Questions tagged [nonlinear]

This tag is deprecated because it is too broad. Please find a more specific tag.

Filter by
Sorted by
Tagged with
1 vote
1 answer
25 views

What is the definition of a non-linear estimator? I heard that ratio of estimators is non-linear

Why don't we consider nonlinear estimators for the parameters of linear regression models? says that LASSO is a non-linear estimator. I think LASSO has a solution via matrix multiplication. I don'...
0 votes
1 answer
26 views

Power calculation by simulation - what do I do with model failures?

I'm trying to run a power calculation by simulation on a set of exponential decay datasets using the nlme package in R. Here's the process: Simulate a bunch of exponentials, using some conservative ...
  • 11
0 votes
1 answer
26 views

Transformation of periodic data prior to PCA?

Basically I have periodic data (angles from -180 to 180) that I want perform a PCA on. However, since the data is periodic, a change in angle from say 170 to 10 will not be accurately reflected. I was ...
2 votes
1 answer
33 views

Can Correlation based feature selection discard features that show no correlation by themselves but are meaningful only if combined?

Assuming a feature selection process based on correlation or some other metric, is it possible to overlook input features that by themselves show no actual correlation with the target values, but that ...
1 vote
0 answers
16 views

Mapping Parametric Curves with auxiliary variables

The image below displays an approach of using an auxiliary variable to map the parametric curves of a standard normal pdf and cdf. In Equation (1), z as r.v. is clearly one-dimensional. However, after ...
1 vote
0 answers
81 views

Using curve_fit for Non-Linear, Multi-Variate Models [Python] [closed]

Warning: ML Noob. I have a 3D dataset (data at the bottom) with 2 feature variables and 1 target variable. Polynomial Regression produced unsatisfactory results and it seems that the relationship of ...
1 vote
0 answers
21 views

How to test a product of a OLS estimators?

I estimated a vector $\beta $ using OLS $\hat \beta =(\hat e_1 \hat e_2 \hat e_3)$ and I have the covariance matrice $\hat v(\hat \beta )$. How can I test this null hypothesis $H_0 : \hat e_1 \hat ...
  • 197
0 votes
0 answers
52 views

Estimating the coefficients of a non-linear regression

I am trying to estimate the coefficients $\lambda, \alpha, \beta_1, \beta_2, \gamma, \eta$ in the below equation using Python and some financial data $$ \lambda \times \text{(participation %)} \times \...
1 vote
1 answer
104 views

Is Ordinal logistic regression linear or nonlinear?

Quick question, is ordinal logistic regression a linear or nonlinear model? Finding different sources supporting the other, and the more I read the more I get confused myself. Perse, it should fall ...
0 votes
0 answers
19 views

Advice on fitting curve to three-pooled plant decomposition model in r

I have just finished running a plant decomposition experiment measuring the decomposition of pine needles across climate and lithological types. We have mass loss, plant chemistry data (c, n, labile ...
0 votes
0 answers
17 views

How do I fit a nonlinear mixed effects model with multiple observations from the same sample units using nlmer()?

I am trying to fit a nonlinear mixed-effects model with lme4. However, I am not sure how to adequately account for my sampling design. The model is supposed to ...
0 votes
0 answers
30 views

Need a predictive (binary outcome) model for a set of binary variables and one continuous variable

I have a data set of about 1600 binary results, that I want to predict from 9 binary variables and a continuous variable. The relationship between the continuous variable and the result variable by ...
0 votes
1 answer
69 views

Fitting a cubic-like curve to data in R

I tried using nls() in R to fit the following expression to a set of data: where g=9.8, alpha & B_0 are unknown, a = 0.01, z_0 = 0.3 such that: theory <- as.formula(V~-(9.8)ab*(pi)(0.02^2)(T)(...
  • 3
0 votes
0 answers
43 views

Differentiate One-step ahead prediction, Simulation (or free run simulation), Open Loop architecture and close loop architecture in NARX

I'm trying to figure out the difference of the following terms from one another: One-step ahead prediction; Simulation (or free run simulation); Open Loop architecture; and close loop architecture I'm ...
0 votes
0 answers
21 views

Distribution of product of samples from two Normal distributions [duplicate]

Hello! I have two normally distributed random variables $M \sim N(\mu_1,\sigma_1^2)$ and $V \sim N(\mu_2,\sigma_2^2)$ having physical meaning as $M$ - mass and $V$ - volume. I need to figure out the ...
1 vote
0 answers
30 views

Additive error model for non-linear case

I have checked other questions regarding additive noise model, but I could not convince myself for non-linear case. Assume the data vector $\mathbf{d}$ is described by a possibly non-linear ...
  • 11
0 votes
0 answers
44 views

Highly correlated linear and quadratic slope in Growth model; cov matrix not definite positive

I'm running a a Growth model in R using the package lavaan, function growth.mi(), on an imputed dataset with four measurement points. The model estimates an intercept, a linear slope, and a quadratic ...
  • 1
0 votes
1 answer
58 views

Kaplan's Non-Linearity Test

I've been searching for an R package or function that applies the Kaplan non-linearity test to univariate time series but they are nowhere to be found. Such test has been widely applied in the ...
1 vote
1 answer
240 views

Possible non-linearity pspline Cox model

Our working group ran a Cox regression with a p-spline to model the possible non-linearity of continuous variables. However, I'm a bit confused with the interpretation of the linearity or non-...
  • 606
0 votes
0 answers
19 views

Efficient metrics for measuring interaction and Building features

Long time user of tree models, rediscovered the benefits of Linear models recently. Now I want to transfer as much non linearity as possible into my features so to mimic as much as possible the ...
  • 219
2 votes
0 answers
283 views

How to fit logistic regression to circular data?

I've made a script that can do normal logistic regression with sigmoid(linear model). However, I have data that has a circular decision boundary and looks like this. My question is how I can modify ...
  • 21
1 vote
0 answers
81 views

Degrees of freedom for a $\chi^2$ with non-linear polynomial model

I have a $\chi^2$ below for some model function $F$: $$ \chi^2 = \sum_{i=1}^{i=M} \frac{\left(y_{i}-F\left(x_i;\vec{a}\right)\right)^2}{\left(\Delta y_{i}\right)^2} $$ I know that non-linear model ...
  • 143
2 votes
1 answer
41 views

If X^2 is not significant but X is significant, do I have to remove X^2 and run again the regression analysis?

Model DV ~ W+PDSR+Corr+(FAGDP1+FAGDP2)+log(PCGDP)+Exp+Pop+Health FAGDP2=FAGDP1^2 Result: After removing FAGDP2(FAGDP1^2) from the model, FAGDP1 turns to be insignificant Am I right in removing FAGDP^...
11 votes
2 answers
3k views

RMSE vs MSE loss function - the optimization solutions are equivalent?

If we optimize a function $f$ with respect to loss $L$, which is defined as RMSE; Are we going to get the same solution as optimizing MSE ? Even, if the function $f$ is non-linear (e.g. a neural ...
1 vote
0 answers
289 views

Quantile regression with an exponential function

The following equation: y = a*x**b where y is a nonlinear function of x. By taking logs, the equation can be expressed as: ln(y) = ln(a) + bln(x). I would like to run a quantile regression instead of ...
0 votes
0 answers
34 views

standar error of non-linear regression

I'm trying to compute the standar error of a non-linear regression fit, I find the answer in this post Non-linear regression confidence interval But i did't find that formula in any other place,and I ...
1 vote
0 answers
16 views

"Nonlinear" random spatial field: an example

I want to generate a "nonlinear" random spatial field in the sense that the autocorrelation function in function of the lag/distance $h$, $\rho(h)$, should be not equal to the $R(h)$ ...
1 vote
2 answers
293 views

Isn't ReLU just a linear function? [duplicate]

I am doing Andew Ng's Deep Learning course and he says that ReLU is better than Sigmoid, but it makes no sense to me at all. The biggest advantage of activation functions are too get a non-linear ...
2 votes
1 answer
59 views

Proof of how to calculate the coefficient of variation of a nonlinear function

I'm struggling to find the proof of Eq. D.14b shown in the figure below: The variable $b$ represents the “Least Squares” best-fit to the slope between $r_e$ and $r_t$ which both depend on $X_1$ to $...
  • 391
1 vote
0 answers
49 views

Why do we use Relu if it's mostly linear

We use activation functions in neural nets to introduce some non-linearity. Now I understand that Relu is a non-linear function and I had no problems with it. But today I learned that when the output ...
  • 43
1 vote
0 answers
19 views

Simultaneous interaction model with nonlinear equations

I observe many groups of 3 individuals, and I want to estimate an interaction model of the form: $$\begin{array}{rl} y_1&=f_1(x, y-1)+e_1\\ y_2&=f_2(x, y-2)+e_2\\ y_3&=f_3(x, y-3)+e_3 \end{...
3 votes
1 answer
92 views

Non-normal data transformation - what does it imply exactly and what does my results mean?

I am missing some understanding here. I am inspecting the relationship between the heart rate variability (HRV) and errors in the Sustained Attention to Response Task. When I conduct a basic linear ...
  • 77
1 vote
1 answer
139 views

Bayesian fitting of a nonlinear model [closed]

Some years ago I developed a nonlinear model and java fitting engine that performs well enough to be useful, but is definitely a hack. I would like to modernize and publish an open-source tool (...
6 votes
2 answers
240 views

Regression with flexible functional form

I am assuming a model of the form $$Y_i=\alpha+\beta X_i+g(\mathbf{Z}_i)+\epsilon_i,$$ here $\mathbf{Z}_i$ is an $m$ dimensional vector and $\epsilon_i$ is i.i.d. white noise. I would like to ...
  • 228
0 votes
1 answer
513 views

Correlation is a symmetric measure, but scatter plot matrix shows asymmetric dependence

The correlation matrix demonstrates that correlation is a symmetric measure: $\rho(X,Y) = \rho(Y,X)$ since the lower off-diagonals are mirror images of the upper off-diagonals. The scatterplot matrix ...
  • 3,199
0 votes
0 answers
361 views

How to use a scatter plot to detect non-linear co-dependence between two variables?

A scatter plot matrix of 3 time series (financial returns data) are shown below. It is a multivariate representation of a scatter plot, with the individual pairs shown in the off-diagonals. The ...
  • 3,199
4 votes
2 answers
990 views

Can non-linear dependence be detected between two variables by regressing them?

Linear regression is meant for linear relationships right, so, if I don't trust linear correlation and want to find out if random variables $y$ and $x$ have a non-linear relationship, can't I just ...
  • 3,199
16 votes
4 answers
2k views

What is the best programmatic way for determining whether two variables are linearly or non-linearly or not even related

What is the best programmatic way for determining whether two predictor variables are linearly or non-linearly or not even related, maybe using any of the packages scipy/statsmodels or anything else ...
0 votes
0 answers
25 views

Does a low correlation level warrant the need to try a different dependence measure?

Can it be determined somehow whether the correlation coefficient between two random variables would be insufficient for assessing the level and type of co-dependency between them, and that another ...
  • 3,199
1 vote
1 answer
61 views

Solving a system of nonlinear equations involving only products of unknowns

I would like to find the solution of a system of equations of the form: $A = w_1 F(x_k) + w_2 F(x_l) + w_3 F(x_m) +...$, where the unknowns are the $w_i$ and the function $F$, while my data are the $A$...
1 vote
0 answers
68 views

Stopped by zero step from line search - R stops optimization early

I am trying to minimize an objective function, $J(\theta)$, with respect to $\theta$, a 19-dimensional parameter vector. $J(\theta)$ is a smooth nonlinear function so I have tried various gradient-...
  • 11
1 vote
1 answer
530 views

How come covariance can pick up non-linear relationships but correlation can't? [closed]

correlation is computed from covariance so how come covariance can pick up non-linear relationships between variables $X$ and $Y$ but (Pearson's) correlation can't?
  • 3,199
3 votes
1 answer
2k views

Neural Network: Matlab uses different activation functions for different layers - why?

I have trained on matlab an Artificial Neural Network with one input layer, one hidden layer and one output layer (my output is values between zero and one, which I turn into 0 or 1 according to a ...
  • 571
1 vote
0 answers
33 views

How to decompose entropy into linear and non-linear components?

Mutual information is the entropy between two random variables, $X$ and $Y$, based on their probabilities. It captures both the linear and non-linear interactions between $X$ and $Y$, whereas ...
  • 3,199
3 votes
2 answers
81 views

Non-Linear Time Series Book

I am looking for a book to study non linear time series for both univariate and multivariate topics. Your suggestions will be greatly appreciated. Thanks.
2 votes
0 answers
83 views

Augmented Dickey Fuller and Nonlinear Time Series

Since the Augmented Dickey Fuller test assumes the time series to be an autoregressive-moving average model, I was wondering if it would be possible to explicitly construct a nonlinear time series ...
2 votes
0 answers
176 views

How to determine the influence of a variable on the relationship between another two variables?

I have three continuous variables X, Y, and Z in the form of timeseries at several geographic locations. All variables have a skewed distribution because the timeseries mostly have zeros in them ...
2 votes
0 answers
198 views

What are options if Rainbow test fails after Linear Regression

I tested with commonly available iris dataset and ran OLS with following formula: PW ~ SW + PL + SL + Species Output is as follows: ...
  • 9,203
8 votes
2 answers
1k views

Why not always use generalized estimating equations (GEE) instead of linear mixed models?

I read about generalized estimating equations (GEE) here, here and at other sites. It is mentioned in first of above links that "the parameter estimates are nearly identical" for linear ...
  • 9,203
1 vote
0 answers
25 views

Difference between sequential/simultaneous nonlinear partial least squares and NIPALS algorithm

I've been reading about nonlinear partial least squares, and according to the below study, there are two types of NLPLS: sequential NLPLS and simultaenous NLPLS. https://www.sciencedirect.com/science/...
  • 149

1
2 3 4 5
7