Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [ranking]

Ranking is ordering data from highest to lowest or *vice versa.* For questions about *constructing* scores to use in ranking, please use the [rating] tag, too.

1
vote
0answers
29 views

What statistical tools are available to remove bias from a dataset?

Three managers report to me. They have done appraisal of staff under them giving them a percentage. I have to sign-off those ratings but I face two major issues: The managers have a certain way of ...
0
votes
0answers
19 views

Ranking Algorithm using Visitors Count and Demographic Population - Using Bayesian Average

I have a sample data-set, which consist of 10 Attractions, which I have to rank based on Visitors Count and Demographic Population (Population of the Planning Area in which the Attraction is located). ...
0
votes
0answers
15 views

Ranking Localities using Regression [closed]

I have a data-set which consists of multiple localities along with various features and I would like to rank each locality based on input features. Sample Data ...
1
vote
0answers
21 views

Ranking on a 3 point scale

Apologies in advance, my background is in CS rather than statistics, so I may use some terms improperly. I have a data set of a few thousand items scored on a 3 point scale, which my research ...
0
votes
0answers
31 views

Correlation of two values with opposite rank/rating

Consider the following set: ...
2
votes
1answer
24 views

Which metric to use in an ordering problem? auPR / ROC / Lift?

I need to order Users from most likely to perform a binary action X in the next n days, to ...
0
votes
0answers
6 views

Understanding percentile computation [duplicate]

I understand percentile in the context of test scores with many examples (eg. you SAT score falls in the 99th percentile), but I am not sure I understand percentile in the following context and what ...
0
votes
0answers
35 views

Statistical test on likert and ranking data

I have data in which survey participants hand to rank (Rank 1 to 3) three specific products. They also answered some 5 point Likert scale questions (from 1: “Strongly Agree” to 5:“Strongly disagree”) ...
0
votes
0answers
16 views

Weighted Empirical Cumulative Distribution Function (CFD): order values before or after weighting? [before]

My input data are some observations of a continuous variable, let's say the number of kilometers of motorbikes. I did a survey and I collected some observations. Somehow, I computed weights for all ...
0
votes
0answers
16 views

LAMBDAMART model gives low training score for queries having large number of candidate documents

I am using LAMBDAMART as the learning to rank algorithm to rank relevant documents for a given query.The model performs well for the queries having lower number(300-400) of candidate documents.However ...
0
votes
0answers
14 views

From unsupervised clustering to a weighted average?

I am in the process of writing my master's thesis, and have stumbled (as one often do..) upon an area of statistics that I am not familiar with. My setup is, that I initially have 2 features which I ...
0
votes
0answers
33 views

Sorting By User Ratings - Overlapping Wilson Confidence Intervals

I'm working on a personal project to rank user ratings on a 5 star scale and have implemented Evan Miller's often-referenced Wilson Score Interval calculation with the help of this comment. My data ...
0
votes
1answer
18 views

testing whether categorical distributions differ

i have data on how a large population (N ~ 1e8) is distributed into (many) categories (i.e. i have count of instances in each category). some categories have low ...
0
votes
0answers
7 views

Ordered aggregated choices given users preferences

I have an issue creating an ordered list by preferences. Let's say I have 3 users (u1, u2, u3) and 10 topics (t1,...,t10). Each ...
1
vote
0answers
24 views

Help analyzing data ranked on a scale

So, I thought it would be interesting to try an experiment with my family. I baked 13 different kinds cookies this year, and then told my 8 family members to rank from each cookie from 1-13. Is there ...
1
vote
0answers
14 views

how do I determine a ranking from votes by multiple members of a group

I'm having 8 members of a group choose their favorite 12 items from a list in order from 1 to 12. How do I analyze their data and determine the group items' ranking from 1 to 12 ? 1 is most favorite ...
0
votes
0answers
30 views

Analyze Ranking Data

I've some data from an experiment. Users had to use 4 different applications and had to rank these 4 applications in regards to "best overall", "easiest to use", "safest to use" using 1 for the best ...
1
vote
0answers
21 views

Why does rank correlation only depend on copula, and not on the margins, if the margins are continuous

I read that for continuous margins, then Rank correlation only depend on copula and not on the margins. However, it is not the case for the non-continuous margins. Is that because the Kendall's tau (...
1
vote
0answers
20 views

Number of unique values for rank correlation to be valid

Are there any recommendations on a minimum number of unique rank values per variable for either rank correlation coefficient or significance of this coefficient to be valid. Is it recommended to ...
1
vote
0answers
55 views

How to correlate movie taste?

I am looking for the best known way to correlate movie taste, i.e. to determine which people out of a large pool deviate the least from your own movie scores. One site with this purpose is Criticker. ...
0
votes
1answer
30 views

What model should I use?

I was having a discussion with my father about building an index that ranks cities as a function of multiple variables. For example, ranking n=20 cities based on $$$/SQFT and air quality. I would ...
0
votes
0answers
14 views

How to compare the rankings of two groups?

I'm trying to compare the rankings of two different groups (states that voted Democrat and states that voted Republican). What test should I use? Based on some googling, it seems that I should be ...
6
votes
1answer
101 views

Correlation between an observation and its rank in a random sample

Suppose $X_1,X_2,\ldots,X_n$ are i.i.d random variables with an absolutely continuous distribution. We say the observation $X_i$ has rank $R_i$ if $$X_i=X_{(R_i)}\quad,\,i=1,2,\ldots,n,$$ where $X_{(...
1
vote
0answers
30 views

How to quantify the uncertainty in a single value obtained from a large number of simulations

Im a physics student working on a project in which I have to simulate a machine that would order a bunch of molecules according to their mass. I want to get a quantitative measure of how well the ...
1
vote
1answer
35 views

Can two imperfect rankings be combined to produce a better ranking?

So I've got a dataset that can be ranked in two noisy ways $R_1$ and $R_2$. Let's call $R_1$ and $R_2$ functions from the dataset $x \in R^N$ to a real number between 0 and 1. Since they are rankings ...
0
votes
0answers
26 views

ranking metric for a specific use case

I am trying to find the best "ranking metric" for my problem but could not find any existing suitable metric, can someone help. I'm interested in information retrieval. For item there is a "...
0
votes
0answers
14 views

Using clickthrough data for training a ranking function

Suppose that you have clickthrough data in the following form -- (query, clicked url, frequency). I wonder if there is any way of using the data to train a ranking function. Naively, you can treat ...
2
votes
0answers
31 views

What is the name of this test for the probability of differences between lists and is it valid?

And are there any better methods? In a 1969 book about investing, the author Burton P. Fabricand describes a method for assessing the effectiveness of a stock picker. Ask the picker to provide a list ...
3
votes
2answers
67 views

Is ratio of ranks a well-studied statistic?

I have two lists of recommendations: that is, two different algorithms have assigned ranks to the same list of objects. I would like to know if they're similar. I specifically care more about ...
0
votes
0answers
10 views

Fitting heteroscedastic noisy rank data

I am trying to fit a model from a continuous independent variable to a rank that starts from 0 and increases. What the rank indicates and what the independent variable is, is beyond the scope of this ...
0
votes
0answers
59 views

Expected average precision for random ranked list

Suppose we are evaluating the label ranking average precision (LRAP), which is an evaluation metric used to compare a ranked list to a ground truth (binary) label vector. Background and Definition ...
1
vote
0answers
31 views

Using Class Probabilities from Random Forest to do Ranking

Assume that we have set of documents which are being labelled as relevant and non-relevant. Can I used the class probabilities generated by Random Forest in python scikit-learn to rank the documents ...
1
vote
0answers
28 views

Random Forest in RankLib

I am building a LETOR model using Random Forest with RankLib. As we know that the Random Forest gets better with higher number of trees, I got a totally different observation in my case. The ...
0
votes
1answer
20 views

Robustness of ranking based on cross validation set, should I bootstrap?

I have a dataset that I separate into training and validation. I fit several models on the training set and then evaluate their performance on the validation set. When I rank the models based on their ...
0
votes
0answers
14 views

Rank Test for a Matrix

Suppose I have a matrix A corrupted with noise and I am looking for a test that tests the null hypothesis that the matrix A, rank(A)==1 v.s. rank(A)>1. I checked a little the literature and this paper ...
0
votes
0answers
21 views

Directly optimizing over AUC surrogate

This is in relation to this paper I am looking for ways to optimize Recall @ fixed Precision ($R@P$) for a machine learning problem and i didnt want to use accuracy as a proxy for $R@P$. Upon ...
0
votes
0answers
16 views

Somers' D deteriorating for more granular rankings

Background I have 30 observations and I want to compare how much experts and model agree with each other. For Model and Expert I have slots which are $\in [1,4]$ and ranking which are $\in [1,30]$. ...
1
vote
1answer
41 views

Assigning probabilities to processes, when you know which probabilities exist but not which one belongs to which process

I have multiple stochastic processes that can have 2 different realisations. I think of them as coins that can take the values heads or tails. For the example I assume that there are 3 coins. I know ...
1
vote
0answers
27 views

Merging three rankings about economic relations

I am facing a -probably- simple or stupid problem, however I don't have the prequisite knowledge. I would like to make an overall ranking, to compare bilateral economic relations (during a given time-...
2
votes
0answers
48 views

Skill-based ranking system with individual performance

I am attempting to rank players in an online game and have successfully used TrueSkill to create a good ranking system however I would like to take it a step further and let individual performance ...
0
votes
0answers
19 views

Scaling/weighting probabilities

I have data which looks like the table below. I am provided with the likelihood of a game to occur (Prob) and the current time in min for that game (Curr_time_min). I would like to create a formula ...
0
votes
1answer
22 views

Ranking Order Test

I am analyzing my capstone data - I had students, from different grades, rate 6 feedback forms from 1-6, where 1 was the most helpful feedback type and 6 the least helpful feedback type. Is there a ...
0
votes
0answers
13 views

How are ranks defined in Page's trend test?

I'm confused about the two kinds of rank in a Page test with $n$ conditions and $k$ subjects. Wikipedia says the $i$th condition receives a rank $Y_i$ and a sum $X_i$ over the subjects' ranks. In ...
1
vote
0answers
36 views

What is the expected fraction of observations in the top x% that remains in the top x% after a random shock?

I'm struggling with a probability question, and I was hoping someone here could help me out. Here's the setting. Suppose you draw observations from a probability distribution Z and sort these ...
1
vote
1answer
26 views

Score ordinal ranking configuration according to an optimal ranking

I have a list of items, each associated with their optimal ranking in the list. How can I give a score to a given order of the list. For instance, if I know that the optimal ranking is: 4 3 5 1 2 And ...
3
votes
0answers
49 views

Elo-type ranking system that incorporates game score

The Elo rating system is used to calculate relative skill levels between individuals or teams. It can be applied to many types of games and sports, but when applied, it only considers wins and losses. ...
0
votes
0answers
19 views

Score to assess ranking of predicted outcomes

Is there any quantitative measure to evaluate a predictive model's ability rank units correctly. For example, I am trying to predict a continuous outcome. The error of my predicted versus actual value ...
0
votes
0answers
24 views

Pairwise comparison for differences between Coefficient of Variation Ranking between groups

I would like to test whether the ranking obtained by ordering the coefficient of variation of some genes are different or not between two groups, and do it pairwise, so, row by row, and get a p-value ...
0
votes
0answers
36 views

What comparative analysis can I use for rank ordered data, divided into two groups, from a survey questionnaire?

I have a dataset from a survey questionnaire. Let's say I can divide the participants into group A and B based on a screening question. These participants then rank 7 different options in order from ...
0
votes
0answers
10 views

Measuring the cost of the prediction error when picking the maximum value in a sequence

I have several entities denoted as a set $A=\{1, \ldots, K\}$. They form a sequence $(y_n)_{n\in A}$ with $y_i\in \mathbb{R}$. The values of $y_i$ are unobservable and get estimated as $\hat{y}_i$. ...