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

79
votes
7answers
63k 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 ...
29
votes
2answers
3k views

How to draw valid conclusions from “big data”?

"Big data" is everywhere in the media. Everybody says that "big data" is the big thing for 2012, e.g. KDNuggets poll on hot topics for 2012. However, I have deep concerns here. With big data, ...
22
votes
4answers
605 views

As a reviewer, can I justify requesting data and code be made available even if the journal does not?

As science must be reproducible, by definition, there is increasing recognition that data and code are an essential component of the reproduciblity, as discussed by the Yale Roundtable for data and ...
11
votes
1answer
121 views

When building a regression model using separate modeling/validation sets, is it appropriate to “recirculate” the validation data?

Suppose I've got an 80/20 split between modeling/validation observations. I've fit a model to the modeling data set, and I'm comfortable with the error that I'm seeing on the validation data set. ...
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 ...
10
votes
2answers
3k views

What is the procedure for “bootstrap validation” (a.k.a. “resampling cross-validation”)?

"Bootstrap validation"/"resampling cross-validation" is new to me, but was discussed by the answer to this question. I gather it involves 2 types of data: the real data and simulated data, where a ...
8
votes
3answers
3k views

What is a consistency check?

I was asked such a question as "Did you do any consistency check in your daily work?" during a phone interview for a Biostatistician position. I don't know what to answer. Any information is ...
8
votes
2answers
823 views

What is the intuition behind the variation of information (VI) metric for cluster validation?

For non-statisticians like me, it is very difficult to capture the idea of VI metric (variation of information) even after reading the relevant paper by Marina ...
7
votes
5answers
3k 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 ...
7
votes
2answers
142 views

How to make sure that a machine learning algorithm's implementation is correct?

Say there is a machine learning algorithm (e.g. classification) that is well known and implemented by the original creators of the algorithm. Yet all you have is the ability to use the algorithm but ...
6
votes
4answers
333 views

How bad is hyperparameter tuning outside cross-validation?

I know that performing hyperparameter tuning outside of cross-validation can lead to biased-high estimates of external validity, because the dataset that you use to measure performance is the same one ...
6
votes
1answer
2k views

Best practices for measuring and avoiding overfitting?

I am developing automated trading systems for the stock market. The big challenge has been overfitting. Can your recommend some resources describing methods for measuring and avoiding overfitting? I ...
5
votes
1answer
370 views

Name of mean absolute error analogue to Brier score?

Yesterday's question Determine accuracy of model which estimates probability of event got me curious about probability scoring. The Brier score $$\frac{1}{N}\sum\limits _{i=1}^{N}(prediction_i - ...
5
votes
2answers
142 views

How to validate if a sample is independent and identically distributed

How can I check if the data is drawn i.i.d. from an unknown multivariate distribution?
5
votes
1answer
121 views

What do you do with your testing data?

Suppose you perform a parameter selection study in an environment with not-so-many data points. You divide the available data into training and testing set and you plan to validate the future model on ...
5
votes
2answers
8k views

How to make representative sample set from a large overall dataset?

What are the statistical techniques to create a sample set, which is representative of the entire population (with a known confidence level)? Also, How to validate, if the sample fits the overall ...
5
votes
2answers
463 views

How to do external validation of logistic regression models and perform model benchmarking

Quality assessment in trauma has for > 25 years been done with the US derived logistic regression model, the TRISS model. DV: survival/death and IVs: physiologic derangement (continuous), anatomic ...
5
votes
2answers
1k views

Validate cluster analysis in R

I am trying to validate hierarchical cluster analysis result following a paper by Guy Brock, et al. clValid: An R Package for Cluster Validation (pdf). Do I have to use all these methods? What are the ...
5
votes
1answer
134 views

Validating a logistic regression for a specific $x$

I have a logistic regression model for 0/1 binary response data that is built from samples $(x_1,Y_1),\dots,(x_m,Y_m)$, where $x_1,\dots,x_m$ are, fixed, nonrandom, real values and $Y_1,\dots,Y_m$ are ...
5
votes
1answer
214 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. ...
5
votes
0answers
436 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 ...
4
votes
2answers
592 views

In logistic regression, does the lack of significance of the parameter estimates in a test sample indicate overfitting?

I am trying to build a logistic regression model where I have a dependent variable $y$ and independent variables $x_1$, $x_2$... $x_n$. $y$ can take only two values - 0 or 1. My original modelling ...
4
votes
1answer
1k views

Using Adaboost for feature selection?

Is it okay to use Adaboost to do feature selection (selecting a subset of dimensions $S$ from a high-dimensional feature vector $V$)? I divided the samples into four non-overlapping sets: $A$ ...
4
votes
1answer
577 views

Best method to validate a multiply imputed Cox model with R?

This question is with regards to using a test data set to validate an imputed Cox model using R. With a non-imputed data set I would use val.surv() from ...
4
votes
2answers
1k views

Variance explained of a mixed effects model in a new data set

I'm using the following function to calculate Edwards R^2 (formula 19 in Edwards et al. 2008) of a mixed effects model (I hope the implementation is correct): ...
4
votes
1answer
2k views

Diagnostic plots for lmer

I am trying to produce a glmm using the lme4 package in R. To validate my model I would like to produce some diagnostic plots ...
4
votes
1answer
461 views

Compare modeled (fitted) paired data to actual data in forecasting problem (Excel sheet included)

In my endeavor to learn forecasting and improve my statistical knowledge, I've decided to forecast the population of a certain area. I've attached the excel file that I used. I know I'm using excel ...
4
votes
0answers
144 views

Are world cup predictions testable?

As of today, dozens of soccer world cup predictions exist, some more complex, some more elegant, and most of them predict every nation's "chance" of winning a particular match/ the cup. As I am ...
3
votes
2answers
977 views

How exactly to partition training-set for k-fold cross validation on multi-class dataset?

Cross validation is one of the most important tools because it gives us an honest assessment of the true accuracy of our system. In other words, the cross-validation process provides a much more ...
3
votes
2answers
2k views

How do I validate my multiple linear regression model?

I have split my data into two parts. I have used my 80% data to build a multiple regression linear model. Now I want to test it using my rest 20% data. What tools on Minitab do I have to make this ...
3
votes
1answer
383 views

Determining values of correction factor based on x bins in observed vs. actual data

I am trying to automate a problem I usually solve by hand. I have a sensor that collects data from the field. Every 6 months or so, I have to do a calibration on that sensor by collecting ...
3
votes
1answer
3k views

Model validation after fitting a negative binomial GLM in R

Ok, I have searched and searched and just have no clue where to start. First, what I would like to do is produce a QQ-plot (or even a readable residual plot) to look at the fit of my model. I guess ...
3
votes
2answers
514 views

Logistic regression performs better on validation data

Recently I've been building a model using logistic regression. To my suprisise LIFT chart looks better on the validation data than on the training data, the same is with ROC. All variables in the ...
3
votes
1answer
72 views

Does the position at which maximum distance occurs in a KS test make a difference?

From my understanding of the KS test, fromt the CDF of two datasets, it measures the distance between the two distributions at various points and and compares the 'maximum distance' to a predefined ...
3
votes
1answer
175 views

What does a negative Somers' D say about model discriminative power?

I developed a Cox proportional hazard regression model in R. Then I tried using validate in Professor Harrell's rms package to ...
3
votes
2answers
1k views

Validity of pseudo-panel data constructed from repeated cross sectional data as a panel data

I am looking at the repeated cross-sectional data from federal reserves, which has both panel data and repeated cross sectional data at different time-points,e.g. 2007-2009 is a panel while 2010 is a ...
3
votes
4answers
6k 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 ...
3
votes
2answers
1k views

What are acceptable validation or cross validation error rates?

Is there a commonly acceptable error rate for validation? As in, if the error rate is less than X %, then my machine learning method would be considered "successful". I'm looking for something ...
3
votes
1answer
834 views

How to choose training and test sets

I would like to propose a single model (decision tree), that is very variable, and validate it. I have choosen parameters after I had obtained good quality measures with a cross-validation. I could ...
3
votes
2answers
319 views

How to do external validation of regression models

Very basic question here, so bear with me... I have a data set with 241 patients with 16 variables plus diagnosis (malignant vs benign). There are 3 previously published logistic regression formulas ...
3
votes
1answer
60 views

Mixing User Data For Cross-Validation

I have data from 12 users, and want to perform cross-validation. Is it necessary that I create my training and test data from different users, or can all of the data be randomized, and then split into ...
3
votes
1answer
162 views

External model validation using new data for prediction: How large of a drop in $R^2$ is significant?

I need to validate a model using `external model validation' and I have a question relating to deciding when a drop in $R^2$ when compared to $R_{prediction}^2$ is significant. DISCLOSURE: This is ...
3
votes
1answer
165 views

Should my test set be balanced or imbalanced?

I have an imbalanced dataset (90% class 0 10% class 1), should I first split it in training and test set, then balance my training set (my test set would still be imbalanced), or could I randomly ...
3
votes
1answer
152 views

Cross-validation for Comparing Clustering Techniques

I'm working on comparing multiple clustering algorithms to each other using the adjusted Rand index for a given dataset. We have a gold standard that we'd like to compare the obtained clustering ...
3
votes
1answer
144 views

Statistical measures for data validation

I have to validate the data in one database by comparing it to data from a validated application system. The solution I came up with was (at least in theory) creating a statistical method that would ...
3
votes
1answer
251 views

Validation of a scale for a different population (CFA)

I'm currently adapting a coping questionnaire which has been widely used in sports to be used with a different population (musicians), so I need to address its reliability and validity with this new ...
3
votes
1answer
246 views

What resources/methods exist for testing/validation or evaluation of Statistical Methods

I'm interested in the process of testing or validating a particular implementation of a statistical method, and what datasets and/or published analysis exist that could be used to do this in practice. ...
3
votes
1answer
569 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, ...
3
votes
0answers
133 views

Validating statistical tests for value at risk and expected shortfall

I am trying to figure out if value-at-risk (VaR, a quantile) type tests could capture if expected shortfall (expectations above a quantile) point forecast generated from a type of model could be ...
3
votes
1answer
184 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 ...