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

1
vote
0answers
8 views

How confident can you be of prediction accuracy, even in the case of a causal relationship?

If we use the example of the correlation between frequency of criquet chirps and temperature, where there is a causal relationhip between temperature and criquets' chirping rates; it seems to me we ...
0
votes
0answers
11 views

How to predict Kalman filter based ARIMA model in R?

I am learning R and time series models by myself. I wrote a code for using ARIMA model based on Kalman filter to predict next 10 steps. But, I am not sure if the code is correct as I checked many ...
0
votes
0answers
11 views

Is there a non-boostrap way to estimate confidence intervals for Kernel regression predictions?

Simple problem of estimating: $$ y = f(x) + \epsilon $$ Where I use your standard Nadaraya-Watson Regression to guess $f(x)$. This is relatively fast and works well even in an online setting. Now I ...
0
votes
0answers
6 views

Proving that lagging results is sufficient to prevent foreknowledge in model

I am trying to explain to a friend why lag prevents foreknowledge in a model. The example that sparked the discussion is here:quantstattrader My Attempts Shifting the prediction back by one wouldnt ...
0
votes
1answer
41 views

Predict results of Elections

I have information on the votes in my town and in the country. I want to predict the results in the country's elections knowing the results in my town. What methods I can use? I have thought of ...
0
votes
0answers
6 views

Prediction whose distribution is shifted and is more leptokurtic

I have a model that, based on subject matter knowledge, should give predictions which have about the same density distribution as the training data. The actual predictions have a similar shaped ...
0
votes
0answers
4 views

How does Quest differ from, for example, C&RT or C5.0?

SPSS Modeler has implementations of a number of decision tree data mining algorithms. Some of them are relatively well-known, such as C&RT and C5.0, some slightly less so, such as CHAID and QUEST. ...
0
votes
0answers
13 views

What are the prerequisites for learning predictive Analysis? [on hold]

What are the prerequisites for learning predictive Analysis? Is mathematical statistics a must?
0
votes
0answers
27 views

What statistical modeling would allow a more accurate Brexit prediction [on hold]

Bookies and hedge funds both underestimated the support for Brexit (bookies at one point gave the Brexit 7% odds). Some factors such as variance in voter turn out, and variance in the populations ...
0
votes
0answers
35 views

How to prove the reliability of a predictive model to executives?

I trained data from 500 devices to predict their performance. Then I applied my trained model to a test data set for another 500 devices and show pretty good prediction results. Now my executives want ...
0
votes
0answers
10 views

Torch - SparseLinear nn to handle large inputs and large output for a prediction problem

I'm pretty new to the magic of torch7 and seek your help/advice for a problem of mine. Context: I am working on a prediction problem. We observed a certain pattern in our values and would like to ...
1
vote
2answers
59 views

Suggestions for appropriate regression models? [on hold]

The image is like a larger version of the one posted, but not as clear. I am trying to find a model that can fit to that pattern so that I can identify when there is a break in the pattern. I am ...
0
votes
0answers
10 views

Doc2Vec giving very less accuracy - 0.0002 [closed]

Using this tutorial - http://sujitpal.blogspot.in/2016/04/predicting-movie-tags-from-plots-using.html I am using the same code for a slightly different problem such that each doc has exactly one tag ...
0
votes
0answers
13 views

Why are the estimated probabilities of event from a multivariate logistic regression model equivalent to the crude event rates?

I have a large dataset (19k) and I am using logistic regression to estimate probabilities of experiencing an event at the patient level. I am interested in looking at the effect of a facility ...
0
votes
0answers
21 views

Is Logistic Regression Appropriate for this Question?

I am attempting to predict the ranking of NBA teams next season based on the number of games they won this season. To do this, I thought I could use a logistic regression with historical data. As ...
0
votes
0answers
16 views

Compare predictive power of 1 model on different data

I would like to test if the odds of bets on football matches with higher betting volume are more efficient (i.e. predict the result better) than bets with lower betting volume. I use a probit model ...
0
votes
0answers
15 views

Innovations algorithm in Matlab [migrated]

This seems like it's supposed to be a simple task but going through the "predict" documentation in Matlab I found this to look unnecessarily complicated so I could be looking in the wrong direction. ...
1
vote
0answers
16 views

Stacking/Blending Predictive Models with More than Two Outcomes

I've been experimenting with stacking predictive models recently. I've mainly been focused on looking at making meta-models based off of predictive probabilities of smaller models while implementing ...
1
vote
0answers
17 views

Creating a blended dataset/transitioning from one predictive model to another

I'm working with two different models right now using a variable X as an input. One of the models is said to be applicable for values of X less than A, and one is said to be applicable for values of X ...
1
vote
0answers
22 views

Prediction with large inputs and outputs

Being a total newbie with machine learning, I thought I would seek your advice on a problem of mine. I'm looking for any leads, starting points ans help you could provide me. I'm looking to predict ...
3
votes
0answers
29 views

Is it ok to use symmetric loss function when evaluation metric is asymmetric?

I completely understand that it's ok to use a loss function different from the evaluation metric. For example, accuracy isn't computationally feasible to optimize directly since it's not ...
1
vote
0answers
42 views

LSTM mimicking unseen time series data during testing

I have built a LSTM network which has been trained on a time series dataset (which is week-wise logged). The LSTM is able to make pretty accurate predictions as of now. Training data seems to have ...
1
vote
2answers
57 views

What is wrong with “PROC fishing” syndrome?

RE: https://www.quora.com/What-do-statisticians-e-g-Stats-PhDs-think-of-data-scientists-in-industry-without-stats-backgrounds There are several comments made regarding "PROC FISH syndrome", whereby ...
0
votes
0answers
22 views

Mixed Models: Random effects for baseline measure

I’m currently working on a data-set where we used a diary-design. As I’ve got multiple measure points for each individual, I decided to use mixed models to analyze the dataset. Our participants filled ...
1
vote
1answer
25 views

Deciding Optimal Cutoff for a Prognostic Index derived from Cox Proportional Hazards

I am planning to develop a prognostic model that would identify a particular group of head neck cancer patients who will do better if chemotherapy is added to standard radiation therapy. The data for ...
1
vote
0answers
16 views

How to preprocess features for supervised similarity learning

I have a data set of profiles that describes a set of people and a binary classification describing when some of these people have been grouped together in the past which I am assuming implies ...
0
votes
0answers
13 views

simulation and model comparison

I created a simulation to compare a number of regression type models/estimators, lets call them M1, ...,Mn. for each iteration of the simulation run: I generate randomly data set X I generare ...
0
votes
1answer
16 views

Can we predict / formulate regression equation for a dichotomous variables and scale predictors ?

Can we predict / formulate regression equation for a dichotomous variables and scale predictors ? Example : If I want to predict if applicant will success or fail in interview based on scale variables ...
1
vote
1answer
20 views

multiclass models: probabilities to predictions with asymmetric distribution of class

I'm dealing with the following problem: I have a multiclass variable, y, with let's say 7 classes. The 7 classes are not evenly distributed, some are way more likely to occur than others. Let's say ...
0
votes
0answers
13 views

Combining probabilities with different amount of evidence in sequence learning

Let us think of a simple case of sequence prediction. Based on 20 observed items, b was observed 16 times, c 3 times, and d only 1 time. The sequence is as follows: ...
1
vote
0answers
20 views

Intuition behind Tensor-based predictive models [closed]

I am trying to understand how can I use tensor to predict events. Let's suppose that I have users Ui * and I have predictors Pj over time. What are the tools and concepts that I need to know in ...
1
vote
1answer
62 views

Fixed Prediction Interval

I want to place a Multiple Regression model into a production system and use the Prediction Interval as a threshold for anomalies. I've seen how I can calculate the Prediction Interval two ways: $$...
0
votes
1answer
12 views

Appropriate divergence measure for a distribution over ordinal values

I would like to measure the divergence (or, more appropriately, symmetric difference) between two distributions $P$ and $D$. In general, you could consider using a measure like Jensen-Shannon ...
0
votes
0answers
18 views

How to propagate “model covariance” into a covariance matrix?

I have a theory $f$ (actually a set of coupled non-linear differential equations) that, from a vector of $n$ initial conditions $\vec x$, is able to predict $m$ values $f(\vec x) = \vec y$. I can ...
0
votes
2answers
29 views

choosing a model after feature selection process

so ive been selecting features for a regression problem and have obtained a list of the best performing feature sets. (note my list is actually several thousand lines long) 188.493 186.989 [379.45, 0....
0
votes
0answers
8 views

Getting probability estimates for each observation from cross-fold validation in SKlearn?

Let's say I have a model that I want to retrieve cross-fold validated probability predictions from. I can divide my data set into n folds, leave one fold out, get probability predictions for each ...
0
votes
1answer
25 views

number of features in feature selection for text mining problems

Let's say for a text mining problem (e.g creating a predictive model using text analysis), using a feature selection method (e.g TF-IDF) we come up with 1000 features/words/tokens. Is there some ...
0
votes
0answers
14 views

SVD - collaborative based filtering - Prediction matrix

On the movielens dataset, I used SVD to find U, s, and V matrices. Then performed the dimensional reduction by elimination of everything corresponding to lower valued eigen values( upto a threshhold). ...
1
vote
1answer
41 views

Goodness of fit, predictive power, discrimination

I'm making a couple of logistic regression based predictive models and intend to compare them and see which is "best". "best" here is obviously ill-defined, but as I'm looking for common metrics for ...
2
votes
1answer
32 views

Preprocessing in predictive models

I'm trying to make a predictive model using logistic regression but before that I'm wondering what kind of explore I can do on my data to get a better understanding or even help me with the model ...
0
votes
0answers
17 views

Model for predicting real value from vector of binary features

I have a population where individuals are described by a set of binary features (about 20 variables); some features are correlated, and some features imply others (i.e., if var A is positive, var B is ...
2
votes
1answer
34 views

How to predict from glm created with average values?

I want to predict count data (example: people visiting a beach) based on some predictors (example: temperature, cloudiness). I have created a generalized linear model (with Poisson distribution and ...
6
votes
1answer
110 views

What is the point of dividing data into training and test parts to assess prediction properties when we have AIC?

Asymptotically, minimizing the AIC is equivalent to minimizing the leave-one-out cross-validation MSE for cross-sectional data [1]. So when we have AIC, why does one at all use the method of dividing ...
1
vote
1answer
23 views

Prediction of vertex scores in a bipartite graphs

I have a bipartite graph with two sets, A and M, of nodes. Every vertex in M has a score associated with it. I have two tasks: To every vertex a in A, I have to assign a score based on the scores of ...
0
votes
0answers
19 views

log loss and squared loss in shrinkage tuning in R?

My model is logistic regression. Is there a way to tune the parameter lambda of lasso or ridge based on cross-validated log-loss and brier(eg. proper scores?) in any R packages? I'm using glmnet ...
0
votes
0answers
10 views

Can different data mining algorithms cross check each other's feature selection?

I have worked with the same data set for a little while, using a number of different data mining algorithms. As a result, I have developed a short list of predators which are virtually always useful - ...
0
votes
1answer
43 views

Learning from clicks on Ads [closed]

I need to build an algorithm that predicts the number of clicks a facebook ad would get in the next 7 days. Based on the given requirements, I prepared a dataset consisting of the following ...
0
votes
1answer
25 views

Standardization and prediction on new data

As far as I know it is common practice to do standardization of variables before shrinkage or PCA, which are methods I intend to use on my model selection for a predictive model. But the problem is, ...
4
votes
1answer
61 views

Predictive model developement for logistic regression?

In the statistical courses I've taken, which are mostly introductory, when I have a model I would make hypotesis tests to reduce it to the simplest form and am effectively done. It is my understanding ...