user avatar
user avatar
user avatar
Hugh
  • Member for 9 years, 1 month
  • Last seen more than 2 years ago
35 votes
Accepted

Can AUC-ROC be between 0-0.5?

27 votes
Accepted

How does minibatch gradient descent update the weights for each example in a batch?

20 votes
Accepted

Can one-sided confidence intervals have 95% coverage

16 votes
Accepted

Can I trust a significant result of a t-test if the sample size is small?

12 votes
Accepted

Feature selection using deep learning?

7 votes

Why should/does(?) statistical sampling work for politics (e.g. Gallup)?

6 votes

What is the impact of doubling a sample size on a p-value

6 votes

Building a model to help me determine parameters of a physical water filter?

6 votes

How big is a representative sample of the EU?

5 votes
Accepted

Any interesting stats from hand washing data?

5 votes

Do Kaggle's evaluation criteria make sense?

5 votes
Accepted

Positive coefficients in regression analysis

5 votes
Accepted

From where term $\left(\frac{1}{n}+\frac{1}{m}\right)$ came in estimated variance of $\bar x - \bar y$

4 votes
Accepted

How to get continuous output with Convolutional network? (Keras)

4 votes

When does one use $\frac{1}{\sqrt{n}}$ and when does one use $1.96\sqrt{\frac{p(1-p)}{n}}$?

4 votes
Accepted

Calculating medians and quartiles of arbitrary probability density functions

4 votes

The normality assumption of t distribution

3 votes

Question on sum and function of chi-square distributed random variable

3 votes
Accepted

Sample Size proportion per control vs. experiment group

3 votes

How to validate experimental data using statistics?

3 votes
Accepted

sum of chi-square and normal distributed variables

3 votes
Accepted

In linear regression, why is the T-value the same whether or not I standardize the dependent and independent variables?

3 votes
Accepted

In distribution tests, why do we assume that any distribution is true unless proven otherwise?

3 votes
Accepted

Is adjusted R squared score still appropriate when number of regressors is larger than the sample size?

3 votes
Accepted

z score for binomial distribution

3 votes
Accepted

The form of the distribution of a test statistic

3 votes

Given the universal approximation theorem, why are LSTM better than feed forward neural networks at certain tasks?

2 votes

Uninformative (flat) Prior density for non-linear functions

2 votes

Is it wrong to choose features based on p-value?

2 votes
Accepted

Is a Z-Test, the right test to compare the mean of several sub groups to a control mean?