All Questions

17 views

Is there a name for this simple probability relation? [duplicate]

Namely: $\quad \frac{P(A \cap B)}{P(A) P(B)}$ Cleary this is 1 if A and B are independent, and I think it would be 1/2 if A = B. So it seems like this is some measurement of dependence. Is it ...
17 views

Terminology: Varying $p$ or “probability” when sampling randomly from a distribution? [on hold]

Does it have a name, if one varies the $p$ or "probability" when sampling randomly from a distribution to meet some requirements set for the random variables that utilise the values drawn from that ...
10 views

Constructing a problem-specific loss function

Problem Description I'm beginning network construction for a problem that I feel could have a far more insightful loss function than a simple MSE regression. My problem deals with multi-category ...
13 views

How to implement a linear and a logistic regression in a single SEM model using R? [on hold]

I created a SEM model in R (lavaan package), but one of my dependent variables is continuous, while the other is binary. The model is as follows: ...
4 views

Identifying Changepoints in Learning Data

I have a "changepoint" problem that I do not understand. The data for my MWE comes from one human player as s/he played the same video game for 31 one-hour sessions (no more than one session per ...
11 views

How to bin correlated data?

Let's say I have 100 data points $\bf{x}$ with covariance matrix $\mathbf{C}$ where non-diagonal elements are non-zero. Now I have a binning operator $\mathbf{P}$ of dimension 10$\times$100, that ...
6 views

scikit-learn ExtraTreesClassifier - Why is the pickle file so huge? [on hold]

Using python + scikit-learn, I fit an "Extremely Randomized Trees" classifier (ExtraTreesClassifier) to a ~ 900K sample array of 100 features. I then tried to pickle it. I instantiated the ...
19 views

Best effect size statistic for ordered categories

I have ordered categories, and a prediction for the size of the categories. If the categories were unordered, I would use Cramer's V as a measure of the effect size. [Feel free to give an opinion on ...
3 views

Missing Argument m in addModule

I'm very new to python and pybrain and i'm trying to get through the tutorial at http://pybrain.org/docs/tutorial/netmodcon.html. I'm stuck almost at the beggining where i have to add module to my ...
17 views

Problem with producing valid forecasts

I have a weird problems with producing good forecasts with R and the forecast package. The data I use can be found here: http://pastebin.com/2gwyVYrj Sample code I used: ...
9 views

Central Limit Theorem- observations vs samples [duplicate]

I'm confused with the concept of central limit theorem and I need some clarification about it, hope you guys can help! Now suppose there is a population in form of numbered balls contained in a box. ...
16 views

Cluster Analysis with correlated variables

I want to perform cluster analysis. I have 10 variables, and 350 observations. I noticed that a lot of variables are correlated. I have two pairs with over 0.9 correlation, and a few others with ...
33 views

Better accuracy with validation set than test set

I trained a model with some algorithms like random forest, logistic regression and so on. My dataset was split into 80% CV train data (so actually 60% of data to train the model and 20 % for testing ...
9 views

Can the mean of ordinal variables correlated between them be interpreted as continuous?

This is probably obvious to most of you but I need to analyse data where a variable is the outcome of a factorial analysis (mean of 5 ordinal variables on a likert scale), more precisely im looking at ...
36 views

What is the effect of taking the mean of a moments-based estimate?

Suppose I estimate the second and fourth moments of a signal as $M_2 \approx \frac{1}{N} \sum_{n=0}^{N-1} | y_n |^2$ and $M_4 \approx \frac{1}{N} \sum_{n=0}^{N-1} | y_n |^4$ and then I use these ...
14 views

error rates of knn minimal for k=1

I am trying to find the best parameter $k$ for a nearest neighbour classifier using cross validation for some datasets. After computing and plotting the error rates, I noticed some strange behaviour ...
17 views

Link between stationarity of AR(2) and stability condition of corresponding difference equation

In the standard textbooks, such as Hamilton (1994), it is stated that the conditions for stationarity of a process $y_t = \theta_0 + \theta_1 y_{t-1} + \theta_1 y_{t-2} + \epsilon_t$ follow from the ...
13 views

Is it valid to use the full dataset to determine important variables and a partial datasets for training a classification algorithm?

Given a dataset with n variables and a binary outcome: Are there assumption violations/risks to drawing conclusions if the entire dataset is used to determine which variables are valid if the second ...
10 views

NA values for coefficients in Cox proportional hazards model

I'm doing a cox regression analysis. My model is given by ...
10 views

Compute partition function

I'm given a distribution on 3 discrete variables $x, y, z$ which is defined as $$p(x, y, z) = \frac{1}{Z} \psi(x, y, z) = \frac{1}{Z} \phi_1(x, y) \phi_2(y, z)$$ where $x, y$ can take up value among ...
49 views

Probability Homework question regarding 3 friends' salary [on hold]

After graduation, three friends start their first jobs. The monthly earnings of friend 1 have a normal distribution with mean $15,000$ and standard deviation ...
13 views

Interpretation of posterior probabilities in Bayesian Network with BNfinder

I'm currently using a python library BNfinder http://bioputer.mimuw.edu.pl/software/bnf/bnfinder_doc.pdf where author on page 10 describes the output of posterior probabilities of the interaction ...
24 views

control variables in panel data regression with Stata [on hold]

I am currently trying to run a regression with panel data in Stata but I have difficulty to consider control variables. Is there a way how I can consider control/mediator variables in my panel ...
15 views

What are all options of graphical user interface for analysis in R? [on hold]

I've created a classifier on my data set using R software by using some libraries. I want to make a GUI for my code so that the ...
4 views

Issue with weights in R CHAID decision tree [on hold]

I am new to R and as well as stats world. For my problem, I am using CHAID in R to process my dataset and arrive at a decision tree. I am trying to assign weights to each of the dependent variables ...
50 views

Why is using centered or uncentered data equivalent in ridge regression?

Why is using centered or uncentered data equivalent in ridge regression? In other words, given two ridge regression problems: (b',c')=\operatorname*{argmin}_{b,c}\Big[ { \sum_i^{m} ...
8 views

How to design this ANOVA formula in R?

I have data with four variables: Treatment (yes/no) Gender (M/F) Ethnicity (Black, White, Latino) Test Score (integer value in set range) I want to know if a treated Black Male had a higher test ...
9 views

Correct Hypothesis Test

Experiment: At selected intersections an intervention (advertisement) is applied on random days for a 4 week period, the intervention was applied exactly half of the time. Data collected centers on ...
19 views

Intuitive understanding of this sentence with regards to time series

I am reading the lecture note here by Simon Gilchrist on equity premium puzzle. The risk free rate is not very volatile: σ(R) = 2% per year but is persistent (ρ = 0.6 in annual data) leading to ...
40 views

MLE - Why assume that there is a true parameter value?

In parameter estimation, we assume that the observed data $D$ is sampled from a distribution $f_{\theta_0} \in \{f_{\theta} | \theta \in \Theta\}$, where $\theta_0$ is the true, unobserved parameter ...
15 views

Calculating risk ratio using odds ratio from logistic regression coefficient

I have a binary logistic regression with just one binary fixed factor predictor. The reason I don't do it as a Chi square or Fisher's exact test is that I also have a number of random factors (there ...
6 views

Time course Normalization

I am trying to understand functional connectivity using fMRI data. Can someone explain time course normalization and about its usefulness in general?
14 views

Right-censored independent variable in Cox/logistic regression

I have a right-censored continuous independent variable that I want to include in a Cox regression. The variable is a physiologic test which is capped at a certain time, say 120 seconds, due to safety ...
18 views

Multiple Linear Regression: results in training and testing data not correponding to run data

I have 3 data sets each with 1 column of Y data and 20 columns of X predictor variables. Training data which is 2200 rows. Testing data with 550 rows. Run data with 550 rows. I am using linear ...
11 views

Fine-tuning model parameters in an systematic/optimised fashion

Tuning parameters in R isn't a new topic. I am embarking on some modelling of a large data set, with the goal to create a predictive model using R, selecting predictors analytically from an ...
17 views

How do i implement a zero inflated poisson inverse gaussian generalized linear model

Having spent a little time in solving these problem. it seems am getting nowhere yet. These are what i found out -the gamlss results is quite different from the zeroinfl function in pscl of R ...
11 views

Approximate estimation of a covariance involving ratios

I have three random variables (T, O, A) that are each approximately normal. These three random variables are combined to form two ratios: X=T/A and Y=O/A. I wish to get an estimate of the covariance ...
19 views

Why do the authors subtract the median in this measure for adjusted average app rating?

I'm just reading the paper "Is this App Safe? A Large Scale Study on Application Permissions and Risk Signals" by Chia et al. (available here from ntnu.no). On page 3, they calculate an interesting ...
29 views

How well does my model fit the data?

I have 3 measurements, and I want to know if there is a correlation between x and y. I use this model to my data, but how can I check if this model is good? If my understanding is correct, it is ...
34 views

Why are we using ICA? [duplicate]

I am new to Independent Component Analysis (ICA) and have a rudimentary understanding of the method. I understand that PCA finds vectors on which the projected data has maximum variance. ICA, on ...
19 views

How I can train data in Matlab? [on hold]

I have a given data, on that basis I wan't to make Markov chain model of norm profile by training given data which is depends on probability equations so how I can do this with Matlab.
321 views

How to understand the drawbacks of Hierarchical Clustering?

Can someone explain the pros and cons of Hierarchical Clustering? Does Hierarchical Clustering have the same drawbacks as K means? What are the advantages of Hierarchical Clustering over K means? ...
137 views

What is the difference between Maximum Likelihood Estimation & Gradient Descent?

What are the pro & cons of both the methods? When should we prefer MLE over GD & vice versa? Does GD work better when building predictive model on Bigdata?
29 views

What is the intuition & math behind Maximum Likelihood Estimation? [duplicate]

We use logistic regression all the time but very few people can actually explain the intuition & math behind Maximum Likelihood Estimation, which is the method used to identify the best ...
9 views

Dispersion parameter in GAM output

I have a question about Negative Binomial distribution. I’m modeling a count data, as following example: ...
8 views

cross section dependency test and random effect variable in Eviews8

How can I conduct a pandel data cross section dependency test in a random effect variable by using Eviews 8. Please Show me a way. Thank you
9 views

Exact test for m x n contingency table conditional (i.e. fixed by design) on one margin

I have a $m \times n$ contingency table (with $m, n > 2)$ . The experiment yields ~15% cells with expected frequencies lower 5 and also zero counts in the empirical data. The prerequisite for the ...
14 views

PCA on kinship matrix

I have a dataset made up of twins. I have computed the kinship matrix using SNP data we have on the invidivuals. I was interested to know if PC1-PC3 would capture the relationships fully. I.e. if I ...
3 views

normality tests of residuals in repeated measures design

I have a repeated measures design where I have plotted the residuals and the majority of my data are not normally distributed. As I understand it, repeated measures designs are quite robust when using ...
6 views

How do I divide the visreg plot in r statistics one more time with the “by” AND “breaks”-argument? [migrated]

I'm using the "visreg"-package in "R" and I want to split up my plot again, but one more time than the package "allows" me: So this is how my plot looks like: with the R-code: ...

15 30 50 per page