Skip to main content
deleted 30 characters in body
Source Link
Nick Cox
  • 59.4k
  • 8
  • 136
  • 212

When you usingWith logistic regression what you analyse is the association of a binary outcome towith a set of predictors. In particular you are modelling the $\log(\text{odds})$ of that particular outcome. The odds themselves are simply: $\text{odds} = \frac{\text{Pr(of Occurring)}}{\text{Pr(of Not Occurring)}} = \frac{\text{Pr(of Occurring)}}{1 - \text{Pr(of Occurring)}}$ where $\text{Pr}$ refers to proportions (or loosely speaking probability). Therefore the estimated coefficient $\hat{\beta}$ in your model shows the difference in $\log(\text{odds})$ between two subjects that differ by one unit of your predictor (here: hours) when all other predictors are constant (or as in your case just absent).

If ones wants toTo find the change in terms of the proportions that are modelled he needsyou need to:

  1. Get the $\log(\text{odds})$ estimate.
  2. Exponentiate it to get the $\text{odds}$.
  3. Get the new proportions as: $\text{Pr}_{\text{new}} = \frac{\text{odds}}{1 + \text{odds}} $. (This later follows from the equality shown above.)

When you using logistic regression what you analyse is the association of a binary outcome to a set of predictors. In particular you are modelling the $\log(\text{odds})$ of that particular outcome. The odds themselves are simply: $\text{odds} = \frac{\text{Pr(of Occurring)}}{\text{Pr(of Not Occurring)}} = \frac{\text{Pr(of Occurring)}}{1 - \text{Pr(of Occurring)}}$ where $\text{Pr}$ refers to proportions (or loosely speaking probability). Therefore the estimated coefficient $\hat{\beta}$ in your model shows the difference in $\log(\text{odds})$ between two subjects that differ by one unit of your predictor (here: hours) when all other predictors are constant (or as in your case just absent).

If ones wants to find the change in terms of the proportions that are modelled he needs to:

  1. Get the $\log(\text{odds})$ estimate.
  2. Exponentiate it to get the $\text{odds}$.
  3. Get the new proportions as: $\text{Pr}_{\text{new}} = \frac{\text{odds}}{1 + \text{odds}} $. (This later follows from the equality shown above.)

With logistic regression you analyse the association of a binary outcome with a set of predictors. In particular you are modelling the $\log(\text{odds})$ of that particular outcome. The odds themselves are simply: $\text{odds} = \frac{\text{Pr(of Occurring)}}{\text{Pr(of Not Occurring)}} = \frac{\text{Pr(of Occurring)}}{1 - \text{Pr(of Occurring)}}$ where $\text{Pr}$ refers to proportions (or loosely speaking probability). Therefore the estimated coefficient $\hat{\beta}$ in your model shows the difference in $\log(\text{odds})$ between two subjects that differ by one unit of your predictor (here: hours) when all other predictors are constant (or as in your case just absent).

To find the change in terms of the proportions that are modelled you need to:

  1. Get the $\log(\text{odds})$ estimate.
  2. Exponentiate it to get the $\text{odds}$.
  3. Get the new proportions as: $\text{Pr}_{\text{new}} = \frac{\text{odds}}{1 + \text{odds}} $. (This follows from the equality shown above.)
Added clarification about how to get estimates for proportions.
Source Link
usεr11852
  • 46k
  • 3
  • 106
  • 164

When you using logistic regression what you analyse is the association of a binary outcome to a set of predictors. In particular you are modelling the $\log(\text{odds})$ of that particular outcome. The odds themselves are simply: $\text{odds} = \frac{\text{Pr(of Occuring)}}{\text{Pr(of Not Occuring)}}$$\text{odds} = \frac{\text{Pr(of Occurring)}}{\text{Pr(of Not Occurring)}} = \frac{\text{Pr(of Occurring)}}{1 - \text{Pr(of Occurring)}}$ where $\text{Pr}$ refers to proportions (or loosely speaking probability). So thatTherefore the estimated coefficient $\beta$$\hat{\beta}$ in your model shows the difference in $\log(\text{odds})$ between two subjects that differ by one unit of your predictor, (here: hours in your case,) when all other predictors are constant (or as in your case just absent).

If ones wants to find the change in terms of the proportions that are modelled he needs to:

  1. Get the $\log(\text{odds})$ estimate.
  2. Exponentiate it to get the $\text{odds}$.
  3. Get the new proportions as: $\text{Pr}_{\text{new}} = \frac{\text{odds}}{1 + \text{odds}} $. (This later follows from the equality shown above.)

When you using logistic regression what you analyse is the association of a binary outcome to a set of predictors. In particular you are modelling the $\log(\text{odds})$ of that particular outcome. The odds themselves are simply: $\text{odds} = \frac{\text{Pr(of Occuring)}}{\text{Pr(of Not Occuring)}}$. So that coefficient $\beta$ in your model shows the difference in $\log(\text{odds})$ between two subjects that differ by one unit of your predictor, hours in your case, when all other predictors are constant (or as in your case just absent).

When you using logistic regression what you analyse is the association of a binary outcome to a set of predictors. In particular you are modelling the $\log(\text{odds})$ of that particular outcome. The odds themselves are simply: $\text{odds} = \frac{\text{Pr(of Occurring)}}{\text{Pr(of Not Occurring)}} = \frac{\text{Pr(of Occurring)}}{1 - \text{Pr(of Occurring)}}$ where $\text{Pr}$ refers to proportions (or loosely speaking probability). Therefore the estimated coefficient $\hat{\beta}$ in your model shows the difference in $\log(\text{odds})$ between two subjects that differ by one unit of your predictor (here: hours) when all other predictors are constant (or as in your case just absent).

If ones wants to find the change in terms of the proportions that are modelled he needs to:

  1. Get the $\log(\text{odds})$ estimate.
  2. Exponentiate it to get the $\text{odds}$.
  3. Get the new proportions as: $\text{Pr}_{\text{new}} = \frac{\text{odds}}{1 + \text{odds}} $. (This later follows from the equality shown above.)
Source Link
usεr11852
  • 46k
  • 3
  • 106
  • 164

When you using logistic regression what you analyse is the association of a binary outcome to a set of predictors. In particular you are modelling the $\log(\text{odds})$ of that particular outcome. The odds themselves are simply: $\text{odds} = \frac{\text{Pr(of Occuring)}}{\text{Pr(of Not Occuring)}}$. So that coefficient $\beta$ in your model shows the difference in $\log(\text{odds})$ between two subjects that differ by one unit of your predictor, hours in your case, when all other predictors are constant (or as in your case just absent).