Questions tagged [mean-absolute-deviation]
Mean absolute deviation around the mean. Use [mad] for median absolute deviation around the median.
37
questions
1
vote
0answers
15 views
How do I calculate Correlation Coefficient using Mean Absolute Deviation?
I am trying to calculate Pearson's Correlation Coefficient using the product of the Mean Absolute Deviations (MADs) of my two lists as denominators instead of the Standard Deviations. Effectively, ...
1
vote
0answers
11 views
Estimate the error bound of a histogram based mean absolute deviation approximation
Given a sequence of numbers $A = a_1, a_2, \cdots, a_n$.
One way to calculate the mean absolute deviation of $A$ is by $G(A)= \sum_{i=0}^n |a_i - median(A)|$.
yet, there can be an alternative, by ...
1
vote
0answers
31 views
Why is there no improvement when training Xgboost with pseudo-Huber loss?
In this StackOverflow post I asked if there was something wrong with my syntax when training an XGboost model (in R) with the native pseudo-Huber loss ...
0
votes
0answers
7 views
What is the maximum entropy distribution given *conditional* means and MADs?
I know the maximum entropy distribution given the mean and MAD (Mean Absolute Difference) around the mean (it's the Laplace distribution, a proof here for example).
I also know the maximum entropy ...
0
votes
0answers
10 views
A fair group allocation
Assume that I have 4 groups and 16 players that I wish to allocate among the groups. Each player has its own ranking (ELO or something). The group ranking is just the sum of rankings of players in ...
2
votes
1answer
57 views
How to calculate the running mean absolute deviation
I wish to calculate the running mean absolute deviation (MAD) without storing the previous n data points. This calculation is for a continuous stream of data, i.e. infinite length. I am trying to ...
0
votes
0answers
53 views
For multivariate linear regression, what is the partial derivative for Mean Absolute Error?
What is the partial derivative for MAE for multivariate linear regression? I understand that for mean squared error (MSE) the partial derivative with respect to some $\theta_1$ would be $-\theta_1 \...
8
votes
1answer
215 views
an upper bound of mean absolute difference?
Let $X$ be an integrable random variable with CDF $F$ and inverse CDF $F^*$. $Y$ is iid with $X$. Prove $$E|X-Y| \leq \frac{2}{\sqrt{3}}\sigma,$$ where $\sigma=\sqrt{Var(X)} = \sqrt{E[(X-\mu)^2]}$.
I ...
0
votes
1answer
15 views
What are the drawbacks of aggregating regression results if error decreases?
I am trying to predict Total National Sales in dollars for a major retailer. However, the data I'm using exists at the state level, and includes several features around specific brands and foot ...
0
votes
0answers
25 views
Why isn't absolute deviation used [duplicate]
If the reason that standard deviation is used is that it's easier to just square the distance every time than find the absolute value. Then why is √(E(x-m)^2)/n not used because if I'm not mistaken |x|...
1
vote
1answer
34 views
Ho do I determine the probability of price reversals using linear regression?
In the screenshot, you will see the daily prices of Nasdaq. Each candle has a High, Low, Open and Close price.
I have drawn a regression line with a 2 standard deviation channel on either side.
How ...
0
votes
0answers
18 views
We square at the variance and SD is it due a link with to Gaussian function? [duplicate]
I had almost same question as "Why square the difference instead of taking the absolute value in standard deviation?". But I also noticed the $\sigma$ or population standard deviation is ...
1
vote
1answer
13 views
Alternative error measure--maximize data to have residuals less than given threshold
I am looking for a method which finds a linear model (2 input variables, everything reasonably close enough to normally distributed), but with an alternative measure of error. Every error measure I ...
5
votes
2answers
103 views
Random variables $(X,Y)$ with $\text{Var}(X)<\text{Var}(Y)$ and $\mathbb{E}(|X-\mu_X|)>\mathbb{E}(|Y-\mu_Y|)$
I am looking for an example of a pair of random variables $(X,Y)$ with expected values $(\mu_X,\mu_Y)$ satisfying the following relationships:
$$
\text{Var}(X)<\text{Var}(Y)
$$ and
$$
\mathbb{E}(|X-...
1
vote
0answers
21 views
How to derive this MAE error bound on the central limit theorem?
Is this derived from Chebyshev's inequality or a tail bound theorem? If not, how was it derived?
Does this require the existence of the third moment?
Does this bound suggest the normal approximation ...
1
vote
0answers
8 views
how to detect a 5% deviation between more than 2 numbers
Dear StackExchange Team
in the industry there are GAs generators that have hundreds of instrument measuring process values, such as pressure, temperatures, etc.
we have a simple case where a ...
0
votes
0answers
11 views
Estimate MAD of marginal means
Assume we have a (unknown) random variable $X(r,p)$ over the space $R \times P$. From this distribution we have observations $X(r_j, p^j_i)$. For every $j$ there are on average around 60 $i$'s lets ...
0
votes
0answers
23 views
Considering the reliability of results given they were produced using different amounts of data
I am doing some deep learning and I have two lists of numbers: the predictions from a regression neural network and the ...
0
votes
1answer
151 views
How to fix heteroscedasticity (funnel shape)?
I am running a mlr in python on a dataset with 2D feature vectors, X1 and X2 on a single response, Y. The data ends up being funnel-shaped, as below:
X1 v Y, with the colors being X2.
It was ...
10
votes
2answers
216 views
Is mean absolute deviation smaller than standard deviation for $n\ge 3$?
I want to compare the mean absolute deviation with standard deviation in general case with this definition:
$$MAD = \frac{1}{n-1}\sum_1^n|x_i - \mu|, \qquad SD = \sqrt{\frac{\sum_1^n(x_i-\mu)^2}{n-1}}...
0
votes
0answers
46 views
Compare variables with zeta-score
Assume the calculation of a physical quantity $x$ from a given formula i.e. $$x=\dfrac{a*b}{c}$$ where $a, b$ and $c$ are experimental observables, therefore $x$ is a quantity derived from ...
1
vote
1answer
268 views
Why do we use squared deviations to compute the SD, given that it amplifies the effect of outliers? [duplicate]
Suppose I have the following hypothetical data:
One thousand times value 15 (i.e., 15 occurs 1000 times)
and a single outlier value - 115 (i.e., 115 occurs just once - an outlier)
Thus the mean is: $...
0
votes
1answer
297 views
Estimating Expected Order Statistics
I have a fairly basic question that I'm looking for a reference for.
First, a couple definitions. Let's say $X_1,\ldots,X_n$ are IID samples from a distribution $F$ over $[0,1]$. For any $k\in\{1,\...
1
vote
0answers
159 views
Statistical test for comparing the performance of two methods using absolute differences
I am doing a study where I have to compare tumor sizes measured using two different methods with the real tumor size.
What I want to prove is that the absolute difference between method 1 and real ...
5
votes
2answers
76 views
Rephrasing Statistics using MAD
I just got done reading Gorard's "Revisiting a 90-year-old debate: the advantages of the mean deviation." (https://www.leeds.ac.uk/educol/documents/00003759.htm) I'm no expert at statistics; in fact, ...
1
vote
2answers
132 views
Verbal Description Of The RSE
I'm reading An Introduction to Statistical Learning, currently on page 69, the chapter on Simple Linear Regression.
The text says:
In the case of the advertising data, we see from the linear ...
-1
votes
2answers
1k views
Why does Mean deviation = Standard deviation = Range/2?
We know that mean deviation and standard deviation are two different things but why are both of them equal to Range/2?
Range ($R$) = Highest value - lowest value
Mean deviation ($\text{MD}$) = ...
6
votes
2answers
3k views
Why not use modulus for variance? [duplicate]
I am trying to wrap my mind around the variance definition.
Given a set of values S and n = #(S), the variance is defined as:
$$
\operatorname{var}(S) = \frac{\sum_{i=1}^n( S_i - \operatorname{mean}(...
1
vote
0answers
127 views
An efficient algorithm for sliding mean deviation
I'm searching for a computationally efficient algorithm to calculate the sliding mean deviation from sample $x_a$ to sample $x_b$ belonging to a large set $x_0, x_1 ... x_n$ with the condition that $a$...
1
vote
1answer
560 views
Best way to describe changes in performance through time.
I'm wondering how to explain changes in production/performance metrics quarter to quarter. In the example below, one can see that the average processing time for "widgets" has decreased substantially ...
0
votes
0answers
30 views
Is standard deviation always larger than mean deviation? [duplicate]
If yes why is it the case that it have this property? There must be some mathematical proof or intuitive understanding in that case.
1
vote
1answer
407 views
Why don't dispersions like median deviation and mode deviation exists on the lines of mean deviation?
Or to say in the formula MD=$\frac{1}{N}\sum_{i=1}^{N}|x_i-\overline{x}|$ why can't we have median or mode instead of mean($\overline{x}$) and as a result speak about additional possible measures of ...
2
votes
1answer
1k views
Is mean deviation the same as mean absolute difference?
Do both terms mean the same thing or are they different?
2
votes
1answer
49 views
Variance of Binomial total deviation
I have a Binomial random variable $X \sim B(n,p)$. Is there a closed form expression or an upper bound for the variance of the absolute deviation $|X-\mathbb{E}[X]|$ ?
4
votes
1answer
765 views
Mean Absolute Deviation of Student t distributions?
I could only find these two formulae, both apparently with some issues.
Which is the correct one? Online references and derivation would be especially appreciated.
8
votes
0answers
8k views
Relative Mean Deviation [closed]
The Mean Deviation, also referred to as Absolute Average Deviation, is sometimes preferred to the Standard Deviation (Cf. Gorard 2004). For a sample, it can be expressed as:
$MD = \frac{1}{n} \sum\...
0
votes
0answers
301 views
Difference between absolute deviation to population median and sample mean
I have independent variables $X_i\in[0;1]$ and suppose they are uniformly distributed. If you want to minimize the total absolute deviation to a fixed number, how much can you gain from using the ...
