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

3
votes
0answers
9 views

How to measure when error stabilizes (convergence) on Random Forests (or, when do I stop training)

I'm doing an implementation of Random Forests. As I was the original paper (page 11) and this nice book on the subject (15.3.1, page 592), they mention that when the out-of-bags error stabilizes (when ...
0
votes
1answer
25 views

Undefined real result error at WinBUGS

I am currently working on my thesis and interested in estimating a multilevel differential item functioning model and I using at WinBUGS. Until I had done model check-up, there are no errors. However, ...
2
votes
0answers
23 views

Standard error notation

Dealing with a standard error of a mean $$ \widehat{SE}_{\bar x} = \hat \sigma_{\bar x} = \frac{s_x}{\sqrt{n}}$$ $$ SE_{\bar x} = \sigma_{\bar x} = \frac{\sigma_x}{\sqrt{n}}$$ Is this the ...
0
votes
0answers
19 views

How to include the error term as an explanatory variable in a lm() model when the errors are auto-correlated?

I am wondering if there is a way to include the error term as an explanatory variable in a lm() model when the errors are auto-correlated. For example, I have a model that gives errors that has a ...
0
votes
0answers
16 views

Standard error of the mean for binomial dist [duplicate]

I know what intuitively what's going on but... We know that in general the standard error of the mean is $$ \sigma_\bar{X}^2 = \sigma_X^2/n $$ Right? But when I apply this to the binomial ...
0
votes
0answers
18 views

Standard Deviation expressed in percentage

I did an estimation. I got the result, lets call it x. Then, I did the experiment. I got another result, y. I need to know what difference in percentage is between those 2 results? What is the error ...
-1
votes
0answers
13 views

why is this giving me an NaN [migrated]

Ok, my problem is that I'm trying to compute $(-1)^{1/3}$, but when i ask R to compute this an NaN occur. > (-1)^(1/3) [1] NaN I really don't know why? I'm using R 2.15. i want to compute ...
6
votes
1answer
55 views

Selecting priors based on measurement error

How do you calculate the appropriate prior if you have the measurement error of an instrument? This paragraph is from Cressie's book "Statistics for Spatio-Temporal Data": It is often the case ...
0
votes
1answer
27 views

Use of infinity norm instead of SSE for machine learning accuracy?

Are there any examples or arguments in favor of using an infinity norm (or equivalent) over sum of squared errors or root mean squared error for evaluating machine learning algorithms?
0
votes
0answers
16 views

How do you scale percentage intervals based on absolute size?

If you were told the travel time from A to B is 5 minutes, you wouldn't mind if it took between 0 and 10 minutes. So happy within 100% of 5 minutes. If the trip took 5 hours (360min), you wouldn't ...
0
votes
0answers
11 views

What is the relationship between separable SVM test error bounds and soft-margin SVM test error bounds?

Can I compute the bounds for a soft margin SVM by taking the VC dimension for an SVM and using the misclassified examples as train error? Does the inequality from wikipedia's VC dimension page hold ...
0
votes
0answers
12 views

logarithmic calibration and geometric mean - citation search

I have a logarithmic calibration line: MachineSignal = -3.21 log(concentration) + 21.9 It seems obvious to me, that if I have a triplicate measurement of concentrations (measured indirectly through ...
1
vote
0answers
8 views

How to calculate MoE for subsamples

I have demographic and income data for 3 million people from the American Community Survey (courtesy of IPUMS), and my goal is calculate the median income for every permutation of age group, gender, ...
0
votes
1answer
25 views

Error bars and coefficient computation on linear regressions in Matlab

I have a handful (~5) of values x I need to plot against a handful of values y (actually, log(x) vs. log(y)), in order to derive a linear equation used to derive an empiric power equation. However, I ...
2
votes
0answers
19 views

Error of bounded mean estimation with quantization

I have a distribution whose mean $\theta \in [0,1]$. Given $n$ observations, I compute the sample mean (say $\hat{\theta}$) and quantize it to accuracy $\frac{1}{n}$ (basically I can use only ...
0
votes
1answer
16 views

Is margin of error truly valid at extreme proportions? Such as 1% agreement, mere traces of data

Survey margin of error contracts as the proportions become more extreme. Its validity and applicability in such cases has always concerned me, but I suppose much depends on the context. Where we have ...
2
votes
0answers
13 views

Strong and weak control

I have been searching for some explanations of weak and strong control for errors, but I do not really understand what it means. Could someone help me? Strong control refers to the control of Type I ...
3
votes
1answer
36 views

Prediction error in least squares with a linear model

In the classical linear model with $$Y=X\beta +\epsilon,$$ where $Y \in \mathbb{R}^n$ is the observation, $X\in \mathbb{R}^{n\times p}$ is the known covariates, $\beta \in \mathbb{R}^p$ is the ...
0
votes
1answer
21 views

ANOVA in R: How MSresiduals are estimated when using Error(interaction)?

I have checked the existing answers, but I found no answer to my question. It is about choosing the right ANOVA model in R and how the MSresiduals are estimated. I have an experiment with two ...
0
votes
1answer
17 views

Compare two measures with measurement uncertainty

I have to compare, choosing a significance level, two quantity normally distributed with respective measure uncertainty (quantified with error propagation law). How could I make the comparison between ...
0
votes
0answers
22 views

How do I determine the innovation term in an ARIMA equation?

I am not a statistics specialist : I had to take over the internship subject of another student to include it in mine. He was working with $SARIMAX$ models and I would like to import them in an ...
2
votes
1answer
42 views

how to calculate a summary value and statistical error in time series

I have a set of data that comes for empirical measurements over a number of days. From the beginning of the experiment to the end of it, every five minutes temperature was measured inside (Ti) and ...
0
votes
0answers
19 views

Error messages when doing regression in SPSS

I need to do a number of regressions in SPSS but keep getting error messages. For example - "There are X cells (i.e., dependent variable levels by combinations of predictor variable values) with ...
1
vote
1answer
29 views

How can we choose which model generalizes better?

I got asked this question today: How could we reasonably safely conclude that, for a given dataset, in practice, one classifier generalizes better than another? I could not give a concise ...
0
votes
0answers
4 views

Contribution of residuals to the mean error

I have data for 1000 students' performance over 10 different tests on a scale of 0 -100 (a 1000 rows X 10 col matrix). I calculated the mean score and the associated std. deviation for each student. ...
1
vote
0answers
10 views

Power to detect significant correlation given measurement uncertainty

First of all, apologies if some of the technical terminology in here is not accurate - my experience with statistics is fairly limited. To illustrate my problem, let's say I wanted to design a study ...
0
votes
1answer
18 views

Reported error rates on neural networks

It is common to depict the error rates of types of neural networks in a table, for example, see the MNIST website. However, because of the non-determinism caused by weight initialization the actual ...
0
votes
0answers
40 views

Bivariate Poisson regression: Error: “in `contrasts<-`(…): contrasts can be applied only to factors with 2 or more levels ”

I realize this error message has been posted before, but the solutions previously provided does not work for me, so here goes: I am working with a data.frame, which looks like this: ...
4
votes
1answer
28 views

How I can measure an error in a bar plot?

This is my barplot. Model(red) is my estimated frequency at each X-axis vale (0-19) and actual is the frequency at each X-axis vale. How I can measure error of this estimating work in barplot? If I ...
0
votes
1answer
12 views

Is it possible to extrapolate experimental errors from a subsample of a population?

I'm working with a dataset consisting of degradation rates for proteins in an organism, a total of approx 3750 rates in total. Obtaining these rates is difficult, so the majority of rates are reported ...
2
votes
1answer
86 views

Error on interquartile range

How can I compute the error on the interquartile range of a sample? By error I mean its std deviation (e.g. error on the mean = RMS/sqrt(N)). The sample is from a unimodal distribution, similar to ...
0
votes
0answers
6 views

How to compute the normalized misclassification error and the misclassification error?

How is usually computed the normalized misclassification error ? I would like to know the formula for a 2 class problem of size $s_1, s_2$ and for a k class problem of size $s_1,\dots, s_k$ I would ...
3
votes
1answer
51 views

Idea of errors as 'shocks' to a regression?

So I always understood the error term to be the difference between the observed value from the true, yet unobservable, function value. However, I often here, especially related to the economics ...
0
votes
0answers
71 views

Arima function doesn't consider seasonal components

Currently trying to fit several models to some data sets in order to find an accurate enough one, I ran into some difficulties with the Arima function of the ...
1
vote
1answer
22 views

Forecast error differences when using weekly vs monthly data

Why is forecast error (MAPE) much higher when using weekly periodicity vs monthly? I am using exactly the same data for both.
0
votes
0answers
25 views

R - Robust Ancova: Documentation/Examples for the ancmg function in the WRS package

Could anyone point me to a documentation or even better an example for the ancmg1 or ancmg functions of the WRS-package. There is a very short paragraph in the Wilcox' book about Robust Estimation, ...
1
vote
2answers
45 views

Obtaining error bars for a difference

I have a pair of data sets, and I want to know whether the medians of these two sets differ significantly. I've calculated the median of each set and subtracted them from each other. How can I ...
1
vote
1answer
49 views

Why do my ANOVA tables keep returning $\chi^{2}$ values of 1?

I'm using ANOVA to test for differences between different values of the same factor for a mixed effects model which I produced. My model is: ...
0
votes
1answer
78 views

Errors when fitting a SARIMAX model in R

Currently working on big data sets, I would like to fit a SARIMAX model to it in order to forecast future values. Here are my questions : Q1. As a matter of information, does anybody know how does R ...
1
vote
1answer
75 views

R - Test for homogeneity of regression slopes results in singular model

I am trying to check the assumptions of a two-way ANCOVA. So in my model I have two factors (F1, F2) one dummy coded two level covariate (C) one dependent variable (D) In order to check the ...
1
vote
1answer
135 views

How to get the value of Mean squared error in a linear regression in R

Let a linear regression model obtained by the R function lm would like to know if it is possible to obtain by the Mean Squared Error command. I had the FOLLOWING output of an example ...
1
vote
0answers
43 views

error structure in Generalized linear models when y is continuous data and errors not normally distributed

Lets say I have continuous y and x variable and I run a linear regression: mdl1<-lm(y ~ x) A generalised linear model should also give me the same parameters ...
2
votes
0answers
54 views

Standard error on median for exponential distribution

I am trying to find the standard error on the median, $\sigma_\tilde{x}$, for a sample, $X_i$, of a population whose pdf could be modelled as $\lambda e^{-\lambda x} $ if normalized. To make sure we ...
2
votes
0answers
35 views

Calculate prediction errors of binary model: What's a good way?

I am totally new to statistics, so this may be obvious, but I don't get it. Basicly, I fit a special kind of tree-model to a subset of data (one half), and now I want to cross-validate my model ...
1
vote
0answers
33 views

random forest and prediction

I am building a random forest model to make predictions. Response variable is treated as continuous but not really continuous, e.g., integers from 0 to 10. I have problems in constructing ...
1
vote
1answer
57 views

Why is the true (test) error rate of any classifier 50%?

In section 7.10.2 of Elements of Statistical Learning, it says that the true (test) error rate of any classifier is 50%. I'm having trouble understanding the intuition behind this. If you have a ...
0
votes
0answers
5 views

Fast procedurally built inverse model

Suppose I have a DB into which the following key values are entered (in that "random" sequence) {16, 32, 256, 2, 8, 64, 4, 1, 128, 512} Assuming the values get ...
3
votes
1answer
52 views

Error Bars for Monte Carlo Experiment

Suppose we have a random variable $X$, where $\mathbb{E}(X)$ and $\text{Var}(X)$ are known. I have computed $N$ number of MC-type samples from the distribution of $X$. Let $\bar{x} = \frac{1}{N}\sum ...
2
votes
1answer
74 views

Standard error of mean

I am learning statistical analysis, and am now confused about calculating the standard error of the mean. My dataset looks like.. Condition A: ...
1
vote
1answer
71 views

Why is error variance important in CFA?

I am reading the book related to SEM (Byrne, 1998) and it is stated that regression of the observed variables on the factor, and the variances of both the errors of measurement and the factor, as well ...