Use this tag only for regression models (q.v.) in which the response is a nonlinear functions of the *parameters* (not because it's a nonlinear function of the *predictors*).

learn more… | top users | synonyms

1
vote
1answer
30 views

Good machine learning algo for partial derivatives?

Does anyone know of good robust algos to estimate partial derivatives of a regression model? I am talking about a general regression model like this: $\mathbb{E}(y|x_1, x_2, ... x_n) = f(x_1, x_2, ...
0
votes
0answers
9 views

how to implement linear or non linear regression for 3d position estimation?

I am a beginner in Machine Learning. For my project I need a regression algorithm that can estimate the 3D position of a device based on some constraints (moreover inputs). I know how to implement ...
1
vote
0answers
37 views

Help with fitting a non-linear model in R using nlsList

I've done a lot of research so far on fitting a non-linear model in R, but I'm having trouble with it. I'm working with creating a ticket sales model that looks like: ...
0
votes
1answer
55 views
+50

R: Fitting a model with periodic, nonlinear and categorical components

Can anyone give me some advice on how to fit a model with linear (some categorical), non-linear and time series components in R? I don't want to use a non-parametric model like a Loess smooth or ...
2
votes
0answers
32 views

Catagorical variables with very uneven distributions? Removal/modify/leave?

In my current dataset I have quite a few categorical variables. Most have decent distributions between the categories. 30:40:30 splits etc. where these are percentage of dataset members per category ...
3
votes
2answers
32 views

What model would be appropriate for predicting electrical consumption given multiple (mostly) independent variables?

I have about 1000 samples worth of daily electrical consumption for a building. I'd like to build a predictor based on a number of observable inputs, including: daily temperature (continuous) hours ...
3
votes
1answer
35 views

Fit nonlinear parameter

I'm attempting to fit this model: $P = C_0 + C_1*U^r$ Given known vectors of observations $P$ and $U$, I want to fit values for $C_0$, $C_1$ and $r$. How do I make this fit in R? or preferably GSL ...
1
vote
2answers
23 views

Can time be squared to develop a curvilinear model of crop yield against time?

I am developing a linear model of yield against time (33 years of yield data) where year is 1975,1976....2007. I want to know whether change in yield over time was linear or not. So I fitted a linear ...
2
votes
1answer
49 views

N-sigma curves for a non-linear least square curve fit

I'm using python's scipy.optimize.curve_fit routine (which uses a non-linear least squares) to fit an exponential function of the form: ...
1
vote
1answer
30 views

Multiple regression analysis with spatial data as independent variable

In my PhD thesis I am working on spatial modeling of different chemical parameters in groundwater, and for spatial modeling I am also using the multiple statistical approach. I have a question about ...
4
votes
1answer
93 views

Residual plot for nonlinear regression

I have a couple of questions regarding performance of nonlinear regression models. Are the residuals from a nonlinear regression model supposed to be randomly distributed too (as in linear ...
2
votes
1answer
11 views

Error on extrapolated values from a fitted function

I have some data points and I fitted a function (2nd order polynomial here) to the data. The algorithm (scipy.optimize.curve_fit) gave me the optimal parameters and ...
-1
votes
1answer
27 views

Why can certain variables in a multiple regression not be included in logarithmic form?

I have a multiple regression equation where log(salary) = b0 + b1(ceotenure). What is the purpose of putting the dependent variable in logarithmic form? How would you interpret the change in y for a ...
6
votes
1answer
226 views

Nonlinear regression

I have some functions of $x$, in the form of $d\sqrt{x}$ or $d\log(x)$ where $d$ is known. I would like to rewrite (approximate is fine) them in the form $a/(1 + bx^c)$, where $a$, $b$ and $c$ are ...
1
vote
1answer
44 views

$R^2$ correspondence for nonlinear time series

Is there a statistical measure for nonlinear time series data that is comparable to $R^2$ value in linear regression (giving an idea of how well the fit is)? The data is not monotonic, so I cannot ...
0
votes
0answers
17 views

Linear Kernel taking more time to train than RBF Kernel (SVR)

I'm doing a Support Vector Regression with about 70k samples with 500 features each. I'm using sklearn implementation of SVR and my input for the train set is a sparse matrix. But, for my surprise, ...
1
vote
0answers
21 views

Guessing starting values for PARAMETERS statement in PROC NLIN

How to guess what should be the starting values for beta estimates, which we need to specify in PARMS or PARAMETERS statement while using PROC NLIN (PROC NLIN is used to run non-linear regression in ...
0
votes
0answers
52 views

Google Prediction API Flaws

I have been testing the google prediction api https://developers.google.com/prediction/ It seems to be excellent, i gave it 5 features so it can predict a regression problem, the API fitts the data ...
6
votes
1answer
112 views

Gaussian mixture regression in higher dimensions

Problem: I have a discrete representation of a surface/height-map $z = f(x,y)$ that i want to model as a mixture of gaussians (please take probability distributions out of your mind for a moment). ...
0
votes
1answer
25 views

How can I apply LR with non-linear features?

My training data looks like this: ...
3
votes
3answers
319 views

Any algorithms better than polynomial regression

I am trying to fit a baseline through my data, and I am not getting close enough with polynomial regression. I used gradient descent to set the parameters. Are there any other ways or algorithms that ...
3
votes
1answer
110 views

Is this identifiable?

I am interested in the following model : ($1 \leq i \leq p$, $1 \leq j \leq n_{i}$) $$y_{i,j} = A (1+a_{i})(t_{i,j}+\gamma_{i}) + \varepsilon_{i,j}$$ where $A \in \mathbb{R}$, $(a_{i})_{1 \leq i ...
0
votes
1answer
28 views

Looking for measurement for nonlinear model

I use KNN regression to train out a model. The model estimates running time of a program based on different inputs, and the output is a single variable, which is time (double type). I want to ...
0
votes
0answers
21 views

Parametric spline regression after Gaussian process regression?

I'm trying to develop a (functional) model to predict the output of a computer simulation. I've run a small set of experiments, varying the 4 predictors $a$, $b$, $c$, and $d$ via LHS, and calculated ...
0
votes
0answers
17 views

Regression with t distributed autocorrelated errors

I am new, so please bear with me, until its correctly formulated: In short: I am doing simultaneous non-linear regression (parameter estimation) of two different parametric models to three different, ...
0
votes
1answer
53 views

Confidence region about a regression model

I have a set of means and standard deviations. For each mean I can calculate a 95% confidence interval. I plot these means and confidence intervals against an independent variable and I fit a best ...
1
vote
0answers
46 views

Predictive model for heavy tailed distribution

I have a variable with values strongly skewed towards zero: table() ...
1
vote
1answer
36 views

Nonlinear model wirh effects over linear term

I have been working in R with nonlinear models such us: $Y = \alpha_{0}\text{(varia)} + \alpha_{1}\text{Time}\text{(varia)} + ...
0
votes
1answer
39 views

significance of coefficients and significance of marginal effects

Suppose I have a non-linear model, say probit/logit, how can I understand the significance of a coefficient as opposed to the significance of it's marginal effect? Say, I just need to know the ...
0
votes
0answers
47 views

Piecewise nonlinear regression by MLE in R software

I have been working with nonlinear models whose parameters have been estimated by Maximum Likelihood. Also, I use the "Vuong" test for model selection in non-nested models, this test requires to have ...
1
vote
0answers
8 views

What do I do with zero columns in a tensor.prod.model.matrix?

Suppose my two marginal bases are given by (for variable $p$ and $t$ the degree is equal to $1$ and $5$ inner knots are used). ...
1
vote
0answers
28 views

Comparing nested, non-linear models

I would like to compare the fit of two non-linear regression models: 1) $$ Y = (\Pi^{10}_{i=1}\beta_i^{x_i})^{1/\Sigma \beta} $$ 2) $$ Y = \begin{cases} (\Pi^{10}_{i=1}\alpha_i ...
1
vote
1answer
45 views

Regresssion of Accurate Data

I'm collecting calibration data for a device which involves three variables $S$, $L$, and $x$. For a given coordinate $(S, L)$, the device will provide me with the corresponding value of $x$ to a high ...
1
vote
1answer
59 views

Multiclass logistic regression update algorithm

My question pertains to section 2, called "Multi-class Logistic regression", of this pdf, especially the update rules. (The entire section is only a couple of paragraphs.) Everything seems to make ...
7
votes
2answers
204 views

Selection of k knots in regression smoothing spline equivalent to k categorical variables?

I'm working on a predictive cost model where the patient's age (an integer quantity measured in years) is one of the predictor variables. A strong nonlinear relationship between age and risk of a ...
1
vote
0answers
29 views

How to calculate standard errors of a non-linear model prediction?

I'm trying to understand how to show the prediction error of a model fit in R using the non-linear least squares function nls. Although there is an argument ...
3
votes
4answers
93 views

Beta confidence intervals in transformed linear regression

Let's say I have a model: $$Y_i = \beta_0 \beta_1^{X_i} \epsilon_i$$ (note: This is slightly different than the more common example case of $Y_i = \alpha e^{\beta x_i}\epsilon_i$.) I can take the ...
1
vote
0answers
23 views

Nonlinear Random Effects Model Specification in R

I have a dependent variable w with independent variable x representing time, which is clustered by variable site. In addition, I have indicator variables for 3 time period: i1, i2, i3, which ...
0
votes
0answers
19 views

Modify Levenberg Marquardt

Could you kindly let me know if it is possible to print parameters to the console as they are being optimized (using the levenberg marquardt algorithm) in python/matlab? I have been trying to do so ...
4
votes
1answer
144 views

How to calculate 95% confidence interval for non-linear equation?

I have an equation to predict the weight of manatees from their age, in days (dias, in portuguese): R <- function(a, b, c, dias) c + a*(1 - exp(-b*dias)) I ...
0
votes
0answers
18 views

Statistics for catch of tuna longline

I have study on catch for tuna longline. In here I have 3 independent variables (number of hooks, length of branch line & baits) and 3 dependent variables (catch of tuna, catch of marlin & ...
2
votes
1answer
35 views

How do I prove the significance of a non-linear model?

For example, for linear models, you take the p-value of the regression, and you deduce if the regression is or not significative. But with non linear models, in R, there isn't shown a p-value ...
4
votes
3answers
479 views

Why is polynomial regression considered a special case of multiple linear regression?

If polynomial regression models nonlinear relationships, how can it be considered a special case of multiple linear regression? Wikipedia notes that "Although polynomial regression fits a nonlinear ...
3
votes
1answer
77 views

Interaction effects in non-linear models

I have a general question about interpreting interaction effects in a non-linear model. I understand the reasons Ai and Norton (2004) suggest using the stata inteff command to help interpret ...
1
vote
1answer
83 views

Comparing two curves with different x-axis points - appropriate test?

I have two curves and I want to be able to calculate the probability of these curves coming from different distributions or another appropriate statistic. Each curve is fitted through the mean of ...
2
votes
1answer
101 views

How to solve the problem, that the scale of variables influence the gradient/optimization

I've the problem that, using something related to Fisher-scoring, the gradient, which is usually the sum over a variable times a value which depends upon the parameter we are looking for, the updates ...
1
vote
1answer
57 views

Type of regression method to use

I have the marker data of 32 patients for eight different markers. WHat needs to be done here is to predict the type of marker which is suitable for the disease control. I used Disease control as the ...
0
votes
0answers
37 views

Is it possible to estimate the convex combination of parameters in the IRLS-Framework?

Suppose I want to estimate the parameter $\mathbb{E}(Y)=\mu \ge 0$ with $\mu = a(\alpha)\mu_1(\gamma_1) + \Big(1-a(\alpha)\Big)\mu_2(\gamma_2)$ where $a(\alpha)\in (0,1)$ Using the usual ...
0
votes
1answer
97 views

What is SVM regression? Is it for regression or classification?

I'm trying to understand what is SVM regression. It's used for classification or regression? Can someone give an intuitive understanding of it?
1
vote
0answers
32 views

How to deal with imperfect multicollinearity

I am estimating a model for an assignment, and found out that there is a 0.9 correlation between two of the independent variables. So If I am not wrong I should omit one variable and redo the ...