Tagged Questions

Refers to data generated from a distribution that has a countable sample space. Discrete data may be nominal (e.g. the distribution of race in a sample of individuals) or ordinal (e.g. the number of errors on a page of text).

learn more… | top users | synonyms

2
votes
0answers
21 views

Discrete Choice Models

for mulitnomial (or mixed) logit models, when the choice set is too large, either strategic sampling or random sampling of the choice set can be used. My question would be: Is that also true in ...
3
votes
0answers
20 views

Estimating a probability distribution with a discrete and continuous part

This is a question more for advice and a suggested starting point than anything else (though anything else is cool as well ) The data that I have is something like this - 1,000,000 data points of ...
6
votes
2answers
125 views

5 defectives rule of thumb

I have taught six sigma black belt classes using consultant sourced training materials which included the rule of thumb that when estimating the rate of occurrence of discrete events, like the ...
1
vote
1answer
22 views

Calculation of Higher-Order Cross-moments

How can I calculate standardized central cross-moments for 2 time-series? The 4th-order standardized central moment, kurtosis, is; ...
-1
votes
1answer
46 views

Median and mode

Consider grouped data with frequencies and more specifically data that are discrete. If I have for example different xi with the same frequencies, what is the right answer: there is no mode or all ...
1
vote
1answer
67 views

Power-law fitting and testing

I want to test the distribution that best fit a specific metric (that I call SD) extracted from the source code of systems. I have a guess that they follow a power-law behavior. My sample: 20 ...
0
votes
1answer
28 views

Discrete Variables and Regression

I have only discrete independent variables (gender, religious affiliation etc) and continuous dependent variables. Is it possible to use a regression model?
1
vote
0answers
18 views

How to compare a one-day count against a historic mean to identify an external change

A few months ago a client's website had some good press and their daily site visits spiked. Now, every time their traffic shows a bump, they think something external has caused it to happen. I'm ...
1
vote
0answers
17 views

Transforming data with a limited range (0,1,2) for parametric testing (ANOVA) [duplicate]

I've collected data on accuracy of recognition of images. Accuracy is a score out of 2 with points 0,1,2.. participants can score a 0. I am aiming to use a parametric test (ANOVA mixed design) to ...
0
votes
0answers
8 views

MNL discrete choice with quasi-SUR 4 equation system, looking for R package that can handle such a system

I am attempting to recreate the model in this paper: Pinjari (2011) in which the author uses a 4 equation system with discrete choice dependent variables in each of the 4 equations. Does anyone ...
1
vote
1answer
61 views

Can I still interpret a Q-Q plot that uses discrete/rounded data?

I have a data set with only discrete/rounded values in it. As a result, when I produce a Q-Q plot a "stair-case" pattern appears. Can I still interpret this just like a normal Q-Q plot even though it ...
0
votes
1answer
21 views

Correlation or clustering of continuous score and discrete variable states

I have an experiment that produces a decimal score representing quality, and a bunch (5-30) of variables that each take on one of a set of discrete states. - The states are not meaningfully ...
0
votes
0answers
46 views

Clustering method that can use graph links, discrete and continuous properties?

I have an un-weighted, directed graph that clusters ok using MCL or other graph clustering algorithms. However, I also have additional discrete and continuous properties of the nodes being clustered ...
1
vote
1answer
220 views

Plot the probability mass function

I am trying to plot the probability mass function of a sample of a discrete metric. If it was continuous, I know that using pandas it would be as simple as calling: ...
1
vote
0answers
28 views

How can I smooth a set of discrete data points for the purpose of schedule planning?

Disclaimer: I do not have a background in statistics or the math behind filtering, save one long-time-ago college course. I have a well defined problem space. I am calculating hourly staffing ...
1
vote
0answers
24 views

What model to classify a discretized continuous variable

Consider a variable $y$ (typically, $y_i$ is something like number of inhabitants of city $i$) and some given features $X$. Let us assume that these features are continuous (eg. total city area, ...
0
votes
0answers
31 views

How to use Hartemink's discretization algorithm?

From the help documentation of the discretize function of the R package bnlearn: Hartemink's algorithm has been designed to ...
6
votes
1answer
233 views

Question about Dynkin Lehmann Scheffe Theorem

I'm self-studying for an examination, and I would like to understand how to use the Dynkin Lehmann Scheffe theorem for an applied question. I am using Bickel and Doksum's "Mathematical Statistics" ...
0
votes
0answers
44 views

Can Principal Component analyses be applied to a counting trait?

I am analyzing a segregating population of plants coming from an hybridization process. The experiment consists in several field plots (according to an augmented design). In each plot a segregating ...
2
votes
1answer
114 views

Discrete analog of CDF: “cumulative mass function”?

We call the integral of a probability density function (PDF) a cumulative distribution function (CDF). But what's the cumulative sum of a probability mass function (PMF) called? I've never heard the ...
0
votes
0answers
29 views

Conceptual question on image pattern representation

I have a basic question regarding pattern learning, or pattern representation. Assume I have a complex pattern of this form, could you please provide me with some research directions or concepts that ...
8
votes
4answers
639 views

Calculating PDF given CDF

I know that the PDF is the first derivative of the CDF for a continuous random variable, and the difference for a discrete random variable. However, I would like to know why this is, why are there ...
0
votes
1answer
41 views

Correct notation wrt. uniform distribution

Assume that I have a discrete set $L$ and a transformation $\phi: L \rightarrow [0,1]$ that normalizes set $L$ such that now values belonging $L$ are uniformly distributed among the unit interval. ...
1
vote
0answers
27 views

expectation of multivariate discrete distribution

The expectation of a function $f(x)$ over a probability distribution $p(x)$ where $x=(x_1,\dots,x_n)$ and $x_i \in \left\{1,\dots,K\right\}$ requires a summation over all possible $K^n$ combinations. ...
2
votes
0answers
40 views

deterministic sampling for multivariate discrete distributions

Unscented transform can approximate expectations well via deterministic sampling. if $f(x) = N(\mu,\Sigma)$ and $x\in \mathbb{R}^d$ then $\int f(x) h(x) \approx \frac{1}{2d}\sum_{i=1}^{2d} h(x_k)$ ...
1
vote
0answers
53 views

Conjoint analysis or discrete choice analysis ? And which software?

Suppose I would like to model the light-bulb preference of respondents. I would like to ask their preferences between existing bulbs on the market. And when you choose a bulb in a shop you usually see ...
0
votes
0answers
48 views

Which contingency method to use with a 3x3 table yet still account for expected or discrete choice?

Im not sure what test to conduct when I have 3x3 matrix of data and still account for availability. So, in a simple chi square you have an observed observation and then you are often able to ...
2
votes
1answer
104 views

Hazard and density function in survival analysis with discrete time

I am running a survival analysis with descrete time. For that purpose I use the R package survival with this function ...
1
vote
0answers
55 views

A good alternative to data binning?

I read many times that data binning of continuous variables is a very bad idea. For instance, let's take something like heart rate and let's define the following 2 bins: (125 - 135), (136 - 145) ...
0
votes
0answers
103 views

Analyzing discrete choice panel data with mlogit in R

I searched around and saw some high level discussion on mlogit and discrete choice panel models (here and here) but I need a more concrete answer than those. I am hoping somebody can point out what I ...
-1
votes
1answer
62 views

Find the maximum likelihood estimator of $\theta$

Let $(X_1,Y_1), . . . , (X_n,Y_n)$ be a random sample from the discrete distribution with joint probability mass function $$ f_{X,Y} (x,y) = \frac{\theta}4 , \space (x,y) = (0,0)\space or ...
3
votes
1answer
134 views

Bayesian Networks and discretization of variables using K-means clustering

In many approaches to learning Bayesian Networks a solution to tackle continuous variables is to discretize them and apply one of the well established techniques for learning Bayesian Networks ...
2
votes
1answer
41 views

Distribution of MLE of $N$ based on a random sample of size n from discrete uniform dist.(1,2,…,$N$)

Let $X_1, X_2, ..., X_n$ be a random sample from discrete uniform distribution on $(1,2,\ldots,N)$, where $N$ is an unknown positive integer. Find MLE of $N$ and also find the distribution of the MLE. ...
1
vote
1answer
102 views

Uniform sampling of a set of weighted samples

Consider a two-stage sampling scheme: First, use weighted random selection from a list to obtain a set of N unique elements. Next, use uniform random selection to pick one of those elements. How can ...
0
votes
0answers
60 views

POISSON regression with offset variable

Our problem is to determine if there is a relationship between the return on equity of firms (ROE) and the presence (number of indicators used) (Y) of a specific type of indicator showing up in the ...
1
vote
1answer
24 views

How to test if a value is over-represented in one sample vs another

I have two multinomial data samples that both have N discrete categories. I know that a Kolmogorov-Smirnov test will let me know if the distributions of the two ...
2
votes
0answers
30 views

Metric optimization on discrete learning sample

There are a set of ("artifical") not Minkovski (triangle inequality is not guaranteed) metrics defined on set of objects. There are one etalon ("natural") metric, which estimation is known only for ...
3
votes
2answers
211 views

How to decide on the MLE when pmf is 0?

Suppose you have $\theta=\{1,2\}$ and the sample of (0,1,2) with the task of finding MLE: \begin{array} {|c|c|c|} \hline x & p(x|\theta=1) & p(x|\theta=2) \\ \hline 0 & 1/2 & 1/4 \\ ...
0
votes
0answers
25 views

Test for one category

I am doing a research in linguistics and I am not to sure what test to choose in the following problem. There is a group of 26 students. They are asked a question and two possible variants are ...
1
vote
1answer
114 views

What methods exist for finding optimal splits to discretize continuous data with respect to a target variable

I'm doing some research into methods for discretizing a continuous variable coupled with a binary target variable to find the optimal split points to maxamise a measure of impurity (gini/entropy). ...
6
votes
2answers
130 views

Accurately generating variates from discrete power law distribution

What are the best methods to accurately generate random integers distributed according to a power law? The probability of getting $k$ ($k=1,2,\ldots$) should be equal to $p_k = k^{-\gamma} / ...
0
votes
1answer
241 views

3-4-5 Rule How to partition the sets?

In Data Mining course, we are taking 3-4-5 Rule to segments the data uniformly. I'm trying to understand these lines below, and how they are linked to the graph below too. If an interval covers ...
0
votes
0answers
191 views

Fitting normalized data to discrete distribution

I have a graph which represents a P(x) vs. x data where x can have 10 possible discrete outcomes. Data looks as follows: {{200, 0.0058668}, {306, 0.0503333}, {411, 0.163055}, {520, 0.203411}, {624, ...
2
votes
1answer
114 views

One-way ANOVA appropriate?

I am assessing the performance of a hospital ward over 6 years. There have been two sets of changes to the ward over this time: after year 2 and after year 4. I have collected data in 4 sample ...
0
votes
1answer
67 views

Statistical test for testing equal proportions

I have a questionnaire item (N=6572) for which: 5064 (77.1%) subjects responded to the question, and 1508 (22.9%) subjects did not respond to the question. What statistical test should i use to ...
1
vote
1answer
109 views

Change detection for beginners

I've seen Change detection algorithm - likelihood ratio but I am afraid my question is more basic. I have a sequence $(x_j)_{j=1..N}$ of random observations. I know, these observations are not all ...
1
vote
1answer
130 views

Calculating discrete hazard rates problem

I am working on an assignment for a Stochastic Modeling class and am stuck on the following question: Let $X$ have probability mass function $p_j = P \lbrace X = j \rbrace $ for $j \geq 1$. Let ...
5
votes
1answer
94 views

Sufficiency of order statistics

I am told the following proof is incorrect, but I cannot understand why. Consider $X_{(1)}, \ldots, X_{(n)}$ are the order statistics of a random sample of size $n$. I want to show that the order ...
0
votes
1answer
43 views

sum of discrete random variables - am I thinking right?

I have thirty discrete random variables for a risk management application. Each of the random variables may have a value $0$ (with probability $p_1$) or $X_i>0$ (with probability $p_2$). All thirty ...
0
votes
0answers
57 views

Exponentially weighted average of data stream variance

For modeling a sequence of data, I once heard the technical term of "exponentially weighted average of the data stream variance". It is defined recursively as I am not clear why does this recursive ...