Usage and meaning of specific technical words/concepts in statistics.
1
vote
0answers
37 views
Rotational invariance of PPCA
From here (slide 23) and here (page 5, 4th slide) I understand that it is said that PPCA (probabilistic PCA) is rotational invariant. It can be written as follows:
$$\text{PPCA}(X) = [\mu, W, \sigma^...
0
votes
0answers
31 views
Is there a name for the following “truncated” distributions?
Given a distribution $d$ on non-negative numbers and a threshold $t > 0$, I define the "truncated" distribution $d_t$ where
$\left\{
\begin{array}{ll}
d_t(x) = 0 & \mbox{when} \ x ...
1
vote
1answer
39 views
Factor-loadings vs Variable-loadings
In PCA and Factor Analysis, there is the term loadings, which refers to factor loadings (onto the original variable).
Does the term (original) variable loading (onto the latent factor) exist?
1
vote
2answers
34 views
What exactly is called “embedding” in dimensionality reduction?
In the following slide I do not understand the definition of the term embedding.
In the third paragraph, it says it is a mapping from low-dim. to high-dim, but in the last paragraph it suggests that ...
-1
votes
0answers
19 views
How are neural networks taking probabilities as inputs called?
I have been recently reading on different types of neural networks, and was wondering whether a type of deep architectures taking as input probability distributions instead of raw data have a ...
1
vote
0answers
29 views
What does the word “MNIST” stand for “MNIST database”? [closed]
I read about "MNIST database" on this Wikipedia page which says "MNIST" stands for "Modified National Institute of Standards and Technology". But I see someone uses "MNIST" as "MNIST database" in ...
2
votes
1answer
10 views
Term for one snapshot of dynamic data
I want to introduce the data I have taken from a dynamic dataset (GitHub repos) at 12pm today. I want to say the equivalent of "This is the data as of 12pm Sept 4" but am wondering if there is a ...
1
vote
1answer
31 views
Technical term for an assumption about probabilities?
There is a term of art that I either never learned or forgot, referring to an assumption in the context of estimating probabilities. I cannot find it in a quick search of Wiki on, for example, the ...
0
votes
0answers
17 views
In a distribution what do I call regions with high probability mass, that contain smaller peaks within them?
Suppose I have some multimodal distribution as shown below.
It has two regions of high probability, highlighted in purple.
And within those regions are smaller peaks, highlighted in green.
Is there ...
1
vote
1answer
37 views
Layman's explanation on stochastic and statistical models
What's the differences between stochastic models (process) and statistical model (analysis). As I understand, a stochastic model (process) simply means it involves random variables, which is basically ...
1
vote
0answers
19 views
optimizers in deep learning [duplicate]
I'm new to the deep learning field and I've a question that I didn't get for it a clear answer or explanation in the course, I understand the tensors and the idea behind batches but I don't really get ...
0
votes
0answers
18 views
Confusion over terminology for time series classification
This probably is due to my lack of a reference textbook for statistical modeling of time series, anyway I'm not sure which terms we use to distinguish between two different time series classification ...
0
votes
0answers
40 views
Are Bias-Variance trade-off and Mean Squared Prediction Error (MSPE) the same?
I was reading about the Bias-Variance trade-off in the textbook "Elements of statistical learning". Is the expected forecast error listed there the same as the MSPE?
3
votes
0answers
28 views
What exactly should be called “projection matrix” in the context of PCA?
At the end of the PCA algorithm one gets a $D\times d$ matrix $U$ such that $z=U^Tx$ (here $x$ is $D$-dimensional and $z$ is $d$ dimensional with $d\leq D$). In multiple sources on the Web I found ...
0
votes
1answer
29 views
Clarification on “intercept”?
I'm currently reading "Competition-Based Dynamic Pricing in Online Retailing: A Methodology Validated" by Fisher, Gallino, and Li. In the paper they mentioned that variables $\alpha_j$ and $\alpha_r$ ...
0
votes
0answers
10 views
Exogenous Switching Treatment Regression
Can anyone explain what this term means? I was reading the paper "What Determines Gender Inequality in Household Food Security
in Kenya? Application of Exogenous Switching Treatment Regression" https:/...
1
vote
1answer
86 views
What's the definition of “Dynamic Regression Models”?
I am trying to learn about Dynamic Regression models. However, the sources on the topic is (relatively) few compared to other TS topics, and so I cannot really get a grasp of where to start. I really ...
1
vote
0answers
14 views
Difference between Beta process and Beta regression?
In a layman language, how the difference can be defined between statistical process and the same named GLM such as poisson processes and poisson regression or beta processes and beta regression? How ...
1
vote
1answer
70 views
Meaning of “Logistic regression and Cox proportional hazards regression models were multivariable adjusted for age, gender ..” etc
From the abstract to the study titled "Association between the antioxidant uric acid and depression and antidepressant medication use in 96 989 individuals":
We examined plasma levels of the ...
9
votes
2answers
851 views
“Liberal” p-values?
My question is rather semantic. When a method routinely produces high p-values it is called conservative. Would you call the opposite, i.e. a method with a high type-II-error rate liberal?
4
votes
1answer
46 views
What does this paper mean by mean square error?
I'm reading a paper about estimating fetal weight by ultrasound and other techniques. In Table 2 they give descriptive statistics, to wit: of all the examiners, the one with the highest mean square ...
5
votes
2answers
211 views
Notation in statistics (parameter/estimator/estimate)
In statistics, it is very important to differentiate between the following three concepts which are often confused and mixed by students.
Usually, books denote by $\theta$ an unknown parameter. Then ...
4
votes
1answer
49 views
Is there a known name / keyword to describe continuous manual improvement of the labels used to train a classifier?
It may seem like a very basic question to the machine-learning fellows out there... but:
I'm writing a paper on a computer-vision algorithm that identifies various events in time-lapse images of ...
2
votes
0answers
16 views
Complement of a confidence set: standard name?
In the context of statistical inference, is there a standard name for the complement of a confidence set?
For example, suppose $X$ captures the observed data, $\theta$ the parameter of interest, $\...
7
votes
1answer
144 views
How is the family of distributions with PDF proportional to $(1+ax^2)^{-1/a}$ called?
Consider a family of distributions with PDF (up to a proportionality constant) given by
$$p(x)\sim \frac{1}{(1+\alpha x^2)^{1/\alpha}}.$$
How is it called? If it does not have a name, how would you ...
1
vote
1answer
33 views
Using term “evaluate” instead of “estimate”?
Is it ok or mistake to use this words as synonyms? (E.g. to write "we evaluate variance of the estimator by theorem 1" when I mean that we estimate this variance)?
2
votes
1answer
16 views
Proper names for data - quantile and rank
Say I have data from a sample of 100 experiments. For a variable, I'm interested in showing the value x with 0.9 probability of non-exceedance, which is equivalent ...
0
votes
2answers
79 views
Does generative model have to be machine learning-based?
According to Wikipedia,
Given an observable variable X and a target variable Y, a generative model is a statistical model of the joint probability distribution on X × Y, P(X,Y)
However, as far as ...
2
votes
2answers
56 views
Can I claim Makrov Chain or Hidden Markov Model are simple Recurrent Neural Networks?
If we focus on sequence modeling (discrete time and discrete observations), Can I claim Makrov Chain or Hidden Markov Model are simple Recurrent Neural Networks (Because both of them have "time ...
0
votes
1answer
23 views
Autoregressive vs integrated time series model
An autoregressive series is of the form
$$
X_t = c + \varphi_1 X_{t-1} + \varphi_2 X_{t-2} + \cdots + \varepsilon_t
$$
An integrated series is of the form
$$
(1-B)^d X_t = \varepsilon_t
$$
...
0
votes
1answer
18 views
How do we call when one model is trained by another?
Suppose I have one model (say, for image classification) as black box. I don't posess it and don't know it's parameters. Suppose it is web API.
Then I take bunch of images, classify them by this ...
28
votes
7answers
3k views
In Regression Analysis, why do we call independent variables “independent”?
I mean some of those variables are strongly correlated among themselves. How / why / in what context do we define them as independent variables?
3
votes
1answer
33 views
Are “feasible generalized least squares” and “iteratively reweighted least squares” the same thing?
These two techniqies seem closely related:
Iteratively reweighted least squares (IRLS)
Feasible generalized least squares (FGLS)
Are the mathematics the same, just different communities (math or ...
1
vote
0answers
28 views
Meaning of “13-term Henderson filter” [closed]
I wonder what the "13" stands for in the "13-term Henderson filter" seasonal adjustment method. I don't understand the meaning of "13" in this method.
1
vote
0answers
26 views
Log-normal vs. log-linear vs. logging the response variable
I've been reading a lot of Wikipedia pages and StackExchange/CrossValidated posts, and I have come to a point where I realize I do not understand some of the terminology I have been using.
What's ...
0
votes
2answers
53 views
What does scale exactly mean?
I am not so familiar with statistical concepts. I am preparing a questionnaire to measure underlying constructs that affect pedestrian's road crossing behavior. However, I came across this term called ...
0
votes
2answers
66 views
The word for “not well-described by statistics”
I used to know this 25-cent word, and I have forgotten it. It describes a phenomenon where common descriptive statistics like mean and variance misrepresent the individuals or maybe the phenomenon ...
0
votes
1answer
51 views
Can redundant/irrelevant features be called a Noise?
Let's say we want to predict job applicant' salary. We have a dataset with following features:
{Age, Experience, Education, Astrological_Sign, Weather_Today}
5 features in total.
In this set, ...
0
votes
0answers
35 views
Understanding how cross-validation works - do I test the entire data set after cross-validation?
QUESTIONs: I will appreciate help on the correct flow on how to create 5 different splits of the data for imbalanced dataset especially or in general and a clarification if in each new run the ...
1
vote
0answers
18 views
Name and proper notation for multidimensional systematic sampling
I'm trying to find the official name and formulation of the following sampling technique. I believe it is simply referred to as "systematic sampling", but failed to find a reference describing it ...
4
votes
3answers
101 views
How do I call a forecast that is both accurate and precise?
How do I call a forecast (more precisely, a forecasting rule) that is both accurate and precise?
Is there a word that expresses both properties combined?
I do not mean the forecasting rule is perfect,...
20
votes
1answer
869 views
Why the names Type 1, 2 error?
What is the motivation of introducing an additional level of indirection from the descriptive 'false positive' to the integer '1'? Is 'false positive' really too long?
2
votes
1answer
18 views
Is there a standard name for a certain parameter for the beta distribution?
The beta distribution is $$ (\text{constant})\times x^{\alpha-1}(1-x)^{\beta-1} \, dx \quad\text{for } 0\le x\le 1. $$
Supposing $X$ to be so distributed, one has
\begin{align}
& \mu = \...
0
votes
0answers
24 views
Raising average: organic approach vs outlier
I'm having trouble articulating a statistics concept concerning averages. As far as I know, there are two ways to raise the average:
observation by observation (imagine adding +1 to all observations)
...
3
votes
1answer
287 views
In trouble with CDF graph
I'm trying to understand the meaning of this graph, which is a CDF (Cumulative Distribution Function). But I can't.
Why is it starting from the top-left corner? I've never found such a graph.
And ...
0
votes
1answer
45 views
Using apriori algorithm for market basket analysis
While I was studying the formulation of market basket analysis problem in the book Elements of Statistical Learning in the chapter unsupervised learning, I came through the following statement:
...
3
votes
1answer
86 views
Terminology, is this a mixed effects logistic regression?
I have built this model in R and I am getting confused with the terminology.
For each individual ID I have a number of failures ...
0
votes
0answers
19 views
Non-target attribute is imbalanced, is it class imbalance or is there another term?
I have come across the term class imbalance in classification problems. From what I understand, it means the target variable is split into two (or more) categories where on category is significantly ...
0
votes
0answers
15 views
Terminology of fixed vs random effects panel data?
In short, in a fixed effects model, the individual effect is correlated with the regressors, while in the random effects model it is uncorrelated.
But what does "fixedness" have to do with the fact ...
1
vote
1answer
121 views
Meaning of 'sparse' vs 'dense' data / matrices
In the context of the Scikit-learn library documentation, what do the terms "sparse data" and "dense data" mean? For instance, taken from the entry on feature selection:
If you use sparse data (i.e....
