Questions tagged [false-positive-rate]

In a test for a condition (such as a disease) the false positive rate is the proportion of subjects incorrectly classified as having the condition.

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

How could one estimate the false positive rate of a deployed fraud detection system?

On a labeled dataset, the FPR of a classifier could easily be measured. However, after a fraud detection system is deployed, we lose the ability to gain a ground truth classification of the positives. ...
1
vote
0answers
11 views

Procedure to Smooth Noise for Threshold Values

Suppose I am looking at an estimate $\hat\beta$ in a clinical trial data. With $a=.05$, a patient with $\hat\beta>1$ is considered to have some medical condition. A daily example could be a 24-hr ...
2
votes
1answer
22 views

Base rate of accuracy after resampling for classification problems

If I had an imbalanced dataset with 10% positive instances and 90% negative ones, the base rate for accuracy before resampling is 90%. But what about I resampled the data such that I have an equal ...
1
vote
0answers
23 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 ...
2
votes
1answer
39 views

What is “positive”?

I'm deeply confused by some concepts. We often hear the term true/false positive/negative. While it is straightforward to tell if the result is true or false, I ...
1
vote
2answers
23 views

FPR in Confusion Matrix

I was trying to manually calculate $\text{TPR}$ and $\text{FPR}$ for the given data. But unfortunately I dont have any false positive cases in my dataset and even no true positive cases. So I am ...
0
votes
0answers
30 views

Oversampling/Undersampling in respect to Train and Test - Isolation Forest

I've got a quite imbalanced data set. 144.496 : 162 -> ratio of 1000:1 I would like to use IsolationForest to detect the 162 anomalys. I've already split the data. However, the iForest doesn't ...
0
votes
0answers
8 views

Multiple hypothesis correction yields higher FDR on lower number of tests. Why?

I have a DF (df1) with thousands of rows, where each row has a test and associated P, and their corresponding corrected P values (FDR Benjamin-Hochberg). Under ...
1
vote
1answer
35 views

False positive/negative rate in ridge and lasso regressions

I have a confusion matrix of true and estimated $\boldsymbol{\beta}$ vectors of lasso and ridge models from a replicate of a simulation study, say. The following tables illustrate the scenario. $$\...
0
votes
0answers
6 views

What would be the True Negatives (TN) and FPR in this case?

I've developed an algorithm that detects shapes in a given image. The input is an image with a triangle, a square and a circle. My algorithm outputs triangle, square, pentagon. If I'm not mistaken, ...
0
votes
0answers
13 views

How to make sense of both high FNR and NPV?

So, even though this is one of the most basic and already explained things about statistics I always seem to find way not to get it. Having this table which shows high Negative Predictive Value (352/...
1
vote
1answer
53 views

SVM probability output threshold as (1 - FPR)?

I have a binary SVM with probability output (via Platt scaling). I want to set a threshold on the probability outputs since I want to trade off making false positives/negatives. Is it possible to ...
2
votes
0answers
35 views

How to interpret a False Discovery Rate plot

It is the first time that I am trying to calculate the FDR and I use the fdrtool package in R. I want both, local and tail area graphs and I think the third ...
0
votes
0answers
13 views

Estimating false accept rates from imposter scores below a threshold

I have a system that compares two items and produces a match score. Scores below a threshold are manually inspected to determine if they match or don't(imposter). Scores above the threshold are ...
2
votes
1answer
105 views

Is most published research indeed false?

I have come across (Ioannidis, 2005) which explains several reasons (mainly statistics-related, that's why I post this question here) to justify the claim that most published research is indeed false. ...
0
votes
1answer
17 views

Optimal solution for false positive effect on business strategy

I am facing a challenge to reach an optimal solution. I will try to explain with an example : Suppose I have created an algorithm to predict if a customer will subscribe to bank deposit plan or not. ...
0
votes
1answer
81 views

Is it possible to estimate accuracy, precision and recall with the given data?

Background: I talked to my friend today and according to herm(him/her) I can calculate precision, recall and accuracy with the current information. Total instances T: 19,532. Instances belonging to ...
1
vote
0answers
32 views

Exclude areas of feature space without getting false negatives

I am using a decision tree classifier to split the feature space according to two classes ( A and B). Events of class A are important and I want to classify all of them correct, i.e. no false ...
0
votes
0answers
20 views

Test for unequal correlation coefficients inflates Type I error for non-uniform sample distribution. How to correct?

Aim I'm studying the hypothesis test which estimates the probablility of the null hypothesis: The difference between two correlation coefficients is 0. More exactly, I deal with the question ...
0
votes
0answers
16 views

Estimating true positive rate with a confidence interval given a classifier + unknown dataset truths

Let's say I've built a binary classifier - one that for instance, can classify whether a particular transaction is fraudulent or not. This classifier outputs a 1 or a 0, with a given degree of ...
1
vote
2answers
76 views

Is it the case that β+power=1?

In psychology papers that do prospective power analyses (example), one often notices the convention of assuming β values (false negative rates) of 0.20, and power levels of 0.80. In other words (if I ...
1
vote
0answers
104 views

What is the integral of the False Positive Rate over the False Positive Rate, compared to the AUC?

In machine learning the Area Under the Receiver Operating Characteristic Curve ($AUC$) can be illustrated in a plot of the True Positive Rate ($TPR$) against the False Positive Rate ($FPR$). Formally, ...
1
vote
0answers
35 views

How to make really bad results from a machine learning model better by reversing predictions

I trained a classification model on some data with two classes and have really low accuracy. I have a false-positive rate of 86 % for both classes I am trying to predict. I was wondering if I could ...
2
votes
2answers
69 views

Number of samples required to estimate a desired False Positive Rate

I have an algorithm that for each sample $x_i$ returns an anomaly score $0<s_i<1$. I use cross validation to set a threshold $th$ such that $x_i$ is anomalous if $s_i>th$. During cross ...
2
votes
1answer
88 views

How to tell the likelihood of getting a false positive? [closed]

Say we have a test for a disease we are comparing with the gold standard. You are given the prevalence of the disease, which is 1%, and sensitivity, 80%, and specificity, 90% and a total population of ...
0
votes
1answer
32 views

How are false positives possible? Since shouldn't mathematical methods be “exact”?

That is, it's not possible to have true as false, but isn't that basically what a false positive or a false negative does? That it gives a prediction of a condition existing, when it does not? So how ...
20
votes
2answers
11k views

FPR (false positive rate) vs FDR (false discovery rate)

The following quote comes from the famous research paper Statistical significance for genome wide studies by Storey & Tibshirani (2003): For example, a false positive rate of 5% means that on ...