All Questions

0
votes
0answers
2 views

Can the probability of a hypothesis be tested by contrasting posterior predictions against simulated data?

I have a query regarding contrasts of posterior predictions. I have generated three sets of predictions from a model using data from animal orientation experiments. The data were modelled according to ...
0
votes
0answers
4 views

Placebo Tests in Stata (synthetic control method)

I am beginner in Stata and any help would be appreciated. I am trying to work with the stata placebo command provided in the 'help synth' page and then visualize it as done by Abadie and others. The ...
-2
votes
0answers
7 views

Please kindly analyse my data by fitting ARIMA Model for my theses

MONT 2010 2011 2012 2013 2014 Jan 8340 7124 6431 5231 4069 Feb 8566 9121 5629 6119 4505 Mar 6560 6214 6354 6235 6165 Apr 8212 7458 6614 5178 ...
0
votes
0answers
6 views
0
votes
0answers
5 views

How is the model uncertainty calculated?

I have an LSTM model and I want to compute the uncertainty of my model. What formulas for uncertainty can I use? If there is an implementation in python, that'd be great.
0
votes
0answers
4 views

Python: Compute Bootstrap Confidence Intervals for a Kernel Density Estimator

I have plotted the probability density function of some data, using a Kernel Density Estimator. Both the data, and the code I am using can be found here I want to plot the confidence interval of ...
0
votes
0answers
5 views

Cost Function increasing in Multi-classification Neural Network

I am trying to build a Multi-classification neural network from scratch to learn the Fashion-MNIST dataset, which I got from Kaggle. Here is a link to the dataset. Here is a link to my code. I have ...
0
votes
0answers
6 views

how to statisticaly test data collection methods

I have 2 dataset collected with different data collection methods (very large datasets). I use the same classification algorithm on both dataset and get a greatly improved result for one compare to ...
0
votes
0answers
9 views

How to prove the estimator is consistent when there's a multiple regression without intercept?

yi=B1*x1i+B2*x2i+ui I've tried many ways to prove B1 is consistent when we know x2i is observable and is uncorrelated with x1i.
0
votes
1answer
11 views

Year of intervention seems a better predictor than type of intervention (which is dependent on the year itself)

We have a small(n = 19) non-randomized pilot clinical study in which we compare two types of surgical procedures on various outcomes. The choice of which procedure was to be performed depended ...
0
votes
0answers
9 views

Dependence between bernoulli random variables

Suppose I have $X$ such that $P(X=1)=\pi$ and $P(X=0)=1-\pi = q$, and $Y$ such that $$P(Y=1|X=1) = 1-q(1-\rho)$$ $$ P(Y=0 | X=0) = 1-\pi(1-\rho),$$ then I can simulate $X,Y$ such that their ...
2
votes
1answer
10 views

Zero-inflated model predicting only a small range of values. I need help

I built a ZI model and it is producing predicted values that are from a very small range when compared to the observed values. Plus it does not produce any zeros. See the fitted vs. observed graph ...
1
vote
0answers
12 views

Kolmogorov-Smirnov Critical Values

I'm conducting some research where I need the critical values of the one-sample Kolmogorov-Smirnov distribution. I've found a number of tables online, but the answers from these tables seem too high. ...
0
votes
0answers
14 views

The difference between means in t-test

When the sample size is large, the results tend to be statistically significant even when there is a small difference between the means of two groups. however, sometimes we see the results are not ...
0
votes
0answers
6 views

np chart: Number of defectives

To control the number of low-fat (defective) oil cans, an $np$ control chart is used, $CL=3$, control limits distant at ± three standard deviations from the center line and $n=150$. How at least ...
1
vote
1answer
122 views

How to write diff() mathematically?

I am using R/Python diff() operation. e.g., https://docs.scipy.org/doc/numpy-1.14.0/reference/generated/numpy.diff.html I would like to know if there is a ...
0
votes
0answers
16 views

Box-Cox Transformation does not normalize data sufficiently sometimes

initially as far as I have dug up on internet and books I have seen that Box-Cox transformation may not normalize data as we wish. Besides, log-likelihood function is maximised with $\lambda$ variable ...
0
votes
0answers
5 views

Text generation: Word embedding (vector) prediction instead of softmax probabilities?

0 I'm looking into a project that generates text using LSTM. The common approach to this is having the network output a distribution which you use softmax on to get the most probable word. This ...
1
vote
1answer
5 views

Survival Analysis - Truncating follow-up period when there are no events after a certain amount of time

Lets say patients in a trial were followed for over 10 years, but there are no events in either treatment or control group after 5 years (the survival curves are flattened after about 5 years). When ...
4
votes
1answer
26 views

Approximate the critical region such that the size of the test tends to $\alpha$

Consider this question, Suppose $X_1, X_2, . . . , X_n$ is a random sample from an exponential distribution with mean $\lambda$. Assume that the observed data is available on $[X_1], . . . , [X_n]$,...
0
votes
0answers
2 views

REPEATED MEASURES DESIGN

I am not sure how the results of this study should be analysed given its design. I have searched everywhere for this info on this TYPE of experimental design and have had no luck. I don't even know ...
0
votes
1answer
8 views

Interpreting Results of Time Series Decomposition

Suppose, after ACF and PCF investigation, I see my data has strong seasonality. I do both additive and multiplicative time series decomposition, just to check it results. I am not interested in ...
0
votes
1answer
15 views

p-value definition and inadequacy of tail events

Wikipedia defines p-values as (The probability of obtaining a test statistic) equal to or more extreme than what was actually observed For starters, usage of extreme there is subjective. To make ...
0
votes
0answers
4 views

OpenBugs / R How to set up forecast/predictions for separate explanatory variables [on hold]

I have a GLM in OpenBugs with a Poisson distribution, I've run the model and had convergence on six explanatory variables. What I'd like to do is for each of these variables, make a plot for the ...
0
votes
0answers
4 views

Saddle-free Newton method for SGD - while Newton attracts saddles, is it worth to actively replel them?

While 2nd order methods have many advantages, e.g. natural gradient (e.g. in L-BFGS) attracts to close zero gradient point, which is usually saddle. Other try to pretend that our very non-convex ...
1
vote
2answers
9 views

Matching covariate selection- should we not match on binary features where overwhelming majority of subjects fall in one category?

I am trying to investigate if there is a relation between Occupational Therapy (OT) dosage for stroke patients and patient recovery. I have separated the patients into 2 groups by the amount of ...
0
votes
0answers
20 views

What is the slowest day at Six Flags? [on hold]

Where could I find a chart or almanac on ticket sales for Six Flags over Georgia to go with the family on line less days?
0
votes
0answers
2 views

Pointwise Mutual Information using spacy or just detailed explaination

So, I have been trying to play around with NLP recently and decided to work on a project involving Emotional Analysis. I have been following this particular research, http://www.cse.yorku.ca/~aan/...
0
votes
0answers
5 views

Spectral density of (what looks like an) AR(1) but with a (not necessarily white noise) term

Suppose $X_t$ is a stationary mean-zero time series with spectral density $f_X(\omega)$. Note: $X_t$ is not necessarily a white noise. Find the spectral density of $Y_t$ where $Y_t = aY_{t-1} + X_t$ ...
2
votes
0answers
10 views

Before using CV-selected Regression model for Inference, shouldn't model performance be evaluated on unused test set?

I just came across a biokinesiology paper that used some Machine Learning methods, but I think there is a flaw in their methodology. The authors had data on stroke patients and used Lasso regression ...
0
votes
0answers
6 views

Books for Pricing Analytics

I'm looking for recommendations of books about Pricing Analytics (non- life insurance and using R or Python, if possible). I want the big picture, from scratch I appreciate your help.
1
vote
1answer
9 views

credible interval in bayes are higher than the nominal level

When I fitted the nonlinear regression using the openbugs, and calculated the 95% credible interval of the coefficient through the high density interval, I found that the total number of the credible ...
0
votes
1answer
12 views

What type of regression for two groups of data?

I have data from 500 school children who took a test. 250 of the children have a certain type of disability (group A). Each child in group A was matched to a child on the basis of age, gender to a ...
0
votes
0answers
4 views

How to add column in a table without taking table offline [on hold]

How to add column in a table without taking table offline. I was asked this in an interview and didn't have an answer. Can you help.
0
votes
0answers
9 views

How would you see a trend a sales in years even there are fluctuations? [on hold]

How would you see a trend a sales in years even there are fluctuations? Please provide answer with details.
1
vote
0answers
17 views

How can we call likelihood function a joint PDF when the individual terms do not represent Probabilty

My understanding of the Probabilty Density Function is that they evaluate to 0 at a particular point . So if we have some i.i.d points $x_{n}$ from a Normal distribution and we write : \begin{equation}...
0
votes
0answers
12 views

Logistic Regression: How to Detect Complete AND Quasi-Separation of Data Points

I have written a logistic regression routine using the Newton-Ralphson algorithm in VBA for use in a class that I teach which uses primarily EXCEL. I want the algorithm to test for complete and quasi-...
0
votes
0answers
12 views

Combining 3 Tables with a Twist

Let's say I have three tables: patients, samples, and mutations. The patients table has unique rows, each with a unique patient_id. The samples table has unique rows, each with a unique sample_id, ...
0
votes
0answers
10 views

how to run a generalized linear mixed model (GLMM) with multiple random factors in R?

I would like to run a GLMM with multiple random factors using the function glmer in package lme4. I have a dataset on marine debris like this: count density: numeric year: categorical, two levels ...
0
votes
0answers
13 views

Univariate Time Series Ramp Detection

Given a univariate time series, what are common / best practice ways to detect "ramp up" or "ramp down" in a time series over an extended period of time? For example, given a daily time series of an ...
0
votes
0answers
15 views

Minimal Sufficiency for Two Parameters

Let $X_1, ..., X_n$ be iid $f(x; \theta, \lambda) = \dfrac{\lambda e^{-\lambda x}}{1-e^{-\lambda \theta}}$ for x $\in [0, \theta]$. I am asked to find I want to find A minimally sufficient ...
0
votes
0answers
6 views

Group comparison for bivariate/multi-variate distributions

For two groups A and B that consist of n and m individual samples. Each individual sample has a unique i-dimensional probability density functions (PDFs). I had the following questions: How can one ...
1
vote
1answer
128 views

what is the log of the PDF for a Normal Distribution?

I am learning Maximum Likelihood Estimation. per this post, the log of the PDF for a Normal Distribution looks like this. let's call this equation1. according to ...
0
votes
0answers
14 views

After log transforming my data to have equal variances for ANOVA, do I use the new p-values of the transformed data?

When running one-way ANOVA I did not have equal variances, so I log transformed the data and reran ANOVA with equal variances. Do I use these new p-values from Tukey's post-test on my graph showing ...
0
votes
1answer
27 views

Rao-Blackwellize Bernoulli

Let $X_1, .. X_n$ be iid Bernoulli($\theta$). I want to estimate $\lambda = \theta(1-\theta)$, usin $\delta$ (unbiased estimator for $\lambda$) where $\begin{cases} \delta = 1 & X_1 =1 \...
0
votes
0answers
20 views

Meaning of “was produced by the null hypothesis”

There was a question about p value interpretation and one of the comments made me wonder whether there is some basic misunderstanding I have about p values. I wrote "you can discard the null ...
-1
votes
0answers
20 views

why scikit-learn is so disgustingly overfitting? [on hold]

I bumped into a problem that dazzles me very much, I can't believe it's actually happening. I trained an elastic net using last version of scikit-learn function ElasticNetCV and a 4 folds CV repeated ...
-1
votes
1answer
30 views

Probability Integral Transformation Inverse of CDF [on hold]

For PDF and CDF f(x) = 1- 0.5 x, 0 Find the inverse F^-1(x) given uniform distribution over (0, 2) Use your answer to plot histogram on STATA Yes. Draw a random sample of 123 people and plot a ...
0
votes
0answers
8 views

Sufficient Condition Stationarity AR(2) process

Given the following AR(2) process: $y_{t} = \phi_{1}y_{t-1} + \phi_{2}y_{t-2} + u_{t}$ I need to prove that the sufficient condition for this process to be stationary is $\phi_{1} + \phi_{2} < 1$....
1
vote
2answers
51 views

Prove that $\frac{1}{n(n-1)}\sum_{i=1}^{n}(X_{i} - \overline{X})^{2}$ is an unbiased estimate of $\text{Var}(\overline{X})$

If $X_{1},X_{2},\ldots,X_{n}$ are independent random variables with common mean $\mu$ and variances $\sigma^{2}_{1},\sigma^{2}_{2},\ldots,\sigma^{2}_{n}$. Prove that \begin{align*} \frac{1}{n(n-1)}\...

15 30 50 per page