User Matthew Drury

7 votes

Accepted

Am I breaking the assumptions of the Poisson distribution?

answered Jun 22, 2015 at 23:08

7 votes

Should predictive accuracy or, alternatively, minimizing the MSE, be reconsidered?

answered Jun 13, 2015 at 17:35

7 votes

Accepted

interpretation of slope estimate of Poisson regression

answered Sep 8, 2016 at 20:57

7 votes

stepwise logistic regression non significative variables(high p-values)

answered Dec 4, 2016 at 16:41

7 votes

Object of type 'closure' is not subsettable

answered Sep 5, 2016 at 22:18

7 votes

Accepted

GLM Categorical Variable Level grouping / simplification

answered May 31, 2016 at 2:21

7 votes

Predictive power vs. explanatory power of statistical models

answered Mar 17, 2016 at 23:09

6 votes

Accepted

Parameter n_iter in scikit-learn's SGDClassifier

answered May 27, 2016 at 17:47

6 votes

Why is standard deviation defined as sqrt(var(x)) and not as abs(X-u)?

answered Apr 4, 2016 at 16:49

6 votes

What's in a name: hyperparameters

answered Apr 20, 2016 at 0:02

6 votes

Accepted

What is out-of-fold average?

answered Jul 18, 2016 at 4:28

6 votes

Accepted

Difference in expressions of variance and bias between MSE and MSPE

answered Jun 5, 2016 at 22:44

6 votes

Accepted

GBM: impact of the loss function

answered Jun 5, 2016 at 23:03

6 votes

Expectation of a uniform given a value

answered Jun 4, 2017 at 17:40

6 votes

Can someone explain what the foldid argument in glmnet does?

answered Jul 23, 2015 at 19:08

6 votes

Accepted

Notation - gradients

answered Jul 24, 2015 at 18:25

6 votes

How can Poisson GLM work with non-count data (rate data)?

answered Aug 20, 2015 at 2:49

6 votes

Accepted

Let $X$ be a random variable and $f$ an invertible function. Then the CDF of a random variable $Y=f(X)$ always exists?

answered Sep 25, 2015 at 15:10

6 votes

Difference between `mle` and `optimize` functions in R

answered Sep 30, 2015 at 19:08

6 votes

Accepted

Interpreting coefficient values in lasso regression

answered May 3, 2015 at 5:25

6 votes

Can I make a linear congruential generator with a lognormal distribution?

answered May 16, 2015 at 5:05

6 votes

Accepted

Generalised least squares: from regression coefficients to correlation coefficients?

answered May 27, 2015 at 2:34

6 votes

Accepted

Expectation of the absolute difference of two i.i.d Normal distributions

answered Jul 3, 2017 at 0:14

6 votes

Accepted

How is the decision boundary's equation determined?

answered Jul 8, 2017 at 15:30

6 votes

Normality distribution and logistic regression

answered Jul 26, 2017 at 4:54

6 votes

In model selection with $Y$ as the outcome and $ X = (X_1, \ldots, X_p)$ the explanatory variables, why do we care about $F_{Y|X}$?

answered Sep 2, 2017 at 23:28

6 votes

MLE for Poisson distribution is undefined with all-zero observations

answered Sep 26, 2017 at 3:26

6 votes

Accepted

Is it a creditable approach to use Random Forrest Variable importance for causal inference?

answered Jan 31, 2018 at 18:46

6 votes

Accepted

Why is only linearity between predictors a problem?

answered Nov 5, 2017 at 15:41

6 votes

Accepted

What do we exactly mean by a biased estimate?

answered Mar 27, 2018 at 23:35

Stack Exchange Network

433 Answers

Am I breaking the assumptions of the Poisson distribution?

Should predictive accuracy or, alternatively, minimizing the MSE, be reconsidered?

interpretation of slope estimate of Poisson regression

stepwise logistic regression non significative variables(high p-values)

Object of type 'closure' is not subsettable

GLM Categorical Variable Level grouping / simplification

Predictive power vs. explanatory power of statistical models

Parameter n_iter in scikit-learn's SGDClassifier

Why is standard deviation defined as sqrt(var(x)) and not as abs(X-u)?

What's in a name: hyperparameters

What is out-of-fold average?

Difference in expressions of variance and bias between MSE and MSPE

GBM: impact of the loss function

Expectation of a uniform given a value

Can someone explain what the foldid argument in glmnet does?

Notation - gradients

How can Poisson GLM work with non-count data (rate data)?

Let $X$ be a random variable and $f$ an invertible function. Then the CDF of a random variable $Y=f(X)$ always exists?

Difference between `mle` and `optimize` functions in R

Interpreting coefficient values in lasso regression

Can I make a linear congruential generator with a lognormal distribution?

Generalised least squares: from regression coefficients to correlation coefficients?

Expectation of the absolute difference of two i.i.d Normal distributions

How is the decision boundary's equation determined?

Normality distribution and logistic regression

In model selection with $Y$ as the outcome and $ X = (X_1, \ldots, X_p)$ the explanatory variables, why do we care about $F_{Y|X}$?

MLE for Poisson distribution is undefined with all-zero observations

Is it a creditable approach to use Random Forrest Variable importance for causal inference?

Why is only linearity between predictors a problem?

What do we exactly mean by a biased estimate?