Skip to main content
added 117 characters in body
Source Link
Tim
  • 141.2k
  • 26
  • 270
  • 512

If you have no information, you can use “uninformative” priors. Those priors aim to bring as little information as possible, but as you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. That is why more modern recommendation would be to pick a weakly informative prior (centered on something, but very uncertain).

On another hand, using a frequentist model does not mean making no assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, or using regularized regression you are using implicit priors on the parameters, etc. Even if you wanted to make as few assumptions as possible and used a nonparametric model, you would be making some assumptions. For example, say that you would pick $k$NN regression that just averages among "similar" observations. Still, you need to decide on a similarity metric to define what "similar" means and you need to somehow pick the hyperparameter $k$. With Bayesian models, you make additional assumptions by choosing priors, but other approaches also make assumptions.

But, can you have truly no information about something? Say a meteor hits the planet Earth and brings us a new virus from space. A Bayesian statistician needs to build a model on it. They know nothing about space viruses. Hopefully, they know a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge and assumptions that they could use to come up with priors.

If you have no information, you can use “uninformative” priors. Those priors aim to bring as little information as possible, but as you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. That is why more modern recommendation would be to pick a weakly informative prior (centered on something, but very uncertain).

On another hand, using a frequentist model does not mean making no assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, or using regularized regression you are using implicit priors on the parameters, etc. Even if you wanted to make as few assumptions as possible and used a nonparametric model, you would be making some assumptions. For example, say that you would pick $k$NN regression that just averages among "similar" observations. Still, you need to decide on a similarity metric to define what "similar" means and you need to somehow pick the hyperparameter $k$.

But, can you have truly no information about something? Say a meteor hits the planet Earth and brings us a new virus from space. A Bayesian statistician needs to build a model on it. They know nothing about space viruses. Hopefully, they know a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge and assumptions that they could use to come up with priors.

If you have no information, you can use “uninformative” priors. Those priors aim to bring as little information as possible, but as you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. That is why more modern recommendation would be to pick a weakly informative prior (centered on something, but very uncertain).

On another hand, using a frequentist model does not mean making no assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, or using regularized regression you are using implicit priors on the parameters, etc. Even if you wanted to make as few assumptions as possible and used a nonparametric model, you would be making some assumptions. For example, say that you would pick $k$NN regression that just averages among "similar" observations. Still, you need to decide on a similarity metric to define what "similar" means and you need to somehow pick the hyperparameter $k$. With Bayesian models, you make additional assumptions by choosing priors, but other approaches also make assumptions.

But, can you have truly no information about something? Say a meteor hits the planet Earth and brings us a new virus from space. A Bayesian statistician needs to build a model on it. They know nothing about space viruses. Hopefully, they know a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge and assumptions that they could use to come up with priors.

added 648 characters in body
Source Link
Tim
  • 141.2k
  • 26
  • 270
  • 512

If you have no information, you can use “uninformative” priors. As Those priors aim to bring as little information as possible, but as you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. That is why more modern recommendation would be to pick a weakly informative prior (centered on something, but very uncertain).

On another hand, using a frequentist model does not mean making no assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, whenor using regularized regression you are using implicit priors on the parameters, etc. Even if you wanted to make as few assumptions as possible and used a nonparametric model, you would be making some assumptions. For example, say that you would pick $k$NN regression that just averages among "similar" observations. Still, you need to decide on a similarity metric to define what "similar" means and you need to somehow pick the hyperparameter $k$.

But, can you have truly no information about something? Say a metermeteor hits the planet Earth and brings theus a new virus from space to us. A Bayesian statistician needs to build a model on it. He knowsThey know nothing about space viruses. Hopefully, he knowsthey know a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge and assumptions that they could use to come up with priors.

If you have no information, you can use “uninformative” priors. As you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. On another hand, using a frequentist model does not mean making no assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, when using regularized regression you are using implicit priors on the parameters, etc.

But, can you have truly no information about something? Say a meter hits the planet Earth and brings the new virus from space to us. A Bayesian statistician needs to build a model on it. He knows nothing about space viruses. Hopefully, he knows a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge that they could use to come up with priors.

If you have no information, you can use “uninformative” priors. Those priors aim to bring as little information as possible, but as you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. That is why more modern recommendation would be to pick a weakly informative prior (centered on something, but very uncertain).

On another hand, using a frequentist model does not mean making no assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, or using regularized regression you are using implicit priors on the parameters, etc. Even if you wanted to make as few assumptions as possible and used a nonparametric model, you would be making some assumptions. For example, say that you would pick $k$NN regression that just averages among "similar" observations. Still, you need to decide on a similarity metric to define what "similar" means and you need to somehow pick the hyperparameter $k$.

But, can you have truly no information about something? Say a meteor hits the planet Earth and brings us a new virus from space. A Bayesian statistician needs to build a model on it. They know nothing about space viruses. Hopefully, they know a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge and assumptions that they could use to come up with priors.

deleted 1 character in body
Source Link
Tim
  • 141.2k
  • 26
  • 270
  • 512

If you have no information, you can use “uninformative” priors. As you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. On another hand, using a frequentist model does not mean making anyno assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, when using regularized regression you are using implicit priors on the parameters, etc.

But, can you have truly no information about something? Say a meter hits the planet Earth and brings the new virus from space to us. A Bayesian statistician needs to build a model on it. He knows nothing about space viruses. Hopefully, he knows a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge that they could use to come up with some priors.

If you have no information, you can use “uninformative” priors. As you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. On another hand, using a frequentist model does not mean making any assumptions: you may still assume Gaussian likelihood, a linear relationship between the variables, when using regularized regression you are using implicit priors on the parameters, etc.

But, can you have truly no information about something? Say a meter hits the planet Earth and brings the new virus from space to us. A Bayesian statistician needs to build a model on it. He knows nothing about space viruses. Hopefully, he knows a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge that they could use to come up with some priors.

If you have no information, you can use “uninformative” priors. As you already learned from the What is an "uninformative prior"? Can we ever have one with truly no information? thread, the name is a little bit misleading because even such priors bring some information to the model. On another hand, using a frequentist model does not mean making no assumptions: you may still assume things like Gaussian likelihood, a linear relationship between the variables, when using regularized regression you are using implicit priors on the parameters, etc.

But, can you have truly no information about something? Say a meter hits the planet Earth and brings the new virus from space to us. A Bayesian statistician needs to build a model on it. He knows nothing about space viruses. Hopefully, he knows a lot about viruses from Earth, many scientists also did a lot of educated guesses on what extraterrestrial life forms could be and how they could be similar or different to the life on Earth, etc. The scientist in fact has a lot of prior knowledge that they could use to come up with priors.

Source Link
Tim
  • 141.2k
  • 26
  • 270
  • 512
Loading