Skip to main content

All Questions

70 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
13 votes
0 answers
259 views

Logistic regression for classification: are there any analytical solutions for the out-of-sample accuracy?

I run a binary logistic regression, with a binary dependent variable and a continuous independent one. Now I want to evaluate the out-of-sample performance of the classification algorithm so obtained. ...
robertspierre's user avatar
4 votes
1 answer
2k views

ROC Curve AUC for Hypothesis Testing Sensitivity (Power) vs Specificity ($1-\alpha$)

(I called this a ROC curve when I posted two years ago, but it's really the empirical CDF of the p-values.) Let's set up a hypothesis test of $H_0: \theta=\theta_0$ versus $H_1: \theta\ne\theta_0$, ...
Dave's user avatar
  • 67.1k
4 votes
0 answers
145 views

What is the correct definition of Selectivity : TPR or TNR? Since contradictory literature exists

The reason of my question is because contradictory articles exist. Talking about the confusion matrix's performance metrics, we can find: English wikipedia pages mention that ...
Fed Zee's user avatar
  • 661
3 votes
0 answers
42 views

How to do a sensitivity analysis for a Bayesian Model? Prior or Posterior?

I'm developing a mathematical (SIR-style) model for cholera transmission in the Bengal Delta which is fit to data using MCMC. The purpose of the model is more explanatory rather than predictive, and I ...
Learning_how_to_model's user avatar
3 votes
0 answers
176 views

Assessing correlated predictions

Let's assume we have a prediction algorithm (if it helps, imagine it's using some boosted tree method) that does daily predictions for whether some event will happen to a unit (e.g. a machine that ...
Björn's user avatar
  • 35.2k
3 votes
0 answers
91 views

Diagnostic device hypothesis testing for superiority to a fixed value

I am designing a study to demonstrate that a diagnostic medical device is more sensitive than a fixed performance goal of 70%. Currently I am attempting to determine the appropriate sample size. My ...
jeffalltogether's user avatar
3 votes
1 answer
388 views

The effect of oversampling on the positive predictive value

I need to calculate the positive predictive value for a validation set for a rare event. The problem is that the validation set was oversampled for the rare event. The event occurs in 5 percent of the ...
user43856's user avatar
2 votes
1 answer
118 views

Binary classification metrics - Combining sensitivity and specificity?

The harmonic mean between precision and recall (F1 score) is a common metric to evaluate binary classification. It is useful because it strikes a balance between precision (FP) and recall (FN). For ...
usual me's user avatar
  • 1,257
2 votes
0 answers
487 views

When should one look at sensitivity vs. specificity instead of precision vs. recall?

The precision vs. recall tradeoff is the most common tradeoff evaluated while developing models, but sensitivity vs. specificity addresses a similar issue. When should one of these pairs of metrics be ...
John S's user avatar
  • 145
2 votes
0 answers
276 views

Prevalence threshold calculations error

I see on this page the formula for calculation of prevalence threshold: Given also are following values on that page: ...
rnso's user avatar
  • 10.2k
2 votes
0 answers
2k views

what to do when true positive rate is undefined?

I have a binary classification set with about 900 samples. I first use kfold cross validation and AUC of the ROC curve to determine which classifiers perform best. Once I've done that, I use a leave-...
jerpint's user avatar
  • 133
2 votes
0 answers
273 views

Calculating and reporting accuracy, sensitivity and specificity with multiple raters

I'm conducting a study in which I'm comparing 15 radiologists evaluations on a dichotomous variable to a gold standard, in a sample with 58 patients. Obviously I've calculated overall accuracy, ...
Rasmus Green's user avatar
2 votes
1 answer
41 views

Is this a sensitivity?

There are test A and test B. I want to show a ratio of test A positive among all test positive(test A positive or test B positive). Can I call the ratio as sensitivity? Or is it safe to call as ratio?...
Sumito Okuyama's user avatar
2 votes
0 answers
2k views

How to improve the sensitivity of minority class on imbalanced datasets

I am working on a classifier which stratifies a population of samples into different classes. The class distribution (ground truth) is imbalanced, and the prevalence of each class is: $$\begin{...
gc5's user avatar
  • 1,257
1 vote
0 answers
22 views

Hypergeometric approximation of herd sensitivity and its non-linear nature

I have recently been exploring the use of the equation described in Cannon 2001 paper "Sense and Sensitivity" on herd sensitivity (love the name). I have been looking to test a hypothetical ...
Jamie's user avatar
  • 63
1 vote
0 answers
17 views

Interpreting sobol indices

I am trying to test the sensitivity of my model to a change in the parameters std and translation_factor. I get the following results : Sobol First Order Indices: translation_factor: -1....
Anem Dupré's user avatar
1 vote
1 answer
23 views

Is there an equivalent for Yates' correction for a confusion matrix-derived metrics?

Given the following table of predictions vs. actual states: ...
Bryan's user avatar
  • 1,291
1 vote
0 answers
15 views

Best way to sum up and visualize the relation between results of 2 tests measuring the same outcome with 3 results

I have a dataset of different individuals who underwent 2 test that measure the same outcome with 3 possible results not reduced mildly reduced highly reduced I know that the distribution of the ...
Guddi's user avatar
  • 11
1 vote
0 answers
48 views

Sensitivity and specificity for multiple raters

I am conducting a study where 3 raters assessed performance of two similar test in regards to classify a lesion as malignant vs. benign. I wish to calculate specificity and sensitivity of each test ...
PalpatR's user avatar
  • 11
1 vote
2 answers
89 views

Individual Measurement in Overlapping Distributions

I have a situation where I have measurements taken from samples of healthy and pathological populations. The pathological populations tend to have much higher measurements, but the distributions are ...
DankMasterDan's user avatar
1 vote
1 answer
34 views

How to show that simple random sample sensitivity is unbiased for population sensitivity

In diagnostic testing, sensitivity $S$ is the probability that the test gives a positive result given that you have the condition being tested. From a simple random sample of people who take the test, ...
variancekills's user avatar
1 vote
0 answers
47 views

Multiple observations AUC, Sensitivity and Specificity

I am trying to find a CIs for the AUC, sensitivity and specificity. In my scenario, each observation consistent of a subject and an area examined, that is it is obvious that areas examined for the ...
Kozolovska's user avatar
  • 1,455
1 vote
0 answers
36 views

Estimating the mean and variance for a set of probabilities (bounded by 0 and 1) based on Image Segmentation results

Data My data is from a set of images wherein I am computing the Sensitivity of an image segmentation algorithm. Sensitivity is computed as: $$Sensitivity=\frac{TP_{pixels}}{TP_{pixels}+FN_{pixels}}$$ ...
jeffalltogether's user avatar
1 vote
0 answers
367 views

Why is the optimal cutoff for AUC different from that of specificity in this simulation?

I am working on a binary classification problem on an imbalanced data where the majority class is about 90% 'no' and the minority class is about 10% 'yes' of the total data. Iteration 1: I randomly ...
Stats IT's user avatar
  • 548
1 vote
0 answers
92 views

Sensitivity, Accuracy, AUROC, Gini

I got following chart: The algorithms have been applied to a dataset where an outcome is pretty rare, it happens 10% of the times (binary, 0- 90%, 1-10%). It is the response whether a client is going ...
Romero Azzalini's user avatar
1 vote
0 answers
16 views

Tuning the Logit model based on sensitivity

I am working on a logistic model to predict whether or not an employee is likely to take a leave day during a given three month period. The model only correctly classified the “non-event" ...
user313511's user avatar
1 vote
0 answers
80 views

Take into account Sensitivity and Specificity when calculating Estimates/CI's

I'm trying to thing about how to calculate confidence intervals in the presence of known measurement error for some test protocol. Let's assume we're doing a sample survey in which we're performing ...
Ilya's user avatar
  • 41
1 vote
0 answers
31 views

Population selection for sensitivity and specificity

For medical physical assessment sensitivity and specificity is commonly used to assess the clinical relevance of the test. I'm specifically referring to manual medicine here, with orthopedic tests of ...
Jensei's user avatar
  • 123
1 vote
0 answers
21 views

OneR and area under the ROC curve

In the book Data Mining, author Ian Witten says that it does not make sense to calculate the area under the ROC curve when applying OneR because it finds only one point (sensitivity, specificity) ...
Davide's user avatar
  • 79
1 vote
0 answers
19 views

Sensitivity of a diagnostic test

Diagnostic tests A1 and A2 are used to detect the presence or absence of a disease. The results of A1 and A2 are a priori independent of the presence or absence of the disease. A1 and A2 have ...
Curiouslilac's user avatar
1 vote
0 answers
134 views

Deriving a loss function properly accounting for different error type costs

Consider a classification setting like a medical test: Not finding an existing health issue might be much worse (by a factor of 50) than assuming an issue when there is none. I.e. a setting in which ...
Hauptideal's user avatar
1 vote
0 answers
23 views

Sensitivity and specificity on cases rather than individual days

I have data collected from sensors to detect disease in several individuals. Each individual has a known disease status (labelled Actual in the table below) for ...
JB32's user avatar
  • 11
1 vote
0 answers
584 views

Why are specificity and sensitivity (recall) inversely related?

I remember learning this about medical tests when I studied biochemistry and now I met with this rule again by learning about binary classification and PR-curves. If we check the equations for both ...
inf3rno's user avatar
  • 161
1 vote
0 answers
29 views

Compare cut-offs with respect to sensitivity etc

I have a score and a dichotomous criterion for n observations. Using a ROC-Analysis, I found some optimal cut-off, say c. Now, literature (e.g., author of scale with which the score was determined) ...
Mike Ehrmantraut's user avatar
1 vote
0 answers
1k views

Calculating sensitivity and specificity from survival data

I have a diagnostic test performed on 100 participants at baseline. I then follow up these participants for variable periods of time and have data regarding survival. I have used a Cox regression ...
RobMcC's user avatar
  • 253
1 vote
0 answers
88 views

How to make specificity a stable evaluation metric?

ROC (including AUC) metrics are widely used for binary classification problems. AUC is usually selected to evaluate the model. However, some tasks may require high specificity with fixed sensitivity. ...
user2149631's user avatar
1 vote
0 answers
622 views

Calculating a pooled estimate

I am writing a systematic review on certain imaging studies and I was hoping to add a meta-analysis of the sensitivities of the various modalities reported on. My goal was to put together a forest ...
Ethan's user avatar
  • 11
1 vote
0 answers
77 views

Confidence interpretation from false negative rate

For my research I'm using a tool called seeSUMO, which predicts sumoylation sites in a protein based on sequence features. When it reports your results, it gives you a level of confidence for each ...
Deepgreen's user avatar
0 votes
2 answers
51 views

Is it possible that false-positive rate decreases with increasing prevalence?

I am interested in the effect of prevalence on prediction performance. Chouldechova (2016) states that: [w]hen using a test-fair [recidivism prediction instrument] in populations where recidivism ...
Max J.'s user avatar
  • 113
0 votes
0 answers
22 views

Se, Sp, NPV and PPV questions for repeated measures data

I have a dataset that contains multiple test results (expressed as %) per participant, at various time points post kidney transplant. The dataset also contains the rejection group the participant ...
R. Simian's user avatar
  • 173
0 votes
0 answers
27 views

Meta-analysis of ROC areas with missing confidence interval

I am performing a meta-analysis of a diagnostic score going from 0 to 10 based on 30 reports. For each report I have data on number of false/true positive/negative patients for one and in some cases ...
Roland's user avatar
  • 301
0 votes
0 answers
43 views

How to measure Statistical Significance for calculated Sensitivity, Specificity, Precision, Accuracy and f1 values?

I am trying to understand how to calculate one or more measures of statistical significance to display alongside metrics I've calculated from my data. Abbreviations I am using in the rest of this post:...
Natalia's user avatar
0 votes
0 answers
42 views

How to properly compare a single diagnostic test in two subpopulations

Suppose I have a diagnostic test with a binary response. I have performed this test on some population. Now, I split this population in two subgroups (e.g. male/female), and would like to check if ...
Alb's user avatar
  • 115
0 votes
0 answers
21 views

How can we apply sensitivity analysis in comparing two ARIMA models, both measuring intervention effect?

I have a dataset of reporting rates collected over an 8-month period obtained from the baseline (4 months) and during intervention (4 months). The goal is to determine if the intervention has a ...
George Mwenye-Phiri's user avatar
0 votes
0 answers
7 views

How to compute the minimum sensitivity and specificity a classifier needs to estimate a proportion to within some percent error?

I am building a binary classifier. Once classified, the proportion of positive events will be calculated. The predicted proportion is required to be within 10% of the true proportion. In practice, ...
Dave's user avatar
  • 1
0 votes
0 answers
63 views

What is the relationship between bias-variance and sensitivity-specificity for novelty detection?

An over or under-parameterized binary classification model (- vs +) tends to over or under-fit (bias-variance tradeoff). This leads to errors during prediction on unseen data. Depending on if ...
Douw Marx's user avatar
0 votes
0 answers
225 views

Comparing Sensitivity, Specificity, PPV and NPV of one test across two subgroups

I am seeking to compare the diagnostic performance of a test within a population with two defined subgroups. I have the raw data & computed data, but am unsure what the best test is to compare the ...
Richard's user avatar
0 votes
0 answers
72 views

How to apply Bayes' theorem on a contingency in which the sampled distribution differs drastically from the entire population?

Summary: How can I calculate my probability of being truly positive based on a contingency table that has a completely different distribution than the total population? I was recently confronted with ...
jotheta's user avatar
0 votes
0 answers
95 views

Automatically obtain optimum cutoff point for accuracy, sensitivity and specificity

Below is a code snippet to plot the accuracy, sensitivity and specificity. I can manually eyeball and see the cutoff point at approximately around 0.3. I was wondering if there anyway to print out ...
Larry Chuon's user avatar
0 votes
0 answers
24 views

Sensitivity to settings vs statistical sensitivity

I am confused between two different properties of a model. Both are called sensitivity. First, sensitivity is another word for true positive rate. Second, the output of a model changes in response to ...
Mikhail's user avatar
  • 97