Predictive models are statistical models whose primary purpose is to predict other observations of a system optimally, as opposed to models whose purpose is to test a particular hypothesis or explain a phenomenon mechanistically. As such, predictive models place less emphasis on interpretability and ...

learn more… | top users | synonyms

0
votes
0answers
14 views

Forecasting with Dynamic values using R [migrated]

I have a Json object : {"tcDetails":[{"project_nm":"abc","id":"1","n_tc":"32","TC": [{"29/06/2015":50,"30/06/2015":45,.....}] {"level":[{80,85,90,95}]}]} ...
0
votes
0answers
13 views

Forecasting values along with corresponding years [migrated]

I have a sample data set (named as s3) in the following manner: ...
0
votes
0answers
8 views

Missing at source data and predictive model

I have multiple sources of data, and each comes with its own set of observable cahracteristics. Most are common between all sources, but some sources have extra information that is useful, but not ...
3
votes
1answer
27 views

Multivariate multiple linear regression model

I have 2 response variables (Y1, Y2) and some independent variables. I need to predict both Y1 and Y2 using the same set of predictors.In other words I need to fit the model: $Y=XB+E$ where: $Y$ has ...
0
votes
0answers
7 views

Regression model with percentages

I have a dataset with 5 dependent variables ($y_1$,$y_2$,$y_3$,$y_4$,$y_5$) and some independent variables. Each dependent variable is a percentage (so it goes from 0 to 100). The sum of the 5 ...
0
votes
0answers
9 views

How to interpret the R output of anova.coxph

The likelihood ratio chi^2 test is the gold standard for comparing nested Cox models. However I am not sure how to interpret the R output. ...
2
votes
1answer
23 views

Choosing a sample rate for GBM models

I've created several GBM models to tune the parameters (trees, shrinkage and depth) to my data and the model performs well on the out-of-time sample. The data is credit card transactions (running into ...
0
votes
1answer
21 views

Manually scoring logistic regression model in SPSS? [closed]

First off, I'd like to apologize for my cluelessness, but I've come across a problem that I honestly have no clue how to circumvent. My programming skills are extremely limited, and my company uses ...
0
votes
0answers
22 views

Uplift model with a continuous outcome?

Does anyone know any good packages (preferably in R/python) or references that are specifically about building the uplift model with a "continuous" outcome? I've used the upliftRF from R and made it ...
1
vote
0answers
23 views

How to identify important independent variables for a dependent variable?

I have a dependent variable (DV) and about 200 independent variables (IVs). I want to understand which of the 10-20 variables are important for this DV. I could do: PCA - However it'll only tell me ...
3
votes
1answer
61 views

ROC curve for two-sided cut-off

I am very, very confused about ROC curves. I have a Bayesian model which outputs a prevalence on a continuous scale between 0 and 1. I have a classification I would like to use that classifies that ...
0
votes
0answers
11 views

reduced multilabel-dataset performance evaluation

Assume a multilabel problem with given ground truth, where each training instance can have one or more of 3 labels A,B and C, e.g: ...
1
vote
1answer
29 views

optimal sequential sampling in gaussian process models

Let's say we have a one dimensional dataset of 24 points along with their responses. I am reserving three boundary points for testing (i=1,23,24) and i am fitting a Gaussian process model based on a ...
7
votes
1answer
195 views

Should predictive accuracy or, alternatively, minimizing the MSE, be reconsidered?

Ever since Breiman, maximizing predictive accuracy has become a predictive modeling gold standard, of sorts. That it has evolved to this status is understandable: it can be "optimized," is easily ...
0
votes
1answer
32 views

What is the link between the logit and the probability of a binary event?

Reading about logistic regression model, I wondered about the link existing between the logit (or $log\frac{p}{(1-p)}$) and the probability of an event defined as binary by assumption and modeled by ...
0
votes
0answers
7 views

How to give less weight to past history when there are fewer past observations in a panel regression?

I'm interested in how to structure a panel regression so that units that don't have as many past historical observations don't have their predictions as highly influenced by their past data. For ...
0
votes
0answers
11 views

Determining contribution of histogram bins to a total

I have a situation where data in a histogram contributes to a final total numerical value. The weight of the contribution of each of the bins towards the final value is unknown, but a selection of ...
7
votes
1answer
173 views

Clarifications regarding reading a nomogram

Following is a nomogram created from mtcars dataset with rms package for the formula: mpg ~ wt + am + qsec The model itself seems good with R2 of 0.85 and ...
0
votes
0answers
35 views

Need a method for determining variable groupings in R

I am using R and trying to group one of my variables into larger groups so they have credibility. I have been manually setting each factor of the variable as the reference level, looking at all other ...
0
votes
0answers
16 views

Comparing probabilities of two predictive models

Someone has already asked this question. But it is not answered. I have 10 logistic regression models for 10 different product categories. Then i need to come up with the best product to be offered to ...
1
vote
3answers
164 views

Best loss function for very sparse real-valued data

Suppose the target output of my data prediction model is an $M\times N$ matrix where $95\%$ of the values are $0.0$ and the other values are anywhere between $0.0$ and $1.0$, what would be a good loss ...
2
votes
3answers
49 views

Comparing four classifiers

I have trained and tested four different classifiers, and I would now like to compare them. The classifiers have accuracies 95, 90, 81, 75. I know that there is no unbiased estimator of the variance ...
0
votes
0answers
15 views

Estimate VAR model from data about lags

Does anybody have any idea how i would write the var model based on this table? What coefficients should be included? Any hint will be much appreciated. Thank you!
0
votes
0answers
20 views

How best to predict periodic data

I have an event that occurs somewhat infrequently (for some data sets weekly, for some monthly, for some a few times a year, etc.). For many (but not all) datasets, there is some regularity (the ...
1
vote
0answers
27 views

Predicting time to failure with time varying cofators

The Goal I am modeling Hospital Length of Stay. More specifically, I would like to predict the number of days until a patient is discharged given all of the patients clinical factors throughout ...
1
vote
0answers
34 views

Machine learning technique for simple predictive model generation

I regularly deal with data in which I have a single metric that is computationally expensive to calculate. I also have numerous (less than a dozen) low-resolution metrics that attempt to approximate ...
0
votes
0answers
20 views

How to train a Gaussian Mixture Model using Testing Data

My work is to extract HOG features from Arabic Line images and than do classification using Gaussian mixture model to have a look at the performance. My question is after extracting the features how ...
4
votes
0answers
134 views

Determining the effect of number of likes

Let's say I have marketing data and I need to determine how effective the marketing is. The marketing strategy is to publish facebook posts at inconsistent intervals. The goal is to see how the ...
0
votes
0answers
23 views

what is the size of data should be predicted to make the predictive model valid

if I have time series with 1000 values , and I want to build a predictive model , how far in the future should i successfully forecast to make my predictive model valid, is there any condition or rule ...
0
votes
0answers
13 views

How do I model chapter-verse references?

Context: I am part of an 8-person group in which each person posts a Bible verse every day. For those who don't know, that is of the format "Psalm 30:1" where first we reference the chapter, then the ...
3
votes
1answer
31 views

Prior predictive density given by $f(y) = {f(y\mid \lambda) g(\lambda)}\big/{g(\lambda | y)}$?

(I guess stats.SE is the right place for this) I'm reading Albert's book "Bayesian computation with R". To get theprior predictive density, he extensively uses this formula $$f(y) = \frac{f(y\mid ...
4
votes
1answer
165 views

Data augmentation techniques for general datasets?

In many machine learning applications, the so called data augmentation methods have allowed building better models. For example, assume a training set of $100$ images of cats and dogs. By rotating, ...
0
votes
0answers
24 views

What regression analysis to use? IVs with two levels and a DV with two conditions?

I'm trying to figure out what the best regression test to use for my data. I have three predictor IVs each with two levels. I also have a DV values belonging to two different conditions (A & B). ...
1
vote
1answer
34 views

Question about training set and test set

Suppose I need to compare 3 different regression models. Suppose that my only purpose is to select the model which predicts the response variable better. Be M1, M2, M3 these three models. So I ...
0
votes
2answers
52 views

Traffic volume/flow prediction method

I have traffic volume data (Surrey City, CA) like this I wish to use Artificial neural network (Deep Learning) or ARIMA to predict traffic flow/volume of the urban area with the use of previous ...
1
vote
0answers
23 views

CTR Enhancement Model

I am looking to build a model to enhance CTR. Below is the business description. We have a coupon based website. For each retailer, we have a retailer page. Each retailer page will have up-to 100 ...
0
votes
0answers
22 views

How far can we predict in time series of price index?

If I build a model for time series that represents the price index of a stock market for 5 years, how far can I predict in the future? The reason for this question is that I want to be sure that the ...
0
votes
0answers
8 views

Evaluate and report fit of a model on validation cohort(s)

I trained a random forest regression model M on a training set. I am interested in how well the model predicts the responses in 3 different validation sets. I am also interested in the characteristics ...
0
votes
0answers
9 views

Seasonality in Modeling Population

To conquer the effect of seasonality in data, it is recommended to take multiple sample windows, with each having equal performance window. Question - Should we discard seasonality faced sample ...
0
votes
0answers
21 views

benefices of big data on machine learning methodologies

I know that there are a number of predictive models (generized linear ones, trees, neural network, support vector machines, knn, Naive Bayes, ...) that have been proposed to perform various analytical ...
3
votes
0answers
41 views

Logistic Regression Model with Non-Independent Regressors

I'm looking to create a model that takes into account multiple logistic variables in an ordered process. To illustrate, what I'm trying to do is similar to the following: ...
0
votes
0answers
38 views

How to choose between VOMs and Predictive models, e.g., ARIMA?

In time series prediction, there is a lot of work that uses predictive models (e.g., ARIMA). On the other hand, there's also a lot of work that uses Variable Order Markov models (e.g., context ...
0
votes
0answers
30 views

Distribution of output from accuracy {forecast}?

I'm trying to work out a method for "online" or live model evaluation for models used in forecasting. One approach is to use the R package strucchange, but it ...
2
votes
1answer
39 views

Which are the most important predictors (and how great is their impact) of a continuous dependent variable?

I have a continuous outcome (dependent) variable, which is body weight and I'm wondering which of my 20 candidate predictors (independent variables) are the most important ones for prediting body ...
0
votes
3answers
66 views

How to use Random Forest for categorical variables with missing value

I have a labelled dataset of 1M rows and 600 features. I am trying to build a supervised learning model for prediction. I am particularly working with Random forests in R.The data I have has following ...
0
votes
0answers
10 views

Characteristic Analysis : Variable Stability

What is the calculation of "Score Points" in characteristics analysis report (model stability analysis)? Is it the average of predicted probability falling in a particular variable cohort?
0
votes
0answers
9 views

Treatment for High Population Stability Index

What are the ways we can stabilize population if we have high population stability index greater than 0.2 in a predictive model? Or how to adjust if it is less than 0.2 but greater than 0.1?
0
votes
1answer
58 views

Random forest regression prediction for high dimensional data

I am working on a project by using a high dimensional data set. Close to 50000 Obs. with 392 Variable. I used lasso to reduce it to this point from a total of 1200 variables. And the whole data set ...
1
vote
2answers
42 views

How is the chance-level confusion matrix calculated?

I applied an ML technique on my dataset, and got this confusion matrix: 0 1 0 162 62 1 27 50 Funnily, the overall accuracy is worse than ...
1
vote
0answers
31 views

Predictive modelling and cost function

I have to help a company to detect customer in a list of prospects. The company has this benefit/cost function: Value of a new customer = $20 Acquisition cost = $5 So if the model: Miss to ...