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 ...
1
vote
0answers
39 views
Independent, Dependent Variables, Nonlinear
So, I am not a statistician, but a burgeoning mathematician. Here is something that is perplexing me in statistics, however. My apologies if the question is silly, on one hand, or just not solvable, ...
3
votes
1answer
101 views
Is the exponential distribution a good model for this data?
I'm trying to determine if the exponential distribution is a good model for a data set that I'm exploring. It doesn't have to be precise. I'm using the data for capacity planning (if it's a good fit) ...
0
votes
0answers
33 views
Understanding the formula of a model. Translating a statistical model into R code in order to understand its meaning
Here is a quote coming from a biology article:
...
-2
votes
0answers
91 views
Why does statistics work? [migrated]
Statistics deals with probability, where even an extremely unlikely event has some chance of happening. What if there's a series of these unlikely events going on for thousands of year. I mean it ...
0
votes
0answers
17 views
Averaging gridded data with missing values
I would like to use various parameters of remote sensing data (i.e. chorlophyl, sea-surface temperature, wind stress, etc.) as covariates in a species distribution model.
I have sightings data, ...
2
votes
1answer
54 views
Fitting data to gamma distribution to find score which corresponds to pvalue < 0.05?
I have data of size 116.667 rows defined as:
...
2
votes
1answer
42 views
interaction terms in separate models?
I'm doing a multilevel mixed model with three cross-level interactions in LMER. Do all three interactions necessarily need to be included in the same model or can I evaluate them in three separate ...
3
votes
0answers
59 views
Build statistical model
I need to build model where y depends on x (y~x). But while I have the usual data for Y, I only have a range of values for X, e.g.
...
0
votes
0answers
16 views
(Population) pharmacokinetic M&S: AUC from sparse sampling in R
I’m relatively new to (population) pharmacokinetic analyses and have a principal question with corresponding programming. I have both an already established pharmacokinetic model and a new data set ...
1
vote
1answer
34 views
How to correctly model noise?
Assume a linear mixing model $x = As$, where $x = (x_{0}, ..., x_{n})^T$ are linear mixtures of $s = (s_{0}, ..., s_{n})^T$, and $A$ is the mixing matrix.
Now, if I introduce additive noise to this ...
3
votes
0answers
37 views
Is there a better reference for r formulae than ?formula? [migrated]
There are many redundant, and sometimes conflicting, ways of specifying formulae in R. Is there a comprehensive yet concise reference for mapping a conceptual models to R syntax than ...
0
votes
3answers
102 views
Identify seasonality in time series data [duplicate]
I want to detect presence of seasonality in time series data. I know one can achieve that by plotting the autocorrelation function but I need an automatic process if the series is seasonal or not, ...
1
vote
1answer
40 views
Modeling stimulus-response output
I am trying to analyse some data and I am a bit lost as to what is the correct approach to take.
The data are blood hormone levels, taken repeatedly from various subjects, after a certain treatment, ...
0
votes
0answers
16 views
Distribution of linear model parameters when the outcome variable values are Fisher Z transformed correlation coefficients
I am trying to develop a method for comparing individual correlation coefficients from multiple participants from different groups having performed different conditions of a task.
In terms of ...
17
votes
6answers
917 views
What is the meaning of “All models are wrong, but some are useful”
"Essentially, all models are wrong, but some are useful."
--- Box, George E. P.; Norman R. Draper (1987). Empirical Model-Building and Response Surfaces, p. 424, Wiley. ISBN 0471810339.
What ...
0
votes
0answers
15 views
Distinguishing events from different periodic sources
I have records of the time stamps of events coming from a small number of independent sources. Each source $S$ issues events at a given period $Ts$. Due to some jitter the time intervals between two ...
0
votes
1answer
25 views
BMI at baseline & followup with exposure at baseline; model change or BMI at FUP? Control for BMI baseline?
For a prospective occupational cohort where everyone is exposed to one or more chemical agents, examining BMI at follow-up compared to a specific chemical exposure at baseline, is it necessary to ...
0
votes
0answers
19 views
How to constrain parameters in reression models in STATA? [migrated]
I am looking for a way to impose constraints on some of the parameters in a regression model in STATA. More specifically, it is a FE panel data model estimated with XTREG. I have searched the ...
2
votes
0answers
34 views
Modelling rainfall to size storage tanks
I have daily rainfall data for a given site going back about 30 years.
I have a building with an average daily demand for water of $L$ litres and a catchment of $A$ m$^2$ with a runoff coefficient of ...
0
votes
1answer
65 views
Modelling two correlated variables
I wish to simultaneously predict two correlated time series. Here is a plot of one time series against the other:
At the moment I have separate linear regressions for both of them which rely on ...
1
vote
0answers
15 views
jtest vs coxtest
In library "lmtest" The jtest and coxtest functions are used to see if two non-nested models are equivalent.
According to the help function:
...
0
votes
0answers
55 views
How to identify a new pattern in a URL with a machine learning algorithm (Text mining)
I am trying to identify new patterns after analyzing a number of URLs. So let's say, I am investigating the hypothetical website Yoohle.com and their URLs have the following structure.
domain = ...
-7
votes
2answers
156 views
Can you see any S-curve in the scatter plot [closed]
two variables >>> scatter plot >>> relationship >>> ? S-curve!
1) any S-curve?
2) S-curve?
3) if S-curve no scatter plotting?
4) linear correlation=0.85 >>> meaningless?
5) explain the relationship
...
0
votes
1answer
37 views
Fitting models in R with time restriction on coefficients
How should I define a model formula in "R", when one (or more) exact linear restrictions binding the coefficients is available.
Equation: y = b1*x1 + b2*x1
where y = b1*x1 for t < t1 and y = ...
1
vote
2answers
106 views
What model can I use to describe the following time-series?
I'm wondering if someone might be able to help me locate an appropriate model for the following two time-series (the cyan and blue one, the reds are rolling means).
I'm looking more for a general ...
2
votes
1answer
151 views
Comparing models using anova() function in R
From the documentation for anova():
When given a sequence of objects, ‘anova’ tests the models against one another in the order specified...
What does it ...
1
vote
0answers
11 views
Models for learning acquistion process
Imagine such a memory test for a mice. The mice performs an experiment $E$ with two possible issues $0$ (failure) and $1$ (success). If the mice gets $1$ it is "rewarded", if it gets $0$ it is ...
0
votes
0answers
30 views
Given a response variable and 7 parameters. How can I find the function of these 7 parameters which outputs the response variable
I have 7 parameters and an associated output of a system. How do I describe this system? I wish to accurately predict the output given by tweaking the input parameters?
I am not a stats person, so ...
1
vote
1answer
35 views
Local sensitivity around the maximum
After having inferred a statistical model for my physical system $Y=f(X_1, \dots X_n)$, I want to estimate the local sensitivity of each variable $X_i$ (one by one) around the point of maximum ...
0
votes
1answer
60 views
Trying to fit a model after detrending
I have data for Hydrogen Sulfide Series, see here http://www.wikiupload.com/Y4WAZJ4Z0IMTK7V
I applied a Box-Cox Transformation with $\lambda =1/3$ to try to stabilize the data.
I plotted a few sample ...
0
votes
0answers
22 views
Modeling revenues of products in many classes
I am doing product classification that classifies product descriptions into one of thousands of classes. I design a classifier that compute misclassification cost based on the product's expected ...
3
votes
1answer
49 views
Question on the usage of regularization in applied statistics/science
I was reading the paper ``A significance test for the lasso'' by Lockhart, Tibshirani et al and was considering the issue of applying regularization in the applied sciences (for example, behavioral ...
0
votes
1answer
171 views
additive and non-additive(multiplicative) interactions - soft question -
we use models with multiplicative interaction effects when relationship between independent variable and dependent variable are non-additive.
My question is, Are all models with multiplicative ...
1
vote
0answers
24 views
Pattern of events that leads to a goal
I am not a statistician, so go easy on me here...
I have collected lots of data on the behaviour of customers in a shop. A customer will enter the shop and a series of events will then take place ...
1
vote
0answers
55 views
Do I apply delta method correctly?
I'm no mathematician, so please consider the whole explanation as a subject to criticism and optimization.
I'm trying to build a model and calculate an estimate of error variance for the following ...
1
vote
1answer
91 views
How do I fit a constrained regression in R?
I have a formal model from which I'm deriving some parameters that I would like to estimate. I haven't done this kind of thing before, and I'd like to have some help to solve this issue in R. I ...
0
votes
0answers
39 views
Issue in system identification using black box modeling and Yule Walkers Equation
I have a set of observation, a vector consisting of 500 positive real values. I am having a tough time in figuring out what should be the model, i.e a general equation representing the data values. I ...
0
votes
0answers
162 views
How helpful is a quant job in Goldman Sachs for later PhD in Machine Learning?
I am a masters in Computer Science and am interested in pursuing a career in Machine Learning, possibly academic, in the long run.
I have been offered a position related to Financial Modelling at ...
1
vote
0answers
39 views
Probability model for repeated survey data
I'd like to find a suitable probability model but I'm not sure if the one I've thought of makes sense. The intention is to apply a Bayesian analysis to survey data which has been sampled twice. The ...
2
votes
1answer
41 views
How can I estimate a score for my users, on if they will match ad campaign criteria?
I have ad campaigns that I want to display to users. Each one has criteria a user must meet in order for them to be valid for the campaign. For example, "User must be in the USA", or "User must like ...
1
vote
1answer
77 views
What is the explanation for a regressor losing statistical significance when a high leverage point is dropped?
I'm currently working on an Econometrics project and I've come to a point where I've dropped a high leverage point as identified by cook's distance and a leverage plot (had observations that were ...
0
votes
2answers
182 views
Time series prediction - what is Autoregressive Tree model ? (Python)
Our problem: model evolution of values of a continuous variable over time.
I came through a paper presenting an approach for predicting the next values for a time series. Whereas ARIMA model is more ...
1
vote
1answer
63 views
Is there any reason to prefer a bayesian model with few variables?
I have two alternative hierachical bayesian models that were designed to the describe the same process (from a high-level point-of-view). Both model provides
comparable (but not identical) inferences ...
0
votes
0answers
26 views
how to deal with a very predictable variable - but very small sample - should I keep them ?
I am doing modeling for say response y ~ a+b+c+e+f.. x+y+z ( say I got model for decision tree )
if my dataset is big, say 1M records :
I have a-z independent variables , but having x,y,z are ...
2
votes
0answers
37 views
Fitting models to empirical data: do fits for random samples converge on the true fit?
I'm trying to fit a mathematical/theoretical model to empirical data, but the dataset is impractically big to fit all at once. (Specifically: I'm fitting a power law model using the methods of ...
0
votes
1answer
60 views
Factor intercorrelations and model design
Having done an exploratory factor analysis (SPSS), what exactly can I infer from the factor intercorrelation table that is output after the factors are extracted/rotated?
If two factors are ...
0
votes
0answers
182 views
Generalized linear model with autocorrelation, offset and poisson/nb family?
My data consist of daily counts of patients with certain disease (respiratory disease), their residency area, sex, age category and smoking prevalence in each area. I want to model these counts with ...
1
vote
0answers
69 views
Do we normalize too much? [closed]
Yesterday i read this blog post Predictors, responses and residuals: What really needs to be normally distributed?
and I wonder what do you think about it. Personally I totally agree with the ...
10
votes
2answers
1k views
What is the relationship between R-squared and p-value in a regression?
tl;dr - for OLS regression, does a higher R-squared also imply a higher P-value? Specifically for a single explanatory variable (Y = a + bX + e) but would also be interested to know for n multiple ...
3
votes
2answers
86 views
Formulation of a nearly linear model
I try to fit a model of the following form
$$
Y = (\beta X - Z)^+ + \epsilon,
$$
where $Y,Z \ge 0$ and $X,Y,Z \in \mathbb{R}$ and $(x)^+ = \max(x,0)$.
Note that $Y,X$ and $Z$ come from a sample, ...
