Cross Validated Community Digest

Top new questions this week:

Does machine learning really need data-efficient algorithms?

Deep learning methods are often said to be very data-inefficient, requiring 100-1000 examples per class, where a human needs 1-2 to reach comparable classification accuracy. However, modern datasets ...

machine-learning neural-networks sample-size small-sample efficiency  
asked by bobcat 20 votes
answered by Björn 30 votes

In Bayesian statistics, data is considered nonrandom but can have a probability or be conditioned on. How?

In Bayesian statistics, parameters are said to be random variables while data are said to be nonrandom. Yet if we look at the Bayesian updating formula $$ p(\theta|y)=\frac{p(\theta)p(y|\theta)}{p(y)},...

probability bayesian random-variable likelihood  
asked by Richard Hardy 18 votes
answered by Xi'an 22 votes

How to make predictions with non-parametric regression?

Let's say I have a dataset to which I have estimated a relationship using non-parametric regression, specifically Kernel (obviously in this hypothetical example it's probably overfit slightly). The ...

regression cross-validation predictive-models nonparametric nonlinear-regression  
asked by TheFriendlyAsker 11 votes
answered by Tim 14 votes

Why is AIC not reported with a confidence interval?

In parameter estimation, it's common to report a 95% CI around each parameter. Why don't I see AIC (or deltaAIC) with a CI? If I bootstrap the fitting of two potential models, and get a deltaAIC for ...

confidence-interval aic  
asked by sharoz 10 votes
answered by Lewian 17 votes

Are all log-likelihood functions twice differentiable?

For maximum likelihood estimation we need to set the first derivative of the log-likelihood function equal to $\mathbf{0}$. The negative expected value of the Hessian matrix (second derivative) is ...

distributions density-function likelihood fisher-information  
asked by stollenm 6 votes
answered by jcken 10 votes

How to interpret Pearl's do notation?

I'm going through the Dragonnet paper (slides available here), and the authors use Pearl's do notation to make this claim: How can I interpret the do notation? Is the author claiming that the average ...

inference causality notation confounding  
asked by foglerit 6 votes
answered by Adrian Keister 8 votes

Underestimation of standard error

The formula to calculate standard error (aka standard deviation of the sample mean) is $\sigma_{\bar{x}} = \frac{ \sigma} {\sqrt{n}}$. But we generally don't know the population standard deviation $\...

probability mathematical-statistics standard-deviation standard-error  
asked by Taotao Tan 6 votes
answered by Thomas Lumley 10 votes

Greatest hits from previous weeks:

What is the difference between normal distribution and standard normal distribution?

Two terms normal distribution and standard normal distribution are used in statistics. Does standard term contribute to the normal distribution anything? Please give a simple-however a substantive ...

normal-distribution  
asked by Subhash C. Davar 3 votes
answered by Michael R. Chernick 10 votes

How to check for normal distribution using Excel for performing a t-test?

I want to know how to check a data set for normality in Excel, just to verify that the requirements for using a t-test are being met. For the right tail, is it appropriate to just calculate a mean ...

normal-distribution excel  
asked by Eudora 21 votes
answered by whuber 15 votes

How to interpret a QQ plot

I am working with a small dataset (21 observations) and have the following normal QQ plot in R: Seeing that the plot does not support normality, what could I infer about the underlying distribution? ...

r data-visualization inference qq-plot  
asked by JohnK 205 votes
answered by Glen_b 356 votes

What is the difference between pooled cross sectional data and panel data?

They seem so similar. Are they the same thing but just referred to as different names?

regression dataset econometrics  
asked by Kyle 23 votes
answered by Corey Sparks 18 votes

How to calculate quartiles with only standard deviation and mean assuming normal distribution?

I am trying to understand how, using only the standard deviation and mean, you are able to determine the first and third quartiles on a normal distribution. I get that the area under the curve equals ...

software quantiles  
asked by Moses 5 votes
answered by ttnphns 3 votes

What is the difference between a population and a sample?

What is the difference between a population and a sample? What common variables and statistics are used for each one, and how do those relate to each other?

standard-deviation variance sample population  
asked by Baltimark 42 votes
answered by Graham Cookson 39 votes

What does 1x1 convolution mean in a neural network?

I am currently doing the Udacity Deep Learning Tutorial. In Lesson 3, they talk about a 1x1 convolution. This 1x1 convolution is used in Google Inception Module. I'm having trouble understanding what ...

neural-networks deep-learning convolution conv-neural-network  
asked by jkschin 162 votes
answered by Indie AI 159 votes

Can you answer these questions?

Can I compare two sets of data to find the probability of one set of data being higher?

If I have two sets of data, find the probability that one set of data will have a higher value i.e. for sets A and B: if you took one random variable from each set, one is more likely to be greater ...

probability distributions  
asked by Seamus 1 vote

Deriving confidence intervals for a single probability from the sum of two probabilities and the other probability

Suppose we have three categories with $p_1+p_2+p_3=1$. And suppose we have already derived these two (say 95%) symmetric confidence intervals: $$ p_1 \in\ (L_1, U_1),\quad p_1 + p_2 \in\ (L_2,U_2). $$ ...

probability confidence-interval  
asked by Floyd Everest 1 vote

How to add dependency within the outcomes between records in a simulation

For simplicity, consider a Generalized linear model (GLM) for the losses reported to an insurance company for damage to a building. A standard GLM assumes the randomness of the outcomes to be ...

generalized-linear-model simulation non-independent  
asked by John E. 1 vote
You're receiving this message because you subscribed to the Cross Validated community digest.
Unsubscribe from this community digest       Edit email settings       Leave feedback       Privacy
Stack Overflow

Stack Overflow, 110 William Street, 28th floor, New York, NY 10038

<3