Questions tagged [predictive-models]

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 more emphasis on performance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
6 views

Single event prediction using multivariate time series data

I want to predict a single event by using multivariate time series data. The event I am going to predict is 100% going to happen in the following weeks but not sure when. And this event is going to ...
  • 1
1 vote
1 answer
19 views

Reliability of yes or no questionnaire

I have a questionnaire of 15 questions with "yes" or "no" responses distributed to 20 participants. It will be used as an index measure of a variable. How do I measure the ...
1 vote
1 answer
16 views

Should we reinsert trend after doing forecast using detrended data?

Basically, when we detrend a signal, we detect and remove a linear component of that signal. This produces a stationary version of that signal. And we can use various forecasting algorithms to ...
11 votes
4 answers
597 views

Why do the widths of confidence & prediction intervals change across a regression line - shouldn't it be the same with i.i.d?

I thought that we assume i.i.d and therefore identically distributed (constant variance) over the line? But aren't the below saying that technically the distribution changes from one X value to ...
0 votes
0 answers
16 views

What would be a good machine learning model to predict how independent variables with low correlation affect the dependent variable?

I am currently trying to build a machine learning model to predict how a variable "age" affect the efficacy of a worker. The dataset includes many dependent variables, but the only variable ...
  • 1
0 votes
0 answers
10 views

How to forecast sales for different product types and categories

I'm trying to predict sales for a tea export company with different tea types and weights. My goal is to predict sales for each product type category for the next 12 months. Data set looked like this <...
1 vote
1 answer
31 views

Does probability calibration descrease model prediction variance?

Does probability calibration decrease model prediction variance? Example: Let's say we have a classifier that is a mail spam detector. It outputs a score between 0-1 to quantify how likely a given ...
  • 327
0 votes
1 answer
27 views

Assessment of interval-censored survival models

How can I evaluate a survival model made for interval-censored data? I'm building my models in icenReg, which only allows you to check for whether the proporitional hazards assumption is satisfied. ...
  • 49
1 vote
0 answers
14 views

Predicting from a Gamma Hurdle Model in JAGS

I fit a gamma hurdle model to invertebrate biomass data and am having trouble predicting from the model. I've been using these posts extensively to try to set it up: Gamma hurdle model for continuous ...
0 votes
0 answers
30 views

R^2 accuracy xgboost Rstudio going to -500% [closed]

I have been building a model to predict a ratio: CTS=sales/visits. All the variables in the model are time decomposition and rolling means and rollings lags of the dependent variable. Now, this model ...
  • 33
1 vote
0 answers
8 views

Predicting discount % based on past failure rate and product types

I have 2 datasets with details about discount percentages and failure rates. The discount rates are given for each model manufactured by a certain brand. The failure rates are given at the brand level....
  • 11
1 vote
0 answers
8 views

Is a high prediction performance of allocated treatment evidence for lack of unobserved confounding?

Example Say Investigator 1 is looking to investigate the effect of fish consumption (a binary variable $A$ indicating whether they eat or do not eat fish) on cardiovascular health (a continuous ...
  • 1,094
0 votes
0 answers
12 views

Updating models with new data: how much is needed to keep a model accurate?

How do you update a model when the implementation of your model eliminates new data? I have created a boosted trees classification model that predicts whether or not the amount of money requested (<...
  • 41
0 votes
0 answers
12 views

In order to use the model on the most recent data, do they have to be cleaned in the same way as the data used to train the model?

I built Machine Learning model based on for example 100 variables which have been previously cleaned. Then I saved my ML model in pickle. Now, I would like to use my ML model to score my clients. And ...
  • 141
0 votes
0 answers
10 views

3D Surface Fitting

I have a large empirical dataset which may be modelled via the following 3D surface formula: A*[X]+B*[Y]+C*[Z]+D*[X]*[Z] = 1 Where X & Z are the independent ...
0 votes
0 answers
16 views

Is it better to replace the missing value with mean of it's WOE than variable mean?

I am working on upgrade model of a product. One of the important feature when merged with base creates missing value as the value for those base accounts isn't available. In such a scenario which ...
1 vote
1 answer
24 views

Linear regression : The value of R2 increasing with the incraese of the number of K folds when using cross validation : is it a good thing?

Let's say I have a dataframe with one dependent continuous variable and multiple independent categorical and continuous variables. I want to apply linear regression (using R language in my case). The ...
  • 243
0 votes
0 answers
15 views

How does reverse-causation/simultaneous affects prediction?

To my knowledge, reverse causation/simultaneous leads to biased inference in regression analysis, but if I am doing prediction instead of causal inference, how do they affect the predictive ...
0 votes
1 answer
51 views

How can I tell if the difference in abundance is significant when accounting for availability

I'm new to statistics and model and currently struggling to understand how to answer the following example question. I'm trying to find out if the abundance of snails on a particular food source is a ...
  • 1
0 votes
0 answers
22 views

How to predict a class from a nested data

I have a very complicated data and I would like to know if it is possible to use machine learning model for prediction or not. Let me explain about data: The data is a nested list that each list has ...
0 votes
0 answers
12 views

Understanding predictive distribution expression from an information theory perspective

Suppose we are given a set of $M$ models $f^{1}(\mathbf{x}), \cdots, f^{M}(\mathbf{x})$ each taking a vector $\mathbf{x}$ as input and outputting probabilities. We also have access to the one hot ...
  • 466
0 votes
0 answers
27 views

Added predictive value: valid approaches?

I am planning an analysis to quantify the effects of a new biomarker on cardiovascular risk in terms of added predictive value. Having read this nice post by @Frank Harrell: https://www.fharrell.com/...
1 vote
0 answers
58 views

Evaluate a model for a changing distribution

Suppose that I have an unfair 6-sided die. Each time I roll it, the weights for the various sides change in a deterministic way (edit: based on the results of all previous rolls). (Perhaps the weights ...
0 votes
0 answers
12 views

Resample the training data before or after train a baseline model?

I'm working on an unbalanced dataset with three classes. The original proportions are: class 1: 48% class 2: 37% class 3: 15% First I'm gonna train a baseline model and I would like to know if I ...
1 vote
0 answers
23 views

Do you need to normalize labels for models other than neural nets?

As mentioned here, normalizing the target variable often helps a neural network converge faster. Does it help in convergence, or is there otherwise a reason to use it, for any type of model other than ...
0 votes
1 answer
29 views

Statistically comparing real-world data and predictions

I don't often engage in statistics, so please excuse incorrect terminology or if I've missed something obvious. Our team is working on animal morphological data. In summary, we have collected a bunch ...
1 vote
1 answer
44 views

Comparing a predictive model against a hypothetical model of random predictions

Suppose there are three apples, two oranges, and one pear in a bag. I put my hand in a bag, and based on my tactile sense, I guessed what fruit I will grab out of the bag. My fruit predictions are the ...
  • 21
2 votes
1 answer
24 views

Inference of Gradient Boosting on test istance

According to my professor, Gradient Boosting can be done using the following algorithm: Now, I do not really understand the inference part of that algorithm. Why cannot we not simply return $F^{(K)}(...
  • 321
2 votes
2 answers
75 views

Forecasting revenue - what and how to pass input

I have a dataset with quarter wise revenue for past 3 years from Jan 2020 to Dec 2022. I have 4642 customers. Each customer has 1 row of data which includes features based on his purchase frequency, ...
  • 2,290
0 votes
0 answers
24 views

Comparing AUC-PR between groups with different baselines

So I know that the area under the precision-recall curve is often a more useful metric than AUROC when dealing with highly imbalanced datasets. However, while AUROC can easily be used to compare ...
  • 1,751
0 votes
0 answers
19 views

LSTMs: How to deal with the hidden state when predicting

I am trying to understand more about rnn's, more specific LSTM's. I am uncertain about some aspects. Let's consider the following example: We have a time-series with 100 elements. We use the first 70 ...
  • 635
1 vote
0 answers
17 views

Strategies for generating pairwise ranking requests - efficeintly generating the best model inputs for Bradley–Terry model or Plackett-Luce

I'm using the python library choix, which is great for converting pairwise comparisons (or a few other subset ranking metrics, top-1 of n and ranked subset) into ...
  • 111
0 votes
0 answers
10 views

Segregate/Decompose a prediction for a time period into smaller sub-periods

I have a dataset of Electric vehicle demand every 5 mins at every station in a cluster. However, this data is sparse so I cannot train a model and extract the underlying patterns. Therefore, I do some ...
0 votes
0 answers
21 views

"Opposite" of chi-square test of goodness of fit (akin to a linear regression between predicted and observed values)

Suppose I have observed count data $x_1,...,x_k$. I have a hypothesis that this data was drawn from a multinomial distribution (derived from theory) with event probabilities $p_1,...,p_k$. It is ...
0 votes
0 answers
21 views

Can I use a model for predicting if the variables aren't linear?

I made a Linear Regression model that predicts better than my Lasso Regression & Random Forest The linear regression model does not follow the assumptions (linearity) Can I still use it for ...
  • 391
2 votes
0 answers
24 views

How to predict price with dummy variables ARIMAX in R?

Can anyone help? I want to predict a price variable using five dummy variables. Data conditions: contains an up-trend component not stationary I'm confused about whether to split the data or not. It'...
  • 21
0 votes
0 answers
11 views

Using Large Area Data (County) to Predict Small Area Estimand (Census Tract)

I have a health dataset that has a county-level average of interest and auxiliary patients' characteristics (ACS) at the census tract level. I want to use county-level data to predict the parameter of ...
0 votes
0 answers
10 views

Calibration plot in an external validation of predictive model requirements

Dear Cross Validated members., We are working on a multicenter prospective cohort study investigating the predictive accuracy of a sepsis score (qSOFA) to predict 30-days in-hospital mortality using ...
2 votes
1 answer
42 views

How can I use a time series consisting of both Mean and SE to obtain predictions with Mean and SE

This is a slightly modified version of a programming question that I asked in that forum and was redirected here to get a better sense of the statistics involved. https://stackoverflow.com/questions/...
1 vote
0 answers
11 views

Predicting value from multiple independent variables

I have 3 independent variables (eg - weight, height) and want to predict the change in another parameter (dose) with the change in the independent variables. The data is collected from patients who ...
  • 11
2 votes
0 answers
48 views

How should I impute a 100% missing element of a composite variable?

I want to model the variable $Y$ (score 1 to 10) that is a composite of 5 ordinal variables $Y_{a:e}$ with the same levels (0 = "not at all", 1 = "a little bit", 2="a lot"...
1 vote
1 answer
53 views

Relationship between entropy and predictability

The entropy of a random variable $X$ is defined as $\mathbb{E}(-\log(f(X)))$ (where $f$ is the pdf of X, https://en.wikipedia.org/wiki/Entropy_(information_theory)). Is there any general relationship ...
  • 385
2 votes
1 answer
36 views

Probability Calibration, what causes simple linear models like logistic regression to be over-confident and diverge from the true class probabilities?

I've recently studied probability calibration and have investigated many examples and revisited old models of mine to find that they are all poorly calibrated. The idea of stacking also has been cast ...
  • 270
0 votes
0 answers
7 views

How to use this fitted model to predict the annual flood data in the future year? Like in the 2030?

In this paper: https://sci-hub.se/https://doi.org/10.1080/02664763.2021.1940109, if we have the following dataset: in page 18, Section 6 Application: The second real data have 59 observations showing ...
  • 419
1 vote
1 answer
47 views

How to convert daily total rain, recorded at daily intervals, to daily average rain?

I am seeking some assistance in how to take into account difference in trials periods when calculating average rainfall. I am investigating the effect of rain on plant disease severity. My trials have ...
  • 129
0 votes
0 answers
4 views

Are we allowed to average posterior predictive distribution to generate better prediction

Typically for point predictors from different models, we could figure out ways of averaging them to generate better prediction. Now what if we could generate posterior predictive distributions for a ...
  • 21
0 votes
1 answer
34 views

Support vector regression prediction: issue with the output

I want to apply support vector regression (SVR) model parameters to a higher spatial scale using the predict function, but the results are wrong. Here is how the ...
  • 111
0 votes
0 answers
42 views

How to handle a column with both float and categorical values

This sounds like a question that should have come up before but I couldn't find it on CV. I am trying to use a column called limit_price as in the limit price of an order for a machine learning ...
1 vote
0 answers
22 views

How can I determine the likelihood that a visitor will visit again?

The Question I am currently working on an analysis of my company's customers and their visiting patterns. In particular, one question that has come up is: Given that a visitor has visited ...
  • 111
0 votes
0 answers
5 views

Is it correct to generate similar rows by reducing the time-frame of an instance?

I'm participating in a People Analytics project with a small historic dataset that includes event variables. The aim is to predict employee's attrition. I have variables like area, dept., company, etc....
  • 1

1
2 3 4 5
60