8
votes
Accepted
What is the mathematically rigorous definition of chunky data?
Data like this is often called quantized, particularly when the numbers' precision is limited by the measurement device. For example, a scale might only display integer numbers of grams or pounds. ...
- 20.5k
7
votes
Accepted
Probability of failure in a finite population
Suppose you sample $n$ members from a population of $N$ (without replacement) and $k$ of them are failures. The definition of confidence tells us to ask this question:
If there are $K$ failures in ...
- 313k
6
votes
Accepted
How find controls limits for CUSUM chart
First thoughts:
It looks like there are several packages for CUSUM charts in R, inculding but not limited to the following:
'qcc' (v2.6) - quality control charts (2014)
'spc' (v0.5.1) - statistical ...
- 8,613
6
votes
What is the mathematically rigorous definition of chunky data?
Generally, "binned data" is how this is referred to.
If you think of a histogram, each bar refers to a bin. If a value is between the upper and lower ends of a given bin, that value is placed in ...
- 19.6k
6
votes
Closed formula for D4 constant calculation? (Moving range chart constant)
The definition of $D_3$ and $D_4$, from "ASTM MNL7, Manual on Presentation of Data and Control Chart Analysis" is:
$D_3=1-3\frac{d_3}{d_2}$
The equation in the standard should be, $D_3=\max\left(0,1-...
- 1,602
4
votes
Quality control - non-normal distribution
It looks like you are confounding Capability and Statistical Process Control.
Shewhart Charts or Control Charts typically plot what is assumed to be Gaussian data with control limits of $\pm3s$. ...
- 1,602
4
votes
Why isn't bayesian statistics more popular for statistical process control?
One reason is that Bayesian statistics was frozen out of the mainstream until around 1990. When I was studying statistics in the 1970s it was almost heresy (not everywhere, but in most graduate ...
- 41
4
votes
"Random variable" vs. "random value" (when translating from Russian into English)
The correct phrase in order to make statistical sense, is "random variable". And this is because it refers to the "mean line" - and random values do not have a mean, only random variables do.
If ...
- 56.5k
3
votes
Closed formula for D4 constant calculation? (Moving range chart constant)
I know this is a closed answer, but just to extend a little bit of the discussion, and because it's also one of my favorite subjects I would like to add an article I found.
The article it's called: ...
3
votes
Problems with Outlier Detection
@Jerome Baum's comment is spot on. To bring the Gelman quote here:
Outlier detection can be a good thing. The problem is that
non-statisticians seem to like to latch on to the word “outlier”
...
- 20.7k
3
votes
One-class KNN for Quality Control
At the very heart of LOF you will find "k-distance", the distance to the k-nearest neighbor.
The idea of using the k-distance is older than LOF. And the range 10..50 may be a good choice for LOF, but ...
- 41.7k
3
votes
Accepted
How to find the time to failure of a component using mean failure time
What time it will fail will be a random variable, so you can't say what time it will fail.
You may be able to say something about the distribution of the time to failure, including its expectation, ...
- 275k
3
votes
Accepted
"Random variable" vs. "random value" (when translating from Russian into English)
I side with your editor. You plot the obtained values on the plot, then draw a mean (average) line, then calculate three standard deviations above and below the line to show the boundaries. There's ...
- 59.3k
3
votes
Accepted
Non-normal distributions vs data transformation
If you want to use parametric statistics, you assume some underlying distribution. You should therefore always try to use a model with a distribution that makes sense given the process that you are ...
- 10.7k
3
votes
Accepted
Average Sample Size For Curtailed Double Sampling Plan
This comes down to an analysis of "curtailment" (which is a simplified version of sequential sampling). Let's focus on that first. Because I think your reference is incorrect, I will be ...
- 313k
2
votes
How can root mean square error be used to predict logistic regression model accuracy?
If I understand correctly, the situation is that you have an estimated logistic regression model that you use in production. So you need a system of quality control that can tell you if the model ...
- 73.5k
2
votes
Dealing with zeros in a poisson regression
Either (as mentioned in a comment by @Glen_b) use Bayesian methods, or some kind of borrowing strength, that is, analyzing multiple data sets with a common model, with some common parameters (that can ...
- 73.5k
2
votes
How can we say that a clustering quality measure is good?
If you don't have access to the ground truth (i.e. the cluster to which each data point belongs to), there's not much you can do. Those evaluation metrics are not meant to deliver an absolute value: ...
- 951
2
votes
Accepted
Closed formula for D4 constant calculation? (Moving range chart constant)
Repeat the question:
So you want a form for the D4 coefficient for a Shewhart moving range control chart?
Answer:
Here is a table (link), and you can make a really fast lookup for windows within the ...
- 8,613
2
votes
What is the mathematically rigorous definition of chunky data?
In your case it is called quantization, a common issue with signal processing. Typically you see evenly spaced data (even when you get no multiplicities).
In general (is there are many points close ...
- 5,716
2
votes
When is a single data point enough to be considered a trend in the data?
My wife worked as a Medical Laboratory Technologist for several years. There are many tests that are not required once the test meets a desired threshold unless other indicators exist. These values ...
- 1,602
2
votes
Where can I find tests that validate the output of popular statistical software? (e.g. R, SPSS, SAS)
It's also a good idea to check algorithm documentation or, for open source, to read the code if in doubt as packages differ in exact definitions, terminology, and computational details, especially for ...
- 1,369
2
votes
Accepted
Reference to Statistical Control Quality
May be you can get some useful things in the book Design and Analysis of Experiments, by the same author. It not only introduces some more advance techniques such as Factorial design, block and ...
2
votes
Quasi-experimetal Research is it necessary a control group?
There are two distinct issues here. The first is the meaning of the term "quasi-experiment". Quasi-experiments, at least in the way the term was used by Don Campbell who created it, includes numerous ...
- 1,728
2
votes
Accepted
How to test for deviation from a uniform distribution?
What you propose looks OK. Since there is no estimated parameters, the number of degrees of freedom should be $10000 - 1$. Then you can find p-values from the $\chi^2_{9999}$ distribution.
But your ...
- 73.5k
2
votes
If the population size was large enough that the sample size required to represent it is too large to be practical, what should be done?
One of the lovely things about sampling theory is that it demonstrates that you can make good inferences from sampling, even with a very large population and a correspondingly small proportion of ...
- 116k
2
votes
Accepted
Quantifying agreement between datasets from different methods of measurement
The Bland Altman plot is a much more nuanced tool for examining agreement between different methods. It allows you to examine bias as well as agreement. You can understand if the agreement is uniform ...
- 3,143
2
votes
What do the letter and the subscript in the Shewhart's control chart constants ($A_2, A_3, c_4, c_5, \ldots$) mean?
Note: This is a partial answer.
Wikipedia mentions Duncan, A. J., Quality Control and Industrial Statistics 4th Ed., Irwin (1974) ISBN 0-256-01558-9, p.139.
An older edition of this book contains a ...
- 546
2
votes
Accepted
three sigma vs six sigma
Exactly, it's related to the number of sigmas to reach the LSL/USL from the mean of the distribution B compared to distribution A. There is an excerpt from the Wikipedia page that explains this fairly ...
- 968
2
votes
Accepted
Using standard deviation to calculate Control Limits for Individual Control Chart
The NIST Chapter on "Process or Product Monitoring and Control" is a useful reference on this topic. As explained there, it often is preferable to use estimates of $\sigma$ based on the ...
- 84.2k
Only top scored, non community-wiki answers of a minimum length are eligible