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
5 votes
2 answers
417 views

Why does the normality assumption not affect Linear Regression in large samples?

I've read once that the normality assumption shouldn't be a problem and that you actually shouldn't care that much if your sample is large. Why is that? Can someone give me a mathematical explanation? ...
dsbr__0's user avatar
  • 797
0 votes
0 answers
13 views

How to Evaluate a Single-Value Prediction for a 6-Month Period Against Historical Data?

I'm tackling a time-series forecasting issue with daily granularity, aiming to predict a single aggregate value that represents the total sum of incidents over a 6-month period. My approach involves ...
Amit S's user avatar
  • 37
0 votes
0 answers
36 views

Application of mixed-effects model for unbalanced sample size and repeated measures

In my experimental design I have 4 treatments, 3 replicates per treatment and 3 blocks. In each plot I measured whether a plant is infested or not ("Infestate" variable). This measure has ...
GiorgioS's user avatar
2 votes
1 answer
68 views

models MIMIC, predicted probabilities?

I am investigating MIMIC (Multiple Indicators Multiple Causes) models since with them I can do regressions, including factors (made up of several items), and the observed variables (glycemia, ...
Fernando VAzquez's user avatar
0 votes
0 answers
5 views

Statitical comparison of regression prediction to sample of data

I have a dataset, let's call it data1(x,y), where the data y is measured at 16 values of x. I use this dataset to fit to a 3-parameter model. I can obtain estimates for the three model coefficents ...
Davide's user avatar
  • 1
0 votes
1 answer
31 views

non-significant p value in a multivariable cox regression following exhaustive model selection

I run an exhaustive model selection for Cox proportional hazard in R using "glmulti" package. I used the best model for creating multivariable Cox regression. In the multivariable Cox hazard,...
Ahmed Elkoumi's user avatar
0 votes
0 answers
9 views

Removing observations with missing target values in the test set

I'm building my first predictive model and seem to be having a fundamental confusion about missing target values. I'm predicting treatment outcome (with both regression and classification methods for ...
olke's user avatar
  • 115
1 vote
1 answer
50 views

What metric should I use for a Regression model with a gamma distributed target?

Background I'm building a regression model on insurance data to predict the losses associated with a policy. I'm running an Optuna optimisation function to help me with this, but I'm struggling with ...
Connor's user avatar
  • 595
3 votes
0 answers
177 views

Recreating data variance from the posterior distribution

Recreating data variance from the posterior distribution Take a set of data points $(x, y)$ with (Gaussian) uncertainties $\sigma_y$ on the $y$ coordinate; they are modeled as $y \sim f(x; \alpha) + \...
Jacopo Tissino's user avatar
0 votes
0 answers
35 views

Log transformation uses

I am trying to understand how the migration of a male member affects the number of hours spent by left-behind women in various agricultural and non-agricultural activities. I used a simple OLS model ...
Sapna's user avatar
  • 1
0 votes
0 answers
28 views

Daily monitoring of churn prediction model

I've written and trained a churn model that is scheduled to run every day and make new predictions for the probability of each customer to churn within coming 365 days, from the day the scoring is ...
Parseval's user avatar
  • 361
2 votes
1 answer
41 views

R=X*Y is the relationship. Is predicting R and X and obtain Y same as predicting X and Y to obtain R?

Of course the numbers will be different, I mean more in terms of relationship. I know that X affect R and Y affects R . X and Y are independent but since R is a product of X and Y , I dont think that ...
MSKO's user avatar
  • 61
0 votes
0 answers
20 views

Should I indicate "success" of an experimental run at the beginning of the data?

Because I'm that guy, I wanted to run some statistical analysis on the results of a number of experiments; specifically, I'm wanting to track my progress on different runs of the turn-based strategy ...
John Doe's user avatar
0 votes
0 answers
25 views

Recommender System for continuous predictors

I want to build a model that is able to predict the outcome of a user-client interaction. I know that for categorical variables Factorization Machines are a good choice. Imagine for example we are ...
Mirko's user avatar
  • 133
2 votes
0 answers
35 views

Error metric for regression of count data: Poisson Deviance or Mean Square Error?

I would like to understand what difference it makes, if I use, for example, either Mean Square Error or Poisson Deviance as error metric/loss function for a regression of count data. Are there any a-...
g g's user avatar
  • 2,421
1 vote
0 answers
27 views

Assessing surrogacy for 2 treatment effects

I'm interested in analyzing whether an intervention's effect on an outcome, X, qualifies as a surrogate for its effect on another outcome, Y. By the end of the analysis, I would like to have: A) An ...
Ahmed Sayed's user avatar
1 vote
0 answers
29 views

Root Mean Square Log Error (RMSLE) Interpretation

I would like to clarify my understanding of Root Mean Log Squared Error (RMSLE): $$\text{RMSLE}=\sqrt{\frac{1}{n}\sum_{i=1}^{n}\left [\ln \left ( \frac{y_{i}+1}{\hat{y_{i}}+1} \right ) \right ]^{2}}$$...
ta1992's user avatar
  • 11
0 votes
0 answers
21 views

How to construct confidence intervals for difference of means in logs

I have estimated an OLS model and a Negative binomial model of ln housing search (ln S) per unit (for instance, the average number of visitors per house or bidders per house) as a function of ...
Mari Mamre's user avatar
2 votes
0 answers
62 views

Why is the noise included in the posterior predictive distribution in bayesian regression?

Assume the following model: $y = b_0 + b_1 * x$ where we set some priors to $b_0, b_1$. Let $I$ denote our historical data and $x^*$ denote future inputs. Let $p(b_0, b_1|I)$ denote our posteriors. We ...
karl henriksson's user avatar
2 votes
0 answers
41 views

use random forests for prediction

I am working on a project to determine the variables that better predict the binary outcome. I am using conditional random forest and permimp::permimp to assess the ...
Kate's user avatar
  • 93
1 vote
0 answers
26 views

Prediction Interval Construction

At my organization, we use a deterministic formula mid-month to predict an end-of-month value. We have some data on the historical performance of this prediction. We know the value of the average ...
Dan's user avatar
  • 63
0 votes
1 answer
30 views

Make Predictions with an RNN Using a Multi-dimensional Training Set

I have a 2D matrix TD of training data that is a collection of N non-linear signals that are functions of time (hence the ...
Jonathan Frutschy's user avatar
0 votes
1 answer
23 views

Is there a way to predict multiple columns of NA values in a dataset using R? [closed]

I have a data set that has 9 different variables, but 3 of the variables aren't complete. I'd like to find a way to use a prediction model to fill in those variables, but was wondering if there was a ...
Lt78's user avatar
  • 1
0 votes
1 answer
48 views

Can/should probability estimates be calculated on the whole dataset and not just on the test set?

For a binary classification problem on a dataset X, divided in train and test sets (or train, validation, test if performing parameter tuning), one can get probability estimates by fitting the model ...
MarcoC's user avatar
  • 3
2 votes
0 answers
63 views

Which dependent variable is mostly impacted by predictor?

Usually one wants to identify the most important predictors (x1, x2, x3..., xn) in a regression model. My question is reversed: I have a data set that contains a risk factor risk and several outcomes ...
a.henrietty's user avatar
1 vote
1 answer
40 views

Is it okay to make predictions without using all regressors? [closed]

Currently, I am looking at a time series model (linear regression) that has 5 independent variables. The owner of the model says only 3 regressors are fed with input and predictions are made using ...
Larx's user avatar
  • 47
0 votes
0 answers
17 views

Regression of a binary vector from another binary vector in Keras

I am trying to work on building a relationship in Keras, between X and Y where X= (1,30) and ...
stevGates's user avatar
  • 111
0 votes
0 answers
19 views

predicting using only certain terms in a mixed-model regression via lmer or glmer via predict()

When using lm() or glm(), the predict.lm() or predict.glm() functions allow one to obtain predictions from the model using only a subset of the predictor variables, while setting the coefficients of ...
Bill Shipley's user avatar
0 votes
1 answer
24 views

What is F1 Score for this diagram?

I have this Venn chart that represent a dataset prediction of Identifying if our products are classified as "A41" standard or not The Blue Circle represents a Machine Learning Model ...
asmgx's user avatar
  • 291
0 votes
0 answers
12 views

Choose the best model

I'm doing leave one out validation (I take a pair, that include each class) for my data set, the problem is binary clasify for spectres, using NN, on train i get 85% accuracy, even in the class with ...
POCH05's user avatar
  • 11
2 votes
1 answer
40 views

One extreme outlier fitted value that is replaced by another when dropped

I have an OLS model with a very bad prediction score - when I decided to test for heteroskedasticity, it turned out my model's predictions include one incredibe outlier - it looks like my fitted ...
ErikHansen's user avatar
1 vote
0 answers
23 views

How useful is exchangeability for non-extendible sequences?

Question How to model the predictive distribution $\mathrm{P}(X'\mid X_1=x_1, \dotsc, X_n=x_n)$ if I know that the sequence $X_1, \dotsc, X_n, X'$ is exchangeable, but I cannot assume it to be $N$-...
Paweł Czyż's user avatar
2 votes
1 answer
37 views

When trying to predict if an event will happen in the next $n$ time-steps, is it a bad idea to label backwards in time?

Apologies if the title makes no sense. At work, I came across something that I don’t think is a good idea and I was hoping someone could help me convince my colleagues of that - or convince me that I’...
Maya's user avatar
  • 31
1 vote
1 answer
102 views

inverse.predict for $lmer$ models in R [closed]

In $lm$ models in R it is possible to use inverse.predict for predicting input value given a output value. But I can't find code making it for $lmer$ models. Do there not exists code for that in R?
Lifeni's user avatar
  • 305
0 votes
0 answers
9 views

Challenges with Predictor (regression) Performance: Persistent MAE of 0.26 and Inaccurate Prediction of Binary Vectors

I am trying to work on building an variational autoencoder in Keras, with an input shape of ...
stevGates's user avatar
  • 111
0 votes
0 answers
43 views

Estimating variance by regressing squared residuals

For a linear regression, one way to estimate the range of a prediction for a new observation is to calculate the prediction interval for the new observation. What if, instead, the squared residuals ...
Albeit's user avatar
  • 213
1 vote
1 answer
58 views

ADI and CoV - Move thresholds based on dataset?

I am currently working on demand forecasting. During my research online I came to know about methods used to classify demand which helps us to focus on series which have better forecasting ability etc....
The Great's user avatar
  • 3,232
3 votes
1 answer
72 views

Using Bayes' theorem with given accuracy statistics

A common example to demonstrate the basics Bayes' theorem is that of a drug test or that or a test for a disease. For example, the Wikipedia page for Bayes' Theorem has a example for cannabis testing ...
JimmyJames's user avatar
1 vote
0 answers
19 views

Regression of a binary vector to obtain another binary vector [duplicate]

I am working in the security field. I have a dataset, called X, of binary victors. So the sample is a binary vector, for example sample in X = [1,0,0,0,1,0,....n] ...
stevGates's user avatar
  • 111
1 vote
1 answer
45 views

Which statistical tests should I use for predicting one variable with another one?

I want to investigate the association between the serum glucose level of a patient with type 2 diabetes at the baseline (continuous) and distal neuropathy (categorical), $5$ years after the diagnosis. ...
Erfan Naghavi's user avatar
1 vote
0 answers
130 views

How to reduce number of continuous variables before I make a set of best predictors (for handgrip strength in women)

My assignment question is quoted: "2. Which set of variables best predicts handgrip strength in women? a. Reduce the number of continuous variables before doing the analysis." I do not ...
Nathan Vermaerke's user avatar
0 votes
1 answer
34 views

How can I calculate residuals of a dependent binary variable, using a glm (logistic) model that was fit on a different sample?

I have a data frame D1 in R with a dependent binary variable Response (0/1) and a set of covariates like age and gender. I want to know how "typical" ...
may.the.bee's user avatar
3 votes
2 answers
49 views

How can I assess case-level uncertainty of classification using logistic regression?

I'm hoping to fit a binary logistic regression to be used to predict the binary outcome for new cases/observations. I'm wondering if there is any way to gauge uncertainty of a prediction for ...
VS99's user avatar
  • 31
0 votes
0 answers
17 views

Using OLS regression with time-series data and measuring its uncertainty

Imagine I have two cities situated near each other. People have buying patterns in both cities so similar that the number of a company's sales per day is very closely correlated. My goal is to ...
Антон Бугаев's user avatar
1 vote
1 answer
34 views

MSPE and $R^2_{OOS}$

I've been looking at a paper for a while that I find interesting. It's essentially a comparative analysis where the authors are comparing PCA/PLS to different machine learning methods. The aim is to ...
Nbs610's user avatar
  • 13
2 votes
1 answer
48 views

Analyzing microbiome and clinical data for event-prediction

I am analyzing clinical data and complex microbiome data in a longitudinal study. I already compared different groups at baseline and between baseline and "events" using linear mixed models (...
BHO_1990's user avatar
0 votes
1 answer
47 views

How do I approximate a timeseries with a sum of sin and cos functions?

I have a time series and I am trying to approximate it using an equation of the type: y = A + B*sin(2*pi*x/n) + C*cos(2*pi*x/m) + D*sin(2*pi*x/q) + ... The ...
point618's user avatar
0 votes
1 answer
50 views

Is it possible to predict non-classifiable label using single layer perceptron and sigmoid function? (without using any perceptron library)

Imagine predicting BMI index like 1,2,3,4,5 and having weight and height as input. I know it can be easily done with other method. Also I have to use sigmoid function and I am really new to this. I ...
Lu Phone Maw's user avatar
1 vote
1 answer
44 views

Error of prediction from linear regression in R [closed]

I have an equation: $$ \large y = 0.243x + 0.145 $$ In the form: $$ \Large y = ax + b $$ I use it to predict $y$ when $x = 2$. To estimate the distribution around $\hat{y} = 0.631$ I need an estimate ...
Aaron Simmons's user avatar
1 vote
0 answers
59 views

LightGBM Regressor miscalibratred/underestimating on high fitted values and overestimating on low fitted values

I'm training a pretty standard LightGBM regressor and noticing a strange pattern with the residuals (see images below--I'm bunching the predicted values and taking the observed average for the group). ...
dfried's user avatar
  • 201

1
2 3 4 5
63