0
votes
0answers
5 views

How can I smooth a set of distributions?

I have a set of results from MCMC modelling of a variable at discrete time points and I would like to know what kind of approaches I could take to smooth the results, given I would expect some kind of ...
0
votes
0answers
8 views

Identifying proportions in a mixture model using maximum likelihood

I am estimating a finite mixture model with 4 types using discrete choice data. Each type has a number of parameters that defines how that type makes decisions. Along with these parameters I am ...
0
votes
1answer
10 views

Running Ridge/Lasso regression with glmnet - Intercept shows up twice in the output. Have I done anything wrong?

I'm working my way through the ISLR book and I just finished exercise 9c/d in Chapter 6. For some reason the output I end up getting is showing the intercept twice, with no coefficient for one of the ...
2
votes
0answers
10 views

Non-parametric counterpart to the z-statistic?

I have a large sample ($N \approx 1.5\times 10^6$) of observations from a high-dimensional ($d \approx 400)$ "feature space". If one views these individual observations as rows in a table, the $d$ ...
-1
votes
0answers
12 views

Probability Distribution [on hold]

In a recent survey,80% of the community favored building a police substationin the neighborhood. If 15 citizens are chosen,what is the standard deviation of the number favoring the substation?
0
votes
0answers
4 views

How do you compare RMSE after logging the y (the dependant variable)?

In my intro stat class, I'm told that it is difficult to compare RMSE after logging the y. However, after checking the sktest, the data appears to not be normal. So, in order to normalize the y ...
4
votes
0answers
14 views

How should the individual researcher think about the False Discovery Rate?

I've been trying to wrap my head around how the False Discovery Rate (FDR) should inform the conclusions of the individual researcher. For example, if your study is underpowered, should you discount ...
0
votes
0answers
6 views

Intepreting p values from R mediate() output

In the output below, the ACME p value shows that it is significant. But the p-value for Prop. Mediated Average is >10%. I thought Prop. Mediate is the proportion of the total effect mediated by the ...
0
votes
0answers
3 views

Using variables obtained after response in regression

What are the pros and cons of using a variable that is obtained after the response variable in a regression analysis? Is this valid? For example, in a dataset for students in a class. The response ...
0
votes
0answers
6 views

clustering datapoints with chinese restaurant process

If I have data points (scalar) and want to incorporate each data points characteristics into how its being clustered, is there a way of doing it? I assume the standard generative process of CRP is not ...
0
votes
1answer
11 views

Interpreting kmeans output

I am working on a clustering model with the kmeans() function in the package stats and I have a question about the output. My data is a sample from several tech companies and AAPL._UP is a variable ...
0
votes
0answers
7 views

What are the restrictions on the correlation matrix of a continuous-by-categorical interaction?

Let $x$ be a continuous random variable and $c$ be categorical with $K$ categories. Expand $c$ to $c_1,\dots,c_K$ with dummy coding, and compute the correlation matrix $R$ of $c_1x, \dots, c_Kx$. ...
-1
votes
0answers
15 views

Drawing random card from given set of cards

Let's assume I have set of A decks. I was drawing random cards from it and I'm left with incomplete set. I have methods to count how many [1 to 9] or faces are there, and how many cards are left in ...
0
votes
1answer
16 views

Which statistical analysis test can I use when the instances in the sample is not independent?

I am wondering if the data I have here is eligible to do statistical analysis. The problem is: I collected data from 20 person with age less than 20 (Group A), from 21 person with age large than 30 ...
0
votes
0answers
10 views

VECM model output - where is the long run relationship?

So I'm getting the following EViews output, but where on earth is the long run relationship? Do I have to estimate it separately using OLS? If you have to estimate it yourself via OLS, I've already ...
0
votes
0answers
9 views

F-Statistic: Levene's Test vs. Two-Sample

I'm trying to get my head around the calculation of the critical F-Statistic for testing the equality of variances using two different tests. I have 2 groups (n=12) and (m=11). Trying to do a two ...
1
vote
1answer
17 views

How to sample from a non-parametric density estimate?

I have a kernel based non-parametric distribution, let's assume it's a Normal kernel, but the variance of each component is different. How do I sample from this density? If all the components had the ...
0
votes
0answers
15 views

Please help me to do regression with stable distribution with R

I am literally new to R. Is there anyone to make a code to carry out simple AR(1) regression with error terms according on stable distribution? Say $$y(t) = c + by(t-1) + e$$ where $e$ ~ stable ...
0
votes
1answer
8 views

Lagrange Multiplier for clustering with size constrains

I'm trying to solve a clustering problem with size constrains. Minimize $J=\sum_{i=1}^c\sum_{j=1}^n {{u_i}_j}^2{d_i}_j$ Subject to $\forall 1\le j\le n : \sum_{i=1}^c {{u_i}_j}=1$ and ...
1
vote
1answer
25 views

How to choose the observation with the median value when there are an even number of observations?

Obviously, in most circumstances, you would just take the mean of the two middle values. However, imagine a dataset of 100 countries. You want to know which country has the median household income. ...
0
votes
0answers
4 views

Screening/Filter Method for classification problem

I have a data set with 100 variables. And the output is binary (case/control). What kind of method would be a good choice for screening variables at the beginning stage.
1
vote
1answer
16 views

The results and specifics from the 'qs' function in R

I'm not entirely familiar with the results of the qs() function in R's package seasonal. But, by what I understand roughly, the ...
1
vote
0answers
8 views

Two separate or a single mixed-effects model?

Lets say my data is exam results of students nested in schools and there are two kinds of schools: private and public ones. Now, what I am interested is the variance between private and public ...
0
votes
0answers
8 views

Comparing Means: Multiple Dependent Variables

I am using school-level data to compare mean scores for two groups (Group A schools and Group B schools), as measured by a series of indicators: 1) grade-level exam percentile, 2) percent of male ...
0
votes
0answers
6 views

NAs returned when applying r.squaredGLMM [on hold]

I wish to calculate conditional and marginal R2 values for a linear mixed model. However, R keeps returning 'NAs' for each (no warning message). I have tried a number of model variations and the same ...
1
vote
1answer
23 views

How can I avoid misidentification of a exponential distribution as Gamma or Weibull?

I'm trying to write a piece of code in R that identifies a set of sample data as belonging to a specific distribution and pull the specific distribution parameters, by performing the K-S test and ...
0
votes
1answer
23 views

Testing Hypothesis

I have a sample of 40 data, that shows the average of time a person waits in a gas station line. Descriptive statistics of this sample are as follow: N= 40, mean= 115sec, std.dev.=11sec, min=90sec, ...
1
vote
2answers
14 views

How is the chance-level confusion matrix calculated?

I applied an ML technique on my dataset, and got this confusion matrix: 0 1 0 162 62 1 27 50 Funnily, the overall accuracy is worse than ...
0
votes
1answer
7 views

Is there a distance algorithm similar to Jaccard distance that handles scalar data?

we have the characteristics and (scalar) values of those characteristics for three (or more) people: ...
5
votes
4answers
112 views

How can you visualize the relationship between 3 categorical variables?

I have a dataset with three categorical variables and I want to visualize the relationship between all three in one graph. Any ideas? Currently I am using the following three graphs: Each graph is ...
0
votes
0answers
31 views

How to indicate a 95% confidence interval for the total amount to be paid.

Can you please help me to solve this question! Peter who is soon to be married, has for a long time been thinking about the perfect morning gift for his bride, Kate. As the couple is going to run a ...
0
votes
0answers
10 views

Similarity of linear subgraphs

I have a directed graph, on which I have a number of linear subgraphs. In the simple example graph below, these subgraph might be a->b->c->e->g->h, ...
0
votes
0answers
10 views

Including Feature Selection in Cross Validation - Application to Bag of Words

I am working on a prediction problem where I was given a 6,000 record dataset with the value of the dependent variable included ("train"), and a 2,000 record dataset with the same independent ...
0
votes
0answers
5 views

“constraint and column generation method” in Julia-Jump [on hold]

Anyone has any idea of how to program "constraint and column generation method" in Julia-Jump for a mixed-integer three level problem optimization. thank you very much
0
votes
0answers
6 views

Weibull regression with survreg function leads to null coefficients

I'm sorry for my English but I'm not a native speaker. I have a pretty big dataset (20k observations) with 15 covariates and 1 response. I noticed that my response seems to have a Weibull ...
0
votes
0answers
8 views

Bootstrap Step-Wise Selection For GLM in R [migrated]

What I'm trying to do is the following: Resample (bootstrap) the dataset containing my predictors and outcomes, say 1000 times For each bootstrap sample fit a glm using stepwise selection and then ...
0
votes
0answers
2 views

Bivariate Dependent Correlations Hotelling / Williams for large samples?

I have a question about how to handle large sample size bivariate dependent correlations. Currently I'm using the Hotelling / Williams test implemented in the 'Psych' package in R. So I'm testing ...
0
votes
0answers
4 views

Using interaction terms to exclude sample members who do not meet certain conditions?

I believe this might be a specific application of the non-compliance problem in experimental design and estimating treatment effects, but I could be wrong. I want to model the impact of certain ...
0
votes
0answers
6 views

F-statistics for smoothing term in GAM [on hold]

i was wondering how to report GAM F-statistics that R deliveres for smoothing term for a paper?
-1
votes
0answers
15 views

Contour of bivariate normal in r [on hold]

How to sketch constant-density contour that contain 95% of the probability, when population means are zero, variance of two variables are 2 with covariance -0.2 and correlation coefficient is -0.5.
0
votes
0answers
6 views

Estimation VS detection [on hold]

I would like to know what is the difference exactly between estimation (parametric or not) and detection in the statistic signal process. Thanks in advance and have a good day
0
votes
0answers
6 views
0
votes
0answers
7 views

Hazard Ratio Curve [on hold]

Can someone please tell me, which SAS procedure to use or any other method in SAS to draw a Hazard Ratio Curve as in the image below. Thank you.
2
votes
1answer
38 views

How to rank monthly data, using both trends and averages

I have a very large data set containing the daily searches for some Wikipedia entries. I am using the number of searches as proxy of popularity and want to rank the entries. Lets say I have entities ...
1
vote
1answer
23 views

Sample size estimation for test for proportions

I'm interested in finding out if a particular activity increases the chance of a particular segment of prospects converting to a client. I would like to be able to detect a 5% difference in overall ...
0
votes
0answers
1 view

Calculating leverage/cook's distance for a Weighted Spatial Simultaneous Autoregression Model

I am estimating a Weighted Spatial Simultaneous Autoregression Model (spdep::spautolm --> Link) in R and I would like to do some residual analysis. Unfortunately ...
3
votes
0answers
20 views

Testing if the difference between two count variables is different from zero

I have two count variables for several hundred thousand comparisons, one expected and one observed, and I would like to test if the counts are significantly different. One possible approach I have ...
1
vote
0answers
16 views

how to simulate type I error and type II error

Suppose $H_0: F_0$ and $H_1: F_1$, I want to simulate (lower bound of) the sum of type I($\alpha$) and type II($\beta$) error based on n observations. (Q:Am I posing the problem in the well-defined ...
0
votes
1answer
25 views

Time Between Treatment

Suppose a treatment (A or B) is administered multiple times. Consider the following table: ...
1
vote
1answer
26 views

What is a random variable in the definition of a linear regression model

In wikipedia's definition of a linear regression model: $y_i = \beta_1 x_{i1} + \cdots + \beta_p x_{ip} + \varepsilon_i = \mathbf{x}^{\rm T}_i\boldsymbol\beta + \varepsilon_i, \qquad i = 1, \ldots, ...

15 30 50 per page