Validation is the process of assessing whether the results of an analysis are likely to hold outside of the original research setting. DO NOT use this tag for discussing `validity` of a measurement or instrument -- such as that it measures what it purports to.

learn more… | top users | synonyms

0
votes
0answers
13 views

What would be simple way of calculating the area of a 3D PieChart's slices?

I have created a 3D Pie Chart able to be rotated. -> http://plnkr.co/edit/QIYu8sJUWPmxcby1ky9l?p=preview I did it to demonstrate how the visual perception of data in a Pie Chart can be distorted ...
0
votes
0answers
7 views

Method validation in non-regression problems

Assume I have a sample of r species/classes that follow a multinomial distribution, where the vast majority of classes only are observed once. Further, let us say I have k models that all are giving ...
0
votes
2answers
112 views

highly sporadic validation error during training with multilayer perceptron

I'm encountering an issue where a classifier I'm developing reports validation errors during training that span a wide range of values without consistently decreasing over time. Unfortunately, I'm new ...
3
votes
1answer
43 views

What is the difference between sensitivity analysis and model validation?

I read both wikipedia pages of sensitivity analysis and model validation (here, only linear regression validation) but I don't manage to find a way to separate these two terms. I have the impression ...
3
votes
1answer
216 views

Validation of a questionnaire in a new population

I have 400 responses to a 20 item questionnaire which purports to measure an attitudinal constuct in medical students. The instrument was validated in the US for a single year of medical students and ...
6
votes
1answer
554 views

Internal validation via bootstrap: What ROC curve to present?

I am using the bootstrap approach for internal validation of a multivariate model built with either standard logistic regression OR elastic net. The procedure I use is as follows: 1) build model ...
10
votes
3answers
1k views

Why isn't the holdout method (splitting data into training and testing) used in classical statistics?

In my classroom exposure to data mining, the holdout method was introduced as a way of assessing model performance. However, when I took my first class on linear models, this was not introduced as a ...
3
votes
1answer
199 views

Minimal number of samples/conversions for statistical validity

We are measuring conversion rates (% of visitors who bought) on an e-commerce site. The test apply to a segment of visitors who meet specific criteria (for example people from a certain country). ...
0
votes
0answers
17 views

Real-time accounting input valdiation

I'm currently fishing in troubled waters, as I've got a huge scope. I'm sorry in case this question had been asked already in before, however I couldn't find even a topic to look for with my small ...
0
votes
0answers
9 views

Sensitivity analysis for data validation

I have a dataset, which I believe contains errors. Basically my dataset contains recorded time intervals (in seconds) of visits to a certain place, that due to sensor oversensitivy have been ...
0
votes
0answers
16 views

What kind of bias am I introducing when I include Validation set (kept for model selection) in Train data?

As usual, I have three sets of data: Train, Validation and Test. So I use train data for model selection, where I select the model which would perform best on validation data. After selecting the best ...
0
votes
1answer
14 views

Evaluating a clustering against multilabels

I have a clustering of text documents, where each document is uniquely assigned to a cluster. I have a set of labels (keywords) attached to each document. That is, each label may be applied to many ...
5
votes
1answer
759 views

Within-group sum of squares of cluster

I have a multivariate dataset for which I have only a table including the cross-wise Euclidean distances between all points and a list giving the assignment of each point to one of several clusters. ...
0
votes
0answers
27 views

When is preferred the relative and stability-based cluster validation?

I need to validate a clustering algorithm result. I know that Cluster Validation is commonly divided into four categories: internal, external, relative and Stability-based criteria, where internal and ...
0
votes
0answers
19 views

Standard errors and confidence interval in cox regression model validation using RMS package

I am using RMS package of R to validate cox regression model with bootstrap. Please see the sample code below. I have three questions: (1) How do I request the standard errors and/or confidence ...
112
votes
9answers
93k views

What is the difference between test set and validation set?

I found this confusing when I use the neural network toolbox in Matlab. It divided the raw data set into three parts: training set validation set test set I notice in many training or learning ...
5
votes
1answer
442 views

Prediction evaluation metric for panel/longitudinal data

I would like to evaluate several different models that provide predictions of behavior at a monthly level. The data is balanced, and $n=$100,000 and $T=$12. The outcome is attending a concert in a ...
3
votes
1answer
57 views

Where can I find tests that validate the output of popular statistical software? (e.g. R, SPSS, SAS)

This has been difficult to search on Google. I've looked on R's website as well. I assume there are test suites that validate that R, SPSS, SAS, et al are giving the right output for a given analysis? ...
0
votes
1answer
29 views

Can I validate results after statistical hypothesis testing?

I have data from one clinical test for 450 patients. Depending upon my objective, I divided data into 7 different categories to compare two groups, in each category (inherited from parents and not ...
0
votes
0answers
29 views

Comparing two distributions (simulation vs. measurement) for describing model performance

On the one hand we use a complex mathematical model to determine the result of a process. The model will iterate e.g. 2000 times, each time using random samples for some unknown input parameters ...
0
votes
0answers
3 views

sampling size for binary group estimation (under randomized validation)?

Having binary groups with n members (size of several thousand or more members which can have 0 to ...
8
votes
2answers
324 views

Should final (production ready) model be trained on complete data or just on training set?

Suppose I trained several models on training set, choose best one using cross validation set and measured performance on test set. So now I have one final best model. Should I retrain it on my all ...
1
vote
0answers
19 views

What does this evaluation function mean?

I am solving a prediction problem where I am supposed to predict the number of clicks, given some historical Data. I am told that my predictions will be evaluated by a normalized weighted mean square ...
0
votes
0answers
17 views

What test can I use for Model Validation?

I ran the BTYD package in R which predicts the number of transactions that a customer is expected to make in the future.These expected values that I get are not integers but are in the form 0.14, ...
0
votes
0answers
17 views

Inproper model validation

Let us say that I have a data set D that contians N objects from K different species, words for example, where most of them occur one time. Now my advisor want's me to draw random samples with size ...
4
votes
1answer
120 views

ML / train-test-validate: What is allowed when?

As someone getting started in machine learning, I am trying to get my head around the rules / good practices to follow when building, testing and validating supervised ML models in order not to ...
0
votes
0answers
46 views

What are the reasons why a classifier could produce bad results?

I know of four possible reasons: overfitting underfitting input data doesn't represent the problem (which I guess is underfitting) classifier isn't suitable (e.g. problem is not linear) Are there ...
0
votes
1answer
59 views

How to pick the best model with cross validation?

Based on my understanding the leave one out cross validation is to hold a sample out as the test set and fit a model with remaining data and then calculate the error of prediction of the test sample ...
4
votes
0answers
946 views

Hold out sample vs. cross validation for time series, and how to perform in R

I think out-of-sample validation testing for accuracy is essential in initially judging what time-series forecasts to use. In any case, I've been doing some reading on the two most common methods, ...
1
vote
1answer
40 views

What test shall I use to validate the use of a certain score to predict my outcome in a survival analysis?

I validate usage of a clinical cardiovascular score to predict the risk of dementia using data from a longitudinal study. Therefore, my outcome is binary (dementia yes or not) and the independent ...
0
votes
0answers
29 views

Which statistical test is preferred when comparing two predictive models?

Say, I have two predictive models A and B and recorded AUC (Area under curve) by running both the models on 20 different data sets. Now, if I want to find the best model out of these two for these ...
0
votes
0answers
22 views

Large condition number, but no effect on validation

My question is in regards to the relation between the condition number (or other multicollinearity diagnostics) and validation of a linear regression (lm in R). Specifically, I have extremely high ...
2
votes
1answer
446 views

Optimism bias - estimates of prediction error

The book Elements of Statistical Learning (available in PDF online) discusses the optimisim bias (7.21, page 229). It states that the optimism bias is the difference between the training error and the ...
0
votes
0answers
5 views

How to model the behavior of Webservice and doing validation?

The goal is to find a smart way to validate the behavior of webservice such as CMS (wordpress, joomla). To give more detail, we want to be able based on observing host metrics ( cpu utilization,... ) ...
1
vote
0answers
22 views

Bootstrap within bootstrap?

I want to use .632 bootstrapping to validate an algorithm. The problem is that the algorithm itself also has bootstrapping procedures. Will that cause bias? Since bootstrapping with replacement will ...
14
votes
5answers
11k views

How to calculate Area Under the Curve (AUC), or the c-statistic, by hand

I am interested in calculating area under the curve (AUC), or the c-statistic, by hand for a binary logistic regression model. For example, in the validation dataset, I have the true value for the ...
2
votes
0answers
45 views

What should I do when logistic regression model doesn't perform well on test sample?

For logistic model, I divided dataset into two parts training sample (70% of 360 data point (observation)) and test sample (rest 30% of 360) randomly. After that I built logistic model on training ...
0
votes
1answer
42 views

Measures for Clustering Validations [duplicate]

I have unlabeled dataset and I'm using the hierarchical clustering to generate a groups from this data. I had a look to the lit and I found that there are two approaches to evaluate the clustering ...
1
vote
1answer
25 views

which paper(s) to cite when stating that out-of-sample validation is better than in-sample val

Validating a model (meaning, computing metrics on the prediction) using the training samples is, well, rubbish. Out-of sample validation should be preferred. This is well known by statisticians and ...
1
vote
0answers
14 views

The burden for verification/validation data

I seek a rigorous or otherwise proof for the need of verification/validation data. Typically it is suggested, after building a model, to do any validation of the model's health on a set of data that ...
0
votes
0answers
52 views

Validation Questionnaire Sample or format

I want to know on how to make a validation questionnaire for my research paper but I have no idea on how to create one. I searched about validation questionnaire but there's no format or example - ...
2
votes
2answers
74 views

The role of validation in estimation and hypothesis testing

Validation, with or without statistical/machine learning procedures, is used often, if not universally, in prediction. In estimation or hypothesis testing that does not seem to be the case, yet I ...
3
votes
4answers
7k views

What is the meaning of orthogonal in validation testing?

I have heard the term "orthogonal * validation" used recently. It was used in the context of experimental platform testing. What does this mean? I cannot find anything on it in literature or ...
0
votes
0answers
43 views

Calibration curve confidence intervals interpretation. Is to reduce a high Bias Corrected possible in Bootstrapping?

I have been working on a mixed generalized model, glmer, and now I am trying to validate it by a calibrate curve, and also would like generate its CIs. For this, I thought in Bootstraping and found ...
0
votes
0answers
18 views

Using one model to validate another? (Validation with no ground truth?)

My question is on model validation when there is no ground truth. Suppose I have a data set of attributes: $x = \{x_1,\ldots, x_n\}$ These attributes are different attributes that describe animals ...
2
votes
2answers
54 views

Double (nested,wrapper) CrossValidation - final trained model

I'm performing a study where I'm selecting kernel type and hyperparameters in an inner CV loop and an outer loop doing 10-fold CV (using SVR). The output is 10 trained models and performance measures. ...
0
votes
0answers
31 views

Avoiding over/under fitting & validation set size

I'm using a PLS model associated to FT-NIR spectroscopy to predict some properties of biodiesel. At the moment, I'm trying to optimize the number of factors I should use to do the calculations. ...
0
votes
0answers
69 views

SOM Validation method

I made a project using Self Organizing Map (SOM) for clustering multi dimensions data in R. But I have difficulty to find what method that I can use to: validate the clustering result based on data ...
0
votes
0answers
12 views

How to account for drift in system identification output?

I am trying to identify the lateral dynamics of a vehicle. I use steering angle as input, and lateral displacement, lateral velocity and yaw rate as output. I use idss method of MATLAB. The issue ...
1
vote
1answer
51 views

What are the assumptions to test on unseen data to use a predictive model?

I am trying to understand what are the assumptions I have to test, to use a predictive model on unseen data. After the validation phase of my predictive model and the estimation of its accuracy on a ...