The error of an observed value is the deviation of the observed value from the (unobservable) true function value. Do NOT use this tag for SOFTWARE ERROR messages.

learn more… | top users | synonyms

0
votes
1answer
40 views

Errors vs measurement errors

I'm reading about how to fit a straight line with measurement errors in both coordinates ($x$ and $y$). Let the true unobserved variables be $x_{t,i}$ and $y_{t,i}$ and the observed variables be ...
0
votes
0answers
19 views

Is it okay to use relative error on a set of measurements rather than an absolute error?

As far as I've learned, if you have a set of measurements and the differences between the average of those measurements and the individual measurements aren't always smaller than the absolute error of ...
0
votes
0answers
7 views

Predict function error for probabilities in glmnet? [migrated]

I am trying to predict probabilities in a dataset using glmnet. My code reads: ...
0
votes
0answers
9 views

Random forest in matlab: questions about OOB error in TreeBagger [migrated]

I'm currently working on a classification/regression problem with random forests and using Matlab's TreeBagger. I want to estimate the performance of the model for the two different classes(positive ...
1
vote
2answers
73 views

Why don't we train neural networks to maximize linear correlation instead of error?

Recently a project I've been a part of has involved training neural networks so that we maximize the Pearson correlation between actual and predicted values. So this came to my mind: why don't we ...
2
votes
1answer
17 views

Non neglible instrument error associated with a mean

I have N samples, that have mean X and standard deviation sigma. So far so good. I know that each sample has been measured with a measurement error e. Because the data is real world data the ...
2
votes
0answers
27 views

Ratio “observed-to-expected” - how do you call it?

Is there a name for the ratio of the observed count in a cell (say, ij) to the expected count in it - $O_{ij}/E_{ij}$? Likelihood ratio Chi-square (= G-square) statistic is based on these quantities. ...
2
votes
1answer
19 views

GLM with Gamma distribution of errors: negative residuals?

I'm trying to understand how the Gamma distribution, which is always positive, is used to describe errors when using a GLM. In practice, errors can be negative, as I get negative residuals when ...
3
votes
1answer
100 views

What's the difference between the variance and the mean squared error?

I'm surprised this hasn't been asked before, but I cannot find the question on stats.stackexchange. This is the formula to calculate the variance of a normally distributed sample: $$\frac{\sum(X - ...
0
votes
0answers
15 views
2
votes
0answers
16 views

How do you report percent error with limited precision?

Let's say you have an experimental data point with limited precision, such as 0.67 ± 0.1, and a known actual value such as 0.72. What is the standard way to report the percent error in this case, ...
1
vote
2answers
43 views

error analysis on nonlinear curves

I have a set of data from a simulation that generates a curve, and I have a mathematical model (from theory) on what things are supposed to look like. Of course, there is some error expected between ...
0
votes
1answer
21 views

The probability of m out of K things being wrong with an error of ɛ

I have a homework question about a machine-learning algorithm that uses ensemble learning with simple majority voting. Assuming we have K hypotheses, each with an error ɛ, the question asks us to ...
3
votes
1answer
55 views

Should I use Mean Square Error or Classification Rate?

I am a self-taught person and I would like your help. I am learning about predictive modeling in general, and I'm also trying to do predictive modeling for a specific problem. I am exploring ...
0
votes
0answers
11 views

When is it appropriate to use the estimation of error bar $\sqrt{frequency}$?

I have some data which follows poisson distribution. I am just curious under what circumstances is the square root of the bin appropriate to use as an error bar? When do I get in trouble for using ...
0
votes
0answers
12 views

Choosing which distribution is most accurate

Let's say we have two samples from different normal distributions and we want to determine which distribution is most accurate relative to an ideal value. How would we evaluate which one is more ...
0
votes
0answers
19 views

Perceptron Algorithm, RMSE just cycles through two numbers

My input is a bag of words feature vector, of the form: Example: Document 1 = ["I", "am", "awesome"] Document 2 = ["I", "am", "great", "great"] Dictionary is: ...
4
votes
2answers
121 views

What does an error in ANOVA indicate?

When I came across ANOVA, the instructor talked about df(Error), ss(Error), etc. What do these error terms indicate? Do error terms differ for two-way ANOVA with dependent and independent variables? ...
1
vote
0answers
11 views

Question about relative percent error with widely varying expected values

I'm looking at a large collection of values. These values follow an exponential distribution. I have their probabilities and a pre-made Excel spreadsheet that will auto calculate expected values from ...
9
votes
1answer
115 views

Additive Error or Multiplicative Error?

I'm relatively new to statistics and would appreciate help understanding this better. In my field there is a commonly used model of the form: $$P_t = P_o(V_t)^\alpha$$ When people fit the model to ...
0
votes
0answers
25 views

When to use CRPS (Continuous Rank Probability Score)? What are the alternatives? What are the advantages and disadvantages?

Please correct me if I'm wrong, crps is new for me. I want to understand it better. We have to minimize crps, which is based on the cumulative distribution function of the data. While the information ...
0
votes
0answers
5 views

ESL: base error rate question

In page 51, of ESL, it says "The mean prediction error on the test data is 0.521. In contrast, prediction using the mean training value of lpsa has a test error of ...
0
votes
0answers
12 views

Learning to filter audio: Error falls near zero but output is always rubbish

I'm new to machine learning and I'm trying to train a neural network to separate audio from a mixed track. Training data I've collected a bunch of audio snippets from freesound.org, grouped by ...
0
votes
0answers
30 views

How to get the error and error variance after hierarchical bayes using bayesm

I estimated individual part-worth based on multiple paired comparisons by using Bayesian logistic regression in R (bayesm, model: rhierBinLogit by Rossi). rhierBinLogit implements an MCMC algorithm ...
4
votes
1answer
163 views

Reinterpreting a Poisson regression

The way I understand a Poisson regression is that we model $y|x \sim \text{Poisson}(\exp(x'\theta))$ so that $E[y|x]=\exp(x'\theta)$ (e.g. http://en.wikipedia.org/wiki/Poisson_regression). My ...
0
votes
0answers
22 views

Regression on beta coefficients from different models

Brief Background: Let's say I performed different regression models and found their beta coefficients estimates with their corresponding variances. I would now want to do a regression on those beta ...
0
votes
0answers
25 views

Understanding the (multiple) OOB columns in R's randomForest output

This is somewhat related to this post from 2012, however I want to focus specifically on the metrics generated while the randomForest model is running and make sure ...
0
votes
0answers
7 views

Estimating noise required to transform a given distribution into a target distribution (CDF)

I have (independent) samples generated from two different probability distributions A and B, and would like to find a noise distribution e so that adding the noise e transforms A (approximately) into ...
2
votes
0answers
28 views

Approximation error of the delta method: Berry Esseen type bound

I'd like to know if there is a literature reference or well-known result in statistics on the estimation error of the (multivariate) delta method, in particular, a Berry-Esseen type bound. To ...
0
votes
1answer
40 views

How to calculate the total error of a neural network

I know that my question sounds really simple, but honestly I don't know how to calculate it. The error = expected output- estimated output, but what does total error mean? Is it the sum of the error ...
1
vote
0answers
18 views

How is the sample size for a given population determined?

The following passage is an excerpt from Thinking, Fast and Slow by Daniel Kahnemann The risk of error can be estimated for any given sample size by a fairly simple procedure. Traditionally, ...
0
votes
0answers
14 views

The way to convert error function to matrix form in linear regression? [duplicate]

In linear regression squared error function is calculated as: $$ Error(w) = \sum_{i=0}^{m} W^{T}x_i - y_i $$ In which $W^T$ means the transpose of weights vector. $x_i$ is the ith input in vector x ...
3
votes
1answer
69 views

Designing Asymmetric regression (assymettric loss for regression)

I have a hybrid classification/regression problem.The predicted value can be assumed to be centred around 0. I want to penalize the predictor more, if the predicted value and actual value have ...
2
votes
0answers
27 views

Linear regression with estimates of error in predictor

I have data with two different kinds of measurements at the same set of $S$ sites. One of these (call it $X$) returns m estimates at each site, which are not necessarily independent of one another. So ...
4
votes
0answers
44 views

When to use non-additive stochastic error term

I have encountered the following two versions of the Cobb-Douglas production function as an illustration of the differences between intrinsically non-linear and linearisable non-linear regression ...
4
votes
2answers
50 views

Are cross-validated prediction errors i.i.d?

Say, we test an arbitrary regression or classification procedure on $n$ independent samples with leave-one-out cross-validation. This results in an estimate of the prediction error $e_n$ for each ...
0
votes
0answers
12 views

Do I have a correct understanding of Margin of Error/Accepted Error involved in sampling - Conflicting Previous Answers

I constructed a sample size calculator in Excel: Response Rate * (1 - Response Rate) * [Norm.Inv((1-alpha)/2) * (-1)/Accepted Error]^2 If post sampling I have: p ...
3
votes
0answers
52 views

Is there any statistical basis to relative error?

Given a true value $b$ and an approximated value $a$, Wikipedia defines the absolute error to be $\lvert a-b \rvert$ and the relative error $\left\lvert\frac{a-b}{b}\right\rvert$. Ensuring that the ...
2
votes
1answer
39 views

What is the difference between errors and residuals?

While these two ubiquitous terms are often used synonymously, there sometimes seems to be a distinction. Is there indeed a difference, or are they exactly synonymous?
0
votes
0answers
6 views

Errors on a regression line [duplicate]

This may have a simple answer but google has failed me so far. How do I calculate the error on the slope and y intercept of a regression line, which takes account of the errors on each data point? ...
0
votes
0answers
13 views

Error propagation through convolution

I have a list of data points $y_i$ and a respective uncertainty $\sigma_i$ associated to them. Now I am convoluting this with a Gaussian window function (discretized $w_i$) "numpy.convolve" function ...
4
votes
0answers
65 views

Is the ALRE method of standardization/rescaling appropriate for proportion data?

I have data in which groups of experts make proportion estimates. I've been encouraged to use the ALRE method of scoring the error of these estimates. I found an article which describes this method: ...
0
votes
0answers
19 views

Mean Absolute Scaled Error

Right now, I am analyzing the prediction quality of a dynamic model that has variables with different units (e.g. $x_{1,t}$ is in meters, $x_{2,t}$ is in kilograms etc.). I have discovered a great ...
1
vote
1answer
115 views

Weka - Result interpretation

I am running the classify in Weka for a certain dataset and I've noticed that if I'm trying to predict a nominal value the output specifically shows the correctly and incorrectly predicted values. ...
1
vote
2answers
37 views

Relative Error Temperature

I have a model to simulate temperatures and I want to compare it to reference values. I thought that the relative error (or rather percentage error) would be interesting, but I'm rather confused on ...
1
vote
2answers
97 views

Is covariance between two dummy variables zero?

Here is a problem I am facing: I need to test a hypothesis (t test), the formula for which is $t = \frac{\hat{B_1} - \hat{B_2}}{se(\hat{B_1} -\hat{B_2})}$ Now, we know that the bottom isnt actually ...
10
votes
1answer
139 views

Are data handling errors already 'priced in' to statistical analysis?

Ok, fair warning--this is a philosophical question that involves no numbers. I've been thinking a lot about how errors creep into data sets over time and how that should be treated by analysts--or if ...
0
votes
0answers
29 views

What's the difference between error distribution and residual distribution in generalized linear models?

I have met with generalized linear model, but I'm confused with the errors and residuals? Can anyone help me out? I have got three questions. (1)what's the difference between error and residual? ...
0
votes
1answer
53 views

Matrix Inversion Error

I a Multiple linear regression model, from published literature, I am implementing a spreadsheet to generate new predictions based on the published model. the literature stated Coefficients and the ...
5
votes
1answer
127 views

Understanding the error term

I am trying to figure out the meaning of these different "hatted" terms in regression analysis. Here is my basic understanding: $Y$ the original of population/sample values $\hat{Y}$ regression ...