other variables

You formula for $\beta_2$ is wrong. Suppose you would have two independent variables, then you can see in this link that the estimates $\beta_1$ and $\beta_2$ depend on both $x_1$ and $x_2$. Only when ...
BenP's user avatar
  • 318
1 vote

How to model this dataset?

I want to estimate the individual contributions to the group scores, considering the characteristics provided. It seems that you’re looking for the posterior probability $\Pr(S=s|\boldsymbol X = \...
Alexandre Huat's user avatar
1 vote

Mediation analysis with interaction effect

Maybe the SE for the AB equation is wrong? It looks like the so-called "Sobel test", which is a first-order Taylor series approximation of the product terms sampling distributions, called ...
Terrence's user avatar
  • 1,793
1 vote
Accepted

Pros and cons of different methods for comparing betas in regression

Acknowledging that I provided the linked answer to #4 prior to providing a response. In your opinion, which of these methods conceptually most closely aligns with the verbal hypothesis that "...
jluchman's user avatar
  • 937
1 vote

How to determine number of independent variables in regression?

You write I have heard that having more than one independent variable is useful when predicting human behaviour since it can be influenced by a combination of several factors! That is correct. It's ...
Peter Flom's user avatar
  • 110k

Only top scored, non community-wiki answers of a minimum length are eligible