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)

2
votes
1answer
26 views

Is positive coefficient of price correct in a multiple regression model

I am currently undertaking forecasting of energy sales (kWh) for our industrial customers. From historical data gathered from 1993 to 2013, a graph of price per kwh against sales kwh shows a positive ...
1
vote
1answer
28 views

Geodesic distance and mean

My data-set consists of points in globe. Suppose a User visits locations $l_1,l_2,\dots l_n$ (each location in $(lat, long)$ in the city with probability $p_1,p_2,\dots,p_n$ and I want to calculate ...
1
vote
1answer
22 views

Model specification with Deflators: methodological question on forecast model

I am trying to build a model to predict one year ahead Earnings per share $(t+1)$ based on variables in year $t$. I’ve seen a lot of models in practice that use the following methodology: ...
0
votes
0answers
8 views

VARMAX model in R

Is there a function in R that estimates the VARMAX model? There is one for a VARX (MTS package), but I didn't find one that works with the MA part also...
0
votes
1answer
24 views

Simulate data by using existing dataset

I have a complete dataset with input variables and response variables. I would like to perform a simulation where I give the input variables and generate randomly the response variables. Is there a ...
4
votes
1answer
84 views

Model with non-linear transformation

I don't understand this concept well and need help. I was choosing whether to use a linear model or apply a non-linear transformation in my model formula. To do a diagnostic, I quickly plotted my ...
0
votes
1answer
24 views

Specifying lag in `dlnm` when passing arguments to `crossbasis`

I am using the dlnm package to build a finite distribute lag linear model. I intend on testing the model-fit based on various lag levels to assess which lag is ...
1
vote
1answer
35 views

How can I (Should I?) use logistic regression/the logit function to predict outcome of a tennis match in a simple simulator?

I am trying to create a tennis simulator. Specifically I am trying to make a 'random' simulator so that I can see how many times streaks of wins or losses occur, and then compare this to historical ...
1
vote
1answer
36 views

Regression on wavy angular data?

I'm a newbie at stats/machine learning so please bare with me. This plot is a result of an experiment that attempts to find the perceived angle of a stimulus. The stimulus is placed at a position ...
1
vote
1answer
60 views

How to capture & present lm model output from R

After running iterations of lm() in R, I am now stuck with which components of the model's output to present and how to present them. I know that the $R^{2}$ value, ...
0
votes
2answers
33 views

What does initial level of GDP mean?

This might come as a very trivial thing and way below standards of this group but I am struggling to figure out what do the authors mean when they say that they have used initial level of income in ...
0
votes
1answer
12 views

Alternative to MAPE when the data is not a time series

I have a data set where many of the actual values are zero, so I can't use MAPE. It's not a time series, so I can't use MASE ala our very own Rob Hyndman. Is there another alternative to MAPE that I ...
1
vote
0answers
23 views

Overly-sensitive goodness of fit measure: where did I go wrong?

I'm using the chi-squared goodness-of-fit measure to evaluate instances of a fairly complicated model, but the evaluation is unbelievably sensitive to small variations in the model parameter values. ...
0
votes
0answers
8 views

How to model my data into a probit

I am beginning my thesis, and I need some advice. I am trying to estimate a probit model. The binary dependent variable is employment status, and the independent variables include network size, age, ...
1
vote
0answers
26 views

Estimating a distribution from a dataset with multiple parameters

How would you go about solving the following problem? You're an insurance company who writes workers compensation policies. You want to build a probability distribution for the number of annual ...
0
votes
1answer
9 views

procedure of statistical modeling of sample

I never did the statistical modeling of sample. Usually i was engaged in common statistical procedures(descriptive statistic, correlation, regression, factor analysis and so on). Now i decided find ...
0
votes
0answers
24 views

Naïve Random Walk Model as a Benchmark for Predictive Model

I constructed a predictive model for $Y_{i,t+\tau}$ for $\tau=1 to 3$ using panel data with firm and year observations: $Y_{i,t+\tau}=a+bX_{i,t}+e_{i,t+\tau}$ and i'm trying to measure the ...
0
votes
0answers
40 views

Estimation parameters for latent (unobserved) variable

Here is my problem: I have 3 variables $X,Y,Z$ : $X$ is the number of clicks we observed on an web advertisement; $Y$ is the number of time a customer do a sign-up on the website after clicking ...
0
votes
0answers
19 views

How to model the number of pedestrian crossed for a certain distance, and the number of smokers in particular?

In a city of 2 millions people, with 950km of streets, I'd like to estimate the probability to get close to a smoker i.e. less than 10 meter. For that let's represent streets without width, in a ...
0
votes
1answer
93 views

modelling data that contains only ones and zeros

I'm new to modelling this type of data, and I got punished for asking this on stackoverflow... I have a dataset where the predictive variables contain only ones and zeros, and the response variable ...
0
votes
0answers
25 views

Different models for different quantile functions possible?

My aim is to estimate the 2.5%- and 97.5%-quantile function (to get reference intervals) for a specific score in dependence of age separated by classes of a third variable cag. So first I built 11 ...
2
votes
2answers
43 views

Steps in making a Global Regression Model

I saw a journal article [1] saying that he constructed the following S-curve model : $$y=\exp\left({\beta_1 + \frac{\beta_2}{x}}\right) + \mathrm{residual}$$ The topic was about a global regression ...
3
votes
2answers
57 views

What are some methods for generating simulated time series data for use in modeling?

I have a data set which consists of 50 observed years for which I have date and inflow values between a river and a reservoir. The data is formatted as follows: ...
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 ...
0
votes
1answer
30 views

When making a predictive model that is predicting a continuous outcome, how does one arrive at the final prediction?

For instance, a prediction of 1 million could be: A weighted average of various predictions. ex. a .5 chance of 2 million, a .5 chance of 0, for an expected value of 1 million; or The prediction ...
1
vote
1answer
76 views

What econometric model to forecast a seasonal commodity demand while incorporating exogenous Information?

I have a monthly commodity demand and try to forecast this series for the next 5 years. Here is a plot: Of course, the natural approach to forecast this seasonality would be some kind exponential ...
0
votes
0answers
11 views

Should I use coefficient correlation or multiple linear regression to build this scoring model?

Hi I am a junior Data analyst at a non-profit and I need some help with building a 'donor scoring model' to help us identify potential 'good' donors. I am attempting to build a donor scoring model by ...
3
votes
1answer
22 views

Non-constant standard deviation in residuals

I am fitting a model in the frequency domain, and my fit looks as follows: As you can see, the model function does not fit the data perfectly, especially in the higher frequencies. So, I examined ...
1
vote
0answers
34 views

Logistic regression model fit assessment

I have run logistic regression on data. The concordant percentage is coming out 45. That is too low. However, Hosmer–Lemeshow test is coming out insignificant. It means we cannot reject the null ...
1
vote
2answers
84 views

Logistic Regression Model Validation

I am validating a logistic regression model. This is the first time i am validating a model. I am using split sampling method. I have split data randomly into two parts - 70% development and 30% ...
2
votes
1answer
54 views

Interaction effects in big data sets

I'm looking for a method to identify a shortlist of potentially good 2-way interaction terms rather than trying all possible interactions. This question is similarly asked before here but in a more ...
2
votes
0answers
39 views

latent variables versus model parameters

I am quite confused with the distinction between a latent variable and model parameters. So say I have two observed variables $x$ and $y$ and they have some unknown relationship between them i.e. $y ...
0
votes
1answer
29 views

Sum of weights in portfolio theory is not equal to 1

I'm trying to understand basic portfolio theory using R. As far as I understood, the sum of the weights of assets must be equal to 1 . But in this link, that teaches how to compute the efficient ...
0
votes
0answers
12 views

Validating a multivariate categorical model

I assume that my population is a sample of an unknown multivariate categorical distribution $\mathbf{X} = (X_1, X_2, \ldots, X_k)$. From this population, a sample $\mathbf{X^*}$ is available, I assume ...
1
vote
0answers
59 views

ARIMA - SARIMAX modelling with R

I am really new to R and to time series. My field of studies is in the field of Networks and Telecommunication, but my summer internship is about trying to find a statistical model for some sets of ...
0
votes
0answers
39 views

Nested logit program in R

My question is specific to transportation modelling using a nested logit (NL) model. I wonder how to make a program including a t-parameter, t-value, and likelihood in R. I did estimation in a ...
1
vote
0answers
43 views

Taking into account Bayesian model uncertainty

I recently received a review of a paper from a Bayesian Statistics Journal. The Associate Editor wrote this mini-review (quoted below in full). The paper is talking about Bayesian modeling of DNA ...
3
votes
0answers
64 views

Regression analysis when the covariables is a sample from a population of potential variables

This question comes from trying to analyze my recent exam (exam I have given and corrected) statistically. I have a list of questions (20 in total) and each question is given a score from 0 to five, ...
4
votes
1answer
30 views

How to make use of known constants when modeling from data?

As a (perhaps contrived) example, let's say we want to discover from some empirical data Coulomb's law for an electric field: $$F = \frac{1}{4 \pi \epsilon_0} \cdot \frac{|q|}{r^2}$$ In this case we ...
4
votes
1answer
56 views

Creating a model for prices including supply

I'm working on modeling secondary market ticket prices for sporting events, but the issue I'm running into is that the model (a linear regression) assumes that more season ticket holders and more ...
0
votes
0answers
25 views

Item Response Theory alternatives

What are other approaches than Item Response Theory to model learning of students in standardised tests?
5
votes
1answer
56 views

When forecasting sequential data is it best to use auto-regressive models or build a more traditional n x p dataset with features?

I'm familiar with the use of auto-regressive models when it comes to forecasting a single vector of time-series data. Is anybody familiar with a more traditional modeling approach, i.e. - creating ...
0
votes
0answers
15 views

Variable Construct (Dimension) Insertion (Representation) in SmartPLS

I have a question please. I am working on SmartPLS. The question is regarding variable construct representation. Any variable could have construct including dimensions. For example, the ...
0
votes
0answers
26 views

How can I estimate that a customer wont buy again?

I have a history of purchases from different clients and I'm trying to calculate a threshold in days after which the probability of the client making another purchase is below 50% (asumming that this ...
1
vote
0answers
15 views

Do significant control variables need to be eliminated from statistical analysis in general and SmartPLS specificly?

I have been told that we need to eliminate control factors that shows a significant impact on the dependent variable from the model. As I know that control variables are variables that have testified ...
2
votes
1answer
25 views

Question about the probability chain rule

I've understood from this: Is this a correct statement of the probability chain rule? that in the chain rule for probability, conditioning can be done on different variables. I was wondering what ...
2
votes
0answers
19 views

Polynomial model with unpaired data

I'm trying to model data as a 2nd degree polynomial, but the data is unpaired and each data point of average values has a standard error for each axis. My data: A time series in minutes (time ...
0
votes
1answer
58 views

If you convert factors into indicator variables, do you treat them as continuous predictors?

Let's say I have a data matrix X where one feature is a factor with 8 levels. If I change this to be 7 indicator variables of 1's and 0's, do I need to make these columns factors as well? Or if I am ...
0
votes
0answers
49 views

Dealing with linear dependent variables

I have a large dataset with many subject each with responses from a consecutive year going back 10 years (ie 100,000 persons per year (not necessarily 10 data points per person as they may not have ...
0
votes
0answers
21 views

Logistic Regression Performance on training data set V/s AIC

I am fitting a logistic Regression on data set having 700 variables (after Chisquare test) and 15000 rows. For that I did best subset analysis using glmulti package in R on first 70 variables and got ...