All Questions

0
votes
0answers
17 views

Looking for a Regression Method with way to enfornce a reflection/ flip consistency for input [on hold]

I have a set of $N$ dimensional 1D features using which I build a linear a regression model to predict a single scalar value. Say, $\hat{y}(w, x) = w_0 + w_1 x_1 + ... + w_p x_p$ with the regression ...
0
votes
0answers
17 views

Delving Deep into rectifiers:surpassing human-level performance on ImageNet classificatiom

I have read this paper (Delving Deep into rectifiers:surpassing human-level performance on ImageNet classificatiom)again and again and again ,but I do not understand initialization of filter weights ...
1
vote
1answer
24 views

Does a CNN object detector always return the same results for the same image?

There're many object detectors which use convolutional neural networks to detect objects in images or point clouds, like YOLO, SSD, AVOD. My question is, if i feed the same image to an object ...
0
votes
1answer
44 views

Sort datasets by how much it's increasing [on hold]

I'm a programmer and have a task to sort datasets by how much they have increased in values. This is related to google trends. To see how much a keyword is trending. And to compare which keyword is ...
1
vote
0answers
10 views

Implications of adding extra “control” conditions to an ANOVA?

I'm planning a 2x3 ANOVA, all between subjects. I'm expecting a weak main effect for A...a main effect for B where one condition is different than the other two...and then an interaction effect where ...
0
votes
0answers
11 views

Strategies for balancing the test/train split for modeling applications?

I am about to embark on a modeling project where I want to split up my data into test and train groups. Initially I was planning on doing a random assignment of each record according to an 80:20 ...
0
votes
0answers
19 views

Test differences between rates

I ran a digital advertising test with 4 different groups of demographic. 4 different segments visited the website > goal : purchase Segment A - 1000 visitors - 10 purchases > 1,0% purchase rate ...
1
vote
0answers
19 views

ksmooth function in R

I'm trying to understand how ksmooth function in R works (I haven't really taken much statistics other than an introductory one at college, so sorry if this is a ...
0
votes
0answers
17 views

Multiple state transition probabilities in Markov model

I have a problem where, in a multi-state Markov model with monthly timesteps, I have a state X where, in an average of 1 year, individuals exit from the state in this proportion: 56% of individuals ...
-1
votes
0answers
12 views

Panel regression [on hold]

I am new to this method. The model is a fixed effects model (nor a random effects model or pooled regression). My question is about the assumptions. Does this method assume equal error variance (...
0
votes
1answer
13 views

Normalizing data before or after extracting time domain features

I have 100 time series (with 200 instances each) datasets each corresponding to a particular activity. I want to perform supervised classification for the activity. I want to use time domain (time-...
0
votes
0answers
18 views

Equivalence of two optimization problems [duplicate]

Ridge regression problem: $\sum_i^n(y_i-\beta_0-\beta_{1i}-\beta_{2i})^2 \longrightarrow min_{\beta}$ $s.t. \sum_i^p\beta_i^2 \leq c$ $\sum_i^n(y_i-\beta_0-\beta_{1i}-\beta_{2i})^2 + \lambda(\sum_i^...
2
votes
2answers
36 views

How to modify a linear regression model when the variance is not constant?

I have a very basic question. I have a model that has residuals that don't follow a constant variance pattern, but rather it has a clustered pattern (see the figure attached). Any idea of how to deal ...
-1
votes
0answers
26 views

Statistical test to measure whether certain candidates progress further in a job application process

If I have an interview process where people are phone screened, then if they pass then are moved unto another stage, and then another stage etc until they get an offer. I want to identify the ...
0
votes
1answer
29 views

Significance test with non-normal, bounded data?

I am attempting to do a one-sample significance test to determine whether a set of data differs from a given value (0 in this case). The issues I have with these data: Non-normally distributed data, ...
3
votes
2answers
41 views

Removing leading zeros from time series

Currently, I am working with a lot of time series data. A lot of my time series data have a lot of leading zeros. For example, ...
0
votes
1answer
28 views

Longitudinal Cox Regression analysis?

So I have a dataset that is currently in wide format and I have multiple waves recording data such as age, death, diagnosis etc. I have done a simple Cox regression analysis: ...
0
votes
0answers
9 views

Time to treatment and survival

I am trying to figure out how time to one event affects time to a subsequent event. For example, how time to treatment affects survival time. In my data, I am focusing on oncology and the time to ...
0
votes
1answer
28 views

Different notions of over-parameterization

While reading a paper, I came across the statement This prediction function will be parameterized by a parameter vector $\theta$ in a parameter space $\Theta$. Often, this prediction function ...
0
votes
0answers
25 views

Do I discard all my dependent variables as proved by chi-squared test of independence?

I have 134 categorical columns in my data. 7 of which are categorical variables [ one variable is highly unbalanced and has 34 classes while all other variables just has 3-5 classes in each variable ...
0
votes
1answer
17 views

How to quantify the fluctuation of an error?

First of all sorry for the bad title, but unfortunately, I can't think of a better one at the moment. Hopefully, that will change when my question is answered. Let's say I have two sets of values: ...
0
votes
0answers
27 views

Doubling variance for the distribution of sample standard deviation

Assume I'm provided with some $\sigma$ and some $N$, allowing me to formulate the distribution of sample standard deviation (as described here). But say I want to double the variance of this ...
0
votes
0answers
22 views

how to make regression model using output of factor analysis [on hold]

I have a data set on survey for measuring customer satisfaction basis 11 parameters (these are independent variables) and overall customer satisfaction as dependent variable. So a data set of a total ...
1
vote
1answer
34 views

Why do cubic splines need to be continuous at the first and second derivative, but discontinuous at the third?

I'm working through Introduction to Statistical Learning and came upon this: One can show that adding a term of the form $ \beta_4h(x,\xi)$ to the model (7.8) $$y_i = \beta_0 + \beta_1x_i + \...
0
votes
0answers
5 views

Data set for mixed distribution - bimodel

I'm doing my undergraduate thesis and I need to have a data set which is distributed as bi-model in order to complete the application part. I'm going to use non- parametric methods to estimate the ...
0
votes
0answers
11 views

Is this a sign of a bad IRT implementation?

This data is from the Indonesian UTBK SBMPTN (a university entrance exam). It is said to use Item Response Theory for scoring. I found something interesting about it. The image below shows the ...
0
votes
0answers
14 views

Power analysis, moderated mediation, SEM, R [on hold]

Using R, I am trying to estimate a sample size for the following structural equation model defined using lavaan syntax (R): ...
0
votes
0answers
5 views

Workaround for While Loop in RJAGS [on hold]

I know that while loops are not allowed in RJAGS and I am trying to figure out a work around. I am trying to co-model Counts and Durations from a sum of independent Weibull distributed variables. I ...
0
votes
0answers
25 views

Which model type for a distribution of discrete outcomes?

I am doing work on predicting household types (income group, number of workers, presence of children) based on a forecast of a number of economic variables from a regional economic model, such as a ...
1
vote
0answers
26 views

Is an autoregressive model considered a model for independent or dependent data?

It seems to me that, in the statistical literature, data, models, and inference seem to conflate the terminology of dependent and independent. Case 1: a cross sectional sample of weight and height ...
2
votes
1answer
34 views

What is the difference between prior vs bias? (term usage)

I'm confused about the usage of the term "prior" vs "bias". They often seem to be synonymous? Example 1: I'm estimating the probability for heads of a coin, and use a Beta(20, 20) prior. Then you ...
0
votes
0answers
10 views

Deciles Threshold Training vs Validation

I will try to be as clear as possible. I train a scoring model and the goal is to target top deciles for example from it (let's say, 10, 9 and 8). So i have my model, i apply on new datasets and now ...
0
votes
1answer
12 views

What is the proper analysis to run when trying to compare means between multiple years?

I am trying to figure out the proper statistical analysis for my problem. I have a data set that has many variables but I am interested in how the mean deer density changes over time. I have multiple ...
0
votes
0answers
18 views

weighing percentage changes by number of samples

Applying one simple formula for percentage change. This: 100 * (8 - 2) / 2 = 300% gives the same results as this: ...
0
votes
0answers
38 views
+50

Sampling from sample (and not from population, and not from distribution)

Say I have a large model with input parameters that are themselves the result of large models that are long to run. I am interested in the uncertainty of the large model results, and want to estimate ...
0
votes
0answers
14 views

How can I visualize weights of various Keras model layers?

Mostly just for funsies I want to visualize various layers of a Keras model as it's training. So, let's say I make a wee model: ...
1
vote
1answer
20 views

What is the largest n root transformation I should consider for making a time series stationary?

Currently, I am working with multiple time series and not all of them are stationary. In order to make them stationary I am considering different transformations and checking the augmented dickey ...
0
votes
0answers
9 views

Using Correlation to get Accurate Probability

I am trying to gain a better understanding on how to integrate correlation with probability. I am trying to solve the following: There are seven classes and a student can get one of 4 scores, A, A-, ...
0
votes
0answers
3 views

Differences in correlated factors as independent variable changes

My problem is similar to the following: I want to know what factors impact plant growth rates under different temperature conditions. I have data on growth rate, temperature in degrees, and a number ...
4
votes
2answers
48 views

variance of the square of the bias on linear regression

Basic setting let the linear model be: $$ \mathbf{y}=\mathbf{X\beta}+\epsilon $$ where $\epsilon \sim N(0,\sigma^2\mathbf{I}_n)$ $n$ is the number of samples $p$ is the number of attributes. $\...
0
votes
1answer
24 views

Same model coeffs, different R^2 with statsmodels OLS and sci-kit learn linearregression

I'm getting to know Python regression tools with the intention of benchmarking against ML tools available on a couple of cloud based services. I'm using the boston dataset distributed with scikit-...
0
votes
0answers
6 views

Averaging GLM's based on delta AIC < 2 and using the resulting coefficient estimates with their associated raster to build a predictive raster

I'm trying to construct a predictive spatial raster based on averaged GLM's Not the exact code but an example: mod1 <- glm(c~ x1 + x2 + x3, data=data) mod2 <- glm(c~ x1 + x2, data=data) mod3 &...
0
votes
0answers
5 views

How to align predictors with target variable when predictors are sampled at a lower frequency?

I have a set of models I am creating in which the target variable I am forecasting is sampled at a high frequency (daily) but the predictors are all Federal Reserve Macroeconomic variables which are ...
0
votes
0answers
30 views

Fix latent variable endogenous variance (NOT residual variance) in Lavaan

I am fitting some models using lavaan. I have a number of latent variables (specifically I am fitting ACE behavioral genetics models with multiple phenotypes). For the model to be interpretable the ...
2
votes
1answer
18 views

Anova with three factors- interactions and further analysis?

I have an experiment design which comprises of 3 different materials, treated with 3 conditions and a control at 3 different depths. The variable I am measuring is onset oxidation temperatures (OOT). ...
1
vote
0answers
27 views

How to adjust confidence-interval based on model accuracy?

I have a binary classifier with 94% accuracy on unknown test data. I use that model to classify samples from a large population in order to infer the proportion of positives within the population. I ...
0
votes
1answer
17 views

Which metric to use to report regression results: RMSE, R2 or Pearsons Corrrelation?

I'm a bit confused about when to use RMSE, R2 or Pearsons Correlation Coefficient (Rp). I've read some papers that reported RMSE and Rp and didn't even mention R2, but I also found papers reporting ...
1
vote
1answer
34 views

Low Bias in an overfitted model

I have a question about the bias-variance tradeoff in machine learning concerning the implications of overfitting: Assuming $y = f(x)$ + some noise, the error of our model for any input $(x,y)$ is ...
1
vote
1answer
43 views

Using the $Z$-test instead of the binomial test for small $n$ - effect on power and Type I error

Setup Let $M \sim \text{Bin}(p,n)$. Let us then state the following two hypotheses: $$\begin{align} H_0: p = 0.5 \text{ vs } H_1: p > 0.5 \end{align}$$ To test these hypotheses, I could use the ...
0
votes
0answers
18 views

Finding slope of regression line [on hold]

Consider the following econometric model : $q_{i} (quantity demanded)= a_{0} +b_{0}p_{i}+ u _{i}$ $q_{i} (quantity supplied)=a_{1} +b_{1}p_{i}+ v_{i}$ Where $b_{1} > 0$ and $b_{0} < 0 $. ...

15 30 50 per page