A statistical model is a formalization of relationships between variables in the form of mathematical equations. A statistical model describes how one or more random variables are related to one or more random variables. The model is statistical as the variables are not deterministically but ...

learn more… | top users | synonyms (1)

1
vote
0answers
12 views

Find distribution for a dataset $\mathbf{x} = \{x_1, x_2, … x_N\} \in \mathbb{R}$

Assume I have a dataset of $N$ observations $ \mathbf{x} =\{x_1, x_2, ... x_N\}$ where $\{x_i \in \mathbb{R} | 0 \leq x_i \leq 1\}$ and I want to find out how they are distributed. Is it possible to ...
3
votes
0answers
19 views

Does a well-fitting model have shallower chi-square minima than a poorly fitting one?

I am trying to fit some data with a range of models with some variable parameters, to determine which of the possible models best describes the data. I have noticed that if the model is a poor fit, ...
1
vote
0answers
13 views

Approximating a random field

I have got a bunch of $n$ ($\approx 100$) pixelized maps. Each pixel is a single figure. Each so-called map can be represented by a matrix whom each element is a pixel. Let's say that there $p\times ...
4
votes
1answer
80 views
+50

A person repeatedly selects the two most similar items out of three. How to model/estimate a perceptual distance between the items?

A person is given three items, say pictures of faces, and is asked to pick out which two of the three faces are the most similar. This is repeated a large number of times with different combinations ...
0
votes
0answers
39 views

Methodological advice

I need some help validating the statistical methodology I'm trying to use to analyze some data. My data is from a repeated measures study where each participant did two activities. Half of the ...
1
vote
0answers
12 views

How to separate model errors from measurement errors?

I've got data measured with errors that have known measured_RMS. I am testing a model that has model_RMS differences between model prediction and measured data. What would be a reasonable estimate of ...
0
votes
0answers
15 views

Methods for predictive modeling on continous target

I am trying to put a continuous target into predictive modelling method. The target is an amount that can range from 0 to unknown. I have roughly 1000 records (for modelling and validation ...
0
votes
0answers
14 views

Graphing GEE Models in R?

I am currently working on a biological dataset where I am attempting to fit a detection function (Detection probability as a function of distance). I have been using the package geepack (in R-studio) ...
0
votes
0answers
9 views

Need Insight on Measuring Variable Effect

I apoligize in advance for the wall of text. I'm working on a project in which I have been asked to determine what factors influence employees leaving our company. Also, it would be useful to be able ...
0
votes
0answers
11 views

Modeling Switch-Like vs Continuous Signal

I'm currently trying to figure out the best way to model a given scenario, but am unsure of the best way to go about it, so I'll explain the situation in as much detail as possible. So I work in a ...
0
votes
0answers
10 views

Need advice on how to model this scenario in NLME

I am wondering how to analyze this scenario using non-linear mixed effects. I am a working at the novice level, and will have access to the Pinheiro and Bates book through my university library soon. ...
0
votes
0answers
6 views

How to adjust logistic models in case bivariate analyses encounter issues?

The model looks like: Y = X1 + X2 + ... + Xi Y is categorical or, to be exact, ordinal Xs can be categorical (dichotomous, ordinal, nominal) or continuous I first run bivariate analyses between Y ...
3
votes
1answer
70 views

Studentized residuals undefined

I am wondering if anyone could explain why there are some states where Studentized residuals are undefined. For example I got the following R code: ...
1
vote
1answer
10 views

Problem fitting a geeglm regression

I am fitting a model using geeglm in geepack and ran into a problem. I have a dataset pertaining to oil consumption and fit the below model. ...
0
votes
0answers
26 views

Time series: What is my natural time period?

We are modeling univariate ts with R. Sampled daily since 1-1-2013 at five observations per week. We are unclear about how to decide 'natural time period'. Until now we just assumed 260 weekdays in ...
4
votes
1answer
39 views

Algorithm does not converge in R

I am doing a logistic regression in R, where I am modeling how potholes and weather correlate to accidents. When I run a logistic regression, I get the message "Algorithm does not converge" The ...
0
votes
0answers
44 views

Regression Analysis and Optimization in R

I have the following table: ...
0
votes
2answers
40 views

How to modify variables to be significant in logistic regression?

I am running a logistic regression analysis in a particular software. My objective is to study the behavior of the software with significant variables. However, with the data I have, there are no ...
2
votes
0answers
56 views

Is regularization of a linear model really needed?

I'm going to do linear regression on a data set with 60k observations, each with 120 features. The way I see it, there is no why in the world that with more then 50 samples per dimension, a linear low ...
0
votes
0answers
9 views

Should the rivals models include the same number of observed variables?

The question is about comparing models that include different number of observed variables. For example consider I have an 80-items questionnaire and I want to do confirmatory factor analysis (CFA) in ...
1
vote
0answers
17 views

Categorical Variables - Factor Reduction - Can I use the dependent variable?

I am working on a basic fraud detection model. I have about 10 independent features and I am trying to predict if a given transaction is genuine or fraud. Most of the features are categorical and each ...
1
vote
1answer
22 views

Confusing definition of Potts model

I came across some Markov random field models and noticed something that didn't make sense to me. One of these models for a set of latent variables $\{z_{i}\}$ is the following: $$p(z) = ...
5
votes
1answer
67 views

Assuming a probability density for MLE to do model selection

Motivation: I am trying to use Akaike Information Criterion to assess model ranking and over-fitting risk for a set of nonlinear models. I am an electrical engineer with no formal statistical training ...
0
votes
0answers
27 views

Model averaging with MuMIn. What's the mean of pvalue?

the summary() of a model.avg made with MuMIn in R, give a lot of interesting results, in particular model averaged coefficients (estimate, standard error, adjusted standard error and a z value with a ...
2
votes
0answers
23 views

Is there a simple model that assumes a negative relationship between the mean and variance of response?

Poisson and Negative Binomial models assume that the variance of response is greater or equal to the mean of response. Is there a simple model where that assumption is reversed, i.e. variance goes ...
5
votes
1answer
139 views

Are normally distributed residuals not necessarily homoskedastic?

Let's say I've ran a linear regression and I'm checking the model diagnostics. I made a histogram of the residuals and they appear more or less normally distributed as below. I thought for a long ...
0
votes
0answers
31 views

Can we use the AIC values to compare a hurdle poisson model to a multinomial logit model?

I estimated two different models using an SP survey: Hurdle poisson and multinomial logit with 5 alternatives. My dependent variable is the number of weekly trips (0,1,2,3,4,5 trips) that students ...
0
votes
0answers
22 views

Hypergeometric distribution and its continuous counterpart

I'm modeling an urn without replacement. I'm drawing $m$ balls from an urn containing $p_w$ white balls and $p-p_w$ black balls and I want to know what is the probability that I draw at least $m_w$ ...
1
vote
0answers
8 views

AIS data modelling! [closed]

I am interested in exhaust emission modelling with the use data received from vessels equipped with the Automatic Identification System (AIS). Are there any resources developed so far in relation to ...
1
vote
0answers
20 views

Is there a list/catalog of types of regression to choose from?

In my practice, I often find out that after the basic assumptions for linear regression are not met, I have to discover a new type of regression I should use. For example, in the past, I came across ...
3
votes
2answers
82 views

Function Approximation vs. Regression

Some background before I state the questions: I have a $d$-dimensional random vector $X=(X_1,\ldots,X_n)$ and a function $f:\mathbb{R}^d\rightarrow\mathbb{R}$. Ultimately my goal is to understand $f$ ...
1
vote
0answers
40 views

Parameter distribution from profile likelihood

This question is regarding profile likelihood to obtain CI of parameters. There is a published parameter values that best fits (using minimum chi square)the data for some mathematical model say ...
0
votes
1answer
41 views

Goodness of fit: observed vs simulated data

I have a set of 2-dimensional "observed" data of sample size N: $$O = \{(x_1, y_1), (x_2, y_2), ..., (x_N, y_N)\}$$ The hypothesis is that $O$ is a realization of ...
0
votes
0answers
21 views

Modelling remaing time of a process

I have process which has different states. It looks something like this: In some cases the required tools for the assembly need to be fetched (same goes for the supplies for packaging). Typical ...
1
vote
1answer
72 views

Cointegrated Vector ARMA (CVARMA) Model vs. Dynamic Factor Model (DFM)

Two questions regarding the equivalence (or lack thereof) of vector error correction model (VECM) cointegrated vector ARMA model (CVARMA) and dynamic factor model (DFM): Can every VECM CVARMA be ...
0
votes
0answers
34 views

Linear regression vs additive modelling, any meaning when linear modelling has higher accuracy?

I have a simple question. Is there any important meaning when non-linear modelling (general additive modelling such as gamm in R) has lower accuracy than linear modelling? some useful plots are ...
6
votes
0answers
27 views

Reference for the idea that a simpler model can be used when the range of data values is smaller

When we build a statistical-physical model, generally, a simpler model can be justified when the range of data-values is smaller. I can't be the first person to use this idea, but I also can't find ...
0
votes
3answers
63 views

Good applied text for linear regression

I have a pure math background and am now studying statistics. For additional study in my linear regression and time series class, my professor suggested a more applied text rather than a higher level ...
0
votes
0answers
35 views

Optimally distributing sports tickets to customers

I work for a business that has a certain number of sports tickets to distribute to customers and potential customers every year, and I've been asked to develop a model that will give insight into ...
0
votes
0answers
28 views

Need to forecast a small data set. Suggest best method to go about

Hi I have sales data for previous 3 years(6 half years). I need to predict / forecast the sales for next 1-2 years. Tell me which method / model I should use. As always sales dependent on country ...
0
votes
1answer
45 views

Can someone look at my method for fitting a GEE to my data?

I’ve been doing some statistical analyses in R on some data. It’s for use in a manuscript I’m hoping to get published in a biological journal. Unfortunately, the tests I ended up having to run are ...
1
vote
0answers
26 views

Best way to examine mortality tables?

I have a set of tables containing mortality rates (hazard rates) and I want to see how well these values reflect the influence of the covariates (age, sex, issue year, etc.). I also have actual ...
1
vote
0answers
26 views

binomial test for over-represented kmers in biological sequences - what is the right test?

Imagine you have a long string, like a genome, and you split it up into every overlapping word of size n. This is called a kmer. ...
0
votes
1answer
90 views

Interpretation of $\theta$ in negative binomial regression

First off, a very similar question has been asked before. But the answers to this question did not explain what high/low values of theta mean. Here's my crack at trying to figure out what high/low ...
0
votes
0answers
24 views

Model loyality effect of returning customers

I have customers which book an offer about once a year. I'd like to determine if there is a "loyality effect" - i.e. a customer from this year is more likely to book next year again. I can see that ...
1
vote
1answer
33 views

Zero-inflated negative binomial model for true zeros

The zeroinfl function in the pscl package in R assumes that zeros include both false zeros and true zeros. I have a zero ...
3
votes
1answer
70 views

Model selection: where to start? [closed]

For a general modeling problem, there are literally at least a dozen choices of statistical and algorithmic models to choose from. Off the top of my head, choices could be: regression (and its ...
0
votes
2answers
48 views

Difference in predicted value using two different methods

Take these two vectors: ...
1
vote
1answer
41 views

Choosing between two parameters in a model

I have a few parameters that are related (let's call them X1 and X2), and I want to use whichever one will provide the strongest model. The model has many other parameters. Would I simply be able to ...
1
vote
0answers
41 views

Point Estimate of normally distributed threshold parameter with unknown mean and variance

I'm new to Bayesian analysis an applied what I learned in John Kruschke's book to simplified versions of a model I previously fitted with non-Bayesian methods. For those simplified versions, even ...