Questions tagged [scales]

Scales used to express measurements. Usually ratio, interval, ordinal or nominal types of scales are recognized. Dichotomous and count types are sometimes seen as their own. Other classifications exist. [For "scale" as a sum of individual items in psychometry - see also tag 'psychometrics'.]

123 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
10
votes
1answer
409 views

Interpreting regression coefficients based on Andrew Gelman's re-scaling method

I have two predictors in a binary logistic regression model: One binary and one continuous. My primary goal is to compare the coefficients of the two predictors within the same model. I have come ...
5
votes
0answers
164 views

Is there an alternate $\chi^2$ calculation useful for data spanning a large scale?

I have experimental small angle scattering data which provide information about the structure of a molecule. I can use a PDB file of a molecular structure (contains all the atom names and coordinates)...
5
votes
0answers
964 views

Which normalization method for different units (zero, negative, etc.)

Commonly, normalization of ratings seems to mean adjusting values measured on different scales to a notionally common scale. I have different metrics that measure different performance aspects of a ...
5
votes
1answer
1k views

Scale of the correlation coefficient: is “r = .40 is twice as strong as r = .20” allowed/correct?

Some people recommend the following procedure to calculate the mean of several correlation coefficients: transform the coefficients by Fisher's $z$ transformation, calculate the mean of that, and ...
4
votes
0answers
209 views

Finding a scale matrix of multivariate Cauchy distribution given a border of credible region

I want to solve the following problem: I have a multivariate Cauchy distribution, centered at $\mu$, with unknown scale matrix $\gamma$. Now I receive a data point (blue $x$ in the picture) and my ...
4
votes
0answers
5k views

Transforming scores between different rating scales – Importance of response options

I'm working on a meta analysis of the mean of a single variable (using arithmetic mean as the effect size, rather than the relationship between two variables). The attitude I'm assessing has been ...
4
votes
0answers
185 views

Should I run measurement invariance if confirmatory factor analysis is not affirmative?

I have a repeated measures design for a Likert scale with 10 items. This scale is assumed to be unidimensional and this is one of the research questions along with the scales measurement invariance (...
3
votes
0answers
112 views

Understanding the difference between standardization and normalizing for hierarchical clustering

I am trying to understand the difference between normalization and standardization for the hierarchical clustering. I read the documentation and some posts like this and this as well as several SO ...
3
votes
0answers
83 views

What is the intuition behind taking the sum of square roots, squared

In a recent publication, the authors report the following transformation when aggregating across three different scales: Cognitive style level was used as a control variable and captured as ...
3
votes
0answers
227 views

Scale of the response meaning in a GLM

I'm trying to get my head around GLMs. In order to setup the GLM we need a smooth invertible function of the mean which maps $η$ into the scale of the response. I don't really understand what the "...
3
votes
1answer
243 views

How can I scale new data which were not used in training/validating?

I used StandardScaler provided by scikit-learn to scale training and validation data. Then, I fitted a neural network (CNN) model with scaled data for classification. However, in the production stage, ...
3
votes
0answers
832 views

What factor loading is recommended to retaining items in a factor analysis?

I received the following question via email and thought it would be suited to this site: I have a debate with a friend about factor loading and squared multiple correlation. ... In my debate ...
3
votes
0answers
237 views

How do I derive principal components taking account of repeated measures?

I have data from a 24-item (each item ordinal) scale used at two time points in 2 groups - before and after treatment with treatment A and treatment B. I want to capture a core group of symptoms that ...
3
votes
0answers
3k views

How to carry out a Likert scale analysis?

Context: My research aims to assess whether parents who have been involved in a relationship with a social worker are at higher risk of child abuse/neglect. I am trying to establish whether there ...
2
votes
0answers
225 views

Equation for weighted average with normalization(?)

I am trying to understand how I should denote the equation for rescaling the following 7 categories into one value. The final weighted average is 0.57, which is possible by subtracting one and ...
2
votes
0answers
18 views

Does rounding violate the restrictions of an interval scale?

I'm currently working with questionnaire data from the NASA TLX. It uses a graphical rating scale with 100 equally spaced data points, broken up by 21 ticks, leaving intervals of 5. Its manual (p. 4) ...
2
votes
0answers
21 views

Leveling the field for a race competition

I'm not sure if this is really a statistics question, but I can't think of a more fitting Stack Exchange for it. My friends and I at work are having a competition to see who can decrease their one-...
2
votes
0answers
444 views

Reference thesis for outliers in likert scale data

I have a data set that was collected in form of a liker scale through questioners. Now, i am trying to eliminate or identify outliers in my data. By far, from all that i have been able to search, ...
2
votes
0answers
264 views

What is an appropriate way to re-scale ordinal features, for cluster analysis? AND any thoughts on euclidean-distance for ordinal data?

Background I have data from surveys (on political views from CSES) with answers from respondents in ranking-scales, either 0:10 (0, 1, 2, ..., 10) or 0:3 (0, 1, 2, 3). I want to analyze this data ...
2
votes
0answers
48 views

How to handle an independent variable that is partially ordered?

We are currently planning an experiment. We plan with the following variables: An independent variable "treatment" with four values (a, b, c, d) A number of further independent variables for ...
2
votes
0answers
37 views

Using Data on Different Spatial Scales for Econometrics?

Background: Using a Production Function in form of Autoregressive Regression Model for Regional Perfomance Hi, This question is more of a theoretical nature. I have dataset that comprises all data ...
2
votes
0answers
509 views

Do I need to standardize environmental data before canonical correspondence analysis?

I have a dataset of 15 environmental variables (soil physical and chemical properties) and about 25 "species" variables for about 40 sampling sites. I want to do a CCA to analyse the effects of the ...
2
votes
0answers
483 views

Plotting ECDF in R ggplot2, choosing a scale for the Y axis that shows maximum as well as 4-9's, 5-9's, etc

I regularly make graphs of ECDF for performance latencies, where I want to show an upper bound on latency at P(x) < 0.999, 0.9999, etc. As such, I usually scale the Y axis logarithmically to ...
2
votes
0answers
164 views

How to find the correct spatial scale in landscape ecology?

I am currently studying the effect of organic farming on honeybee colonies. I have calculated the percentage of organic land in several buffer areas around the hives (from 100m to 3000m in 100m steps) ...
2
votes
0answers
227 views

Computation of factors after factor analysis

I have run a principal axis factor analysis and I want to form scales for each factor. To be more specific, after having run the FA, I would like to select all items that load in a specific factor and ...
2
votes
0answers
130 views

Comparing two values in a normal distribution after cutting off the tail of the distribution

I'm doing a sports-related analysis about comparing regular-season performance versus playoff performance, in particular which teams tend to do better during the playoffs. Thus, I'm making a "regular ...
2
votes
0answers
101 views

How to scale data in a log-lin regression

I am currently doing exam revision, and I am stuck on a question in one of the past exams. It asks us to data scale the following equation: $\ln W$ = 2.54 + 0.4Educ...
2
votes
0answers
167 views

Is there any “standards” for minimum variance of likert-type measured variables?

I want to develop a questionnaire. Because the target population are children, I used 3-point likert-type scale (0 1 2) for my items. Now I want to remove invariant items (i.e. the items not having ...
2
votes
1answer
448 views

Maximizing Cronbach alpha to select the number of variables that define a given construct

I can't seem to find this anywhere on the internet or in my books. I'm putting together a construct for an underlying variable. Is it acceptable to have a construct with two variables if that ...
2
votes
0answers
87 views

Guess level of measurement of unknown data

i'm writing a few convenience functions for exploring datasets. For that, I have to guess the type of data from the values. What I'm looking for are some good rules of thumb. Some easy cases: ...
2
votes
0answers
191 views

How do I collect data for simple self-survey

I am on a self-experiment quest to solve some health related problems I have, and I want to create a self-survey that I take every day. What's the best way to codify the survey so I can later analyze ...
2
votes
0answers
561 views

How to compute composite score of rank order variables?

I have several rank order items about the use of languages in different contexts. Specifically, respondents were asked to order three languages from most to least used in situations such as at work, ...
2
votes
1answer
2k views

Can a ratio level variable have negative values?

According to Stevens (1946) ratio level variables require an absolute zero. The implication, I believe, is that 0 = an absence of the thing being measured. As such, can ratio level scales have ...
1
vote
0answers
15 views

How to combine both correction for restriction of range and attenuation?

I have two measurements obtained by two different scales that I want to correlate. Because of the nature of the sample I should use both a correction for attenuation and a correction of restriction of ...
1
vote
0answers
8 views

Correlation between subscales

I have used a scale, which includes 3 subscales. Given that the 3 subscales make part of the same,validated instrument, what conclusions can be drawn from the fact that a pair of subscales ...
1
vote
0answers
61 views

best way to combine/analyze multiple datasets that assessed a construct using different scales?

one dataset has a construct X measured with a scale that has 11 items (all rated on a 7-point scale), another one has it measured using a different 5-item scale (rated on a 5-point scale). (and there'...
1
vote
1answer
24 views

Constant-information scale transformation

I was recently introduced to the concept of constant information scale transformations in the book Generalized Linear Model with Examples in R, by Dunn and Smyth. With that, they mention in the book ...
1
vote
1answer
26 views

comparing the performance of a score across different populations

A very well validated score exists. This score predicts mortality after disease A when patients present from country W . The score is a 4 point score. If a subject presents from the community with ...
1
vote
0answers
100 views

Statistically Analyzing Numerical Rating Scale

I'm creating a survey to administer to food inspectors n=30 for an internship project. I want to find their opinions related to food truck and restaurant food poisoning topics and see if their ...
1
vote
0answers
19 views

Interesting and unusual dependent variable--how do you think it should be handled?

We have 2 dependent measures, which are both distributed from -4 to +4 in discrete steps. This is because the values are based on people's responses to four questions about whether they spend more ...
1
vote
0answers
56 views

How do I convert a survey scale [7-point, -3 to 3] to a 7-point scale [1-7]?

I am working with a survey scale that is from -3 to 3. I have a mean value of .94 and I want to identify if there are ceiling effects, but I need to change the entire scale to 1-7 in order to ...
1
vote
0answers
47 views

How to interpret numerical values for a NN regression problem

I'm working a Neural Network for a supervised regression problem. I have to predict the final grade for a student, given a set of attributes from a survey. I have a set of 455 entries and 33 features. ...
1
vote
0answers
42 views

How to represent data with large differences in scale?

For my paper, I want to present my results for two websites, with and without delays, I then go onto optimise that website. For example, normal website with and without optimisations and then ...
1
vote
0answers
254 views

Conversion of yes/no items to Likert scale items

I constructed a Likert scale but unfortunately it had some yes/no items. As a result I have to revise it. Can those yes/no items be re-worded as Likert scale items and would this be considered valid?
1
vote
1answer
47 views

Likert Conundrum?

I am a bit confused as how to derive information from two dependent 7-point likert type questions. The First question asks : How important is the activity to you? The second question aksa: How ...
1
vote
0answers
20 views

scale of one predictor affects significance of another

I have often read that predictors can or should be transformed to ease interpretation of the slope or intercept, or to standardize the coefficients. With this in mind, I attempted to rescale year in a ...
1
vote
1answer
116 views

Log scale not enough

I want to show faster runtimes of a technique compared to another technique. On the x-axis, I have different scenarios and on the y-axis the runtime for each technique in each scenario. The problem ...
1
vote
0answers
245 views

Quantifying internal consistency with multiple raters and continuous rating scales

I have data from an assessment where people are rated by multiple raters on a set of criteria using a rating scale that is (essentially) interval. All people are rated by all raters. I believe that ...
1
vote
0answers
96 views

Change in numerical values and troubles for rescaling data

Here is my problem, a step in the analysis that should be quick & easy, but... I have very various scales in my data and need to rescale my variables to compare them more efficiently in a lmer as ...
1
vote
0answers
49 views

Likert scale with linear form input control

If I want to collect the order of agreement with a statement in a questionnaire, I’d traditionally use an ordinal Likert scale, most likely with classic 5 points, but maybe 4, 6 or 7 and perhaps with ...