Refers to the conditions under which a statistics procedure yields valid estimates and/or inference. E.g., many statistical techniques require the assumption that the data are randomly sampled in some way. Theoretical results about estimators usually require assumptions about the data generating ...

learn more… | top users | synonyms

2
votes
1answer
26 views

Is it ok to spit non-normal variables in tertiles and put them into multivariate regression models?

I am now reviewing a paper in which the authors decided to predict a DV through linear regression using, beyond other variables, dummy variables obtained from a tertile split of continuous variables, ...
1
vote
0answers
25 views

Can mean values be seen as a form of PCA with a LOT of assumptions?

This question just occurred to me out of the blue. PCA is a way to reduce dimensions. Another way that is often (perhaps too often) used is to take mean values of two or more variables. This is done a ...
2
votes
1answer
50 views

Mann-Whitney test

I am carrying out a study in which I have $3$ groups $n= 2$, $n= 5$, $n=17$. Each group has a different inner ear abnormality, following the fitting of an ear implant I have measured their speech ...
2
votes
3answers
61 views

What to do when I have expected count <5 warning for a chi squared test?

I applied a survey consisting of 12 questions to 120 people and each questions include 4 nominal categories; I want to make comparison of people's answers according to their socio-demographic ...
0
votes
1answer
26 views

T test assumptions

I'm performing a t-test on a time series with a sliding window (i.e. every N samples, perform a t test). I know that overall, the samples are roughly normally distributed, however adjacent samples ...
2
votes
2answers
59 views

Same dataset analysed with four different linear models

I've analysed the same dataset (diamonds from ggplot2) in R with four linear models. Each model has a different error structure. ...
3
votes
2answers
172 views

Checking residuals for normality in generalised linear models

This paper uses generalised linear models (both binomial and negative binomial error distributions) to analyse data. But then in the statistical analysis section of the methods, there is this ...
1
vote
0answers
35 views

Forecasting and auto-correlation [duplicate]

I'm reading this chapter forecasting principles and practise from a forecasting book. The author has explained a linear regression model. Now this linear regression model will definitely have some ...
0
votes
0answers
32 views

Cross correlation in Stata

I have a cross sectional dataset of investment figures (in $) and a set of dependent variables. The data relates to various years (2000-2013). More than one investment is included in the dataset for ...
2
votes
0answers
21 views

Ways the likelihood ratio test may fail

I have a question related to: Why is a likelihood-ratio test distributed chi-squared? On point 2 of @StasK's answer, he states: The theorem assumes that all the relevant derivatives are ...
5
votes
1answer
246 views

Is it ever okay to ignore heteroskedastic residuals and continue with analysis?

My data is misbehaving and I can't seem to get residuals with constant variance despite doing more transformations than Optimus Prime. Is it ever okay to just continue with analysis in and just make a ...
4
votes
1answer
131 views

What is the minimum viable cell size for 2x2 ANOVA?

I have a 2x2, between-subjects experimental design (2 independent variables (IVs) with 2 levels each) and one dependent variable (DV). My data are unbalanced and an interaction between the IVs seems ...
2
votes
1answer
34 views

residuals plots from four linear models

I've made 4 linear models. For each of these models, I've plotted the residuals against the fitted values. First plot: generalised linear model with quasibinomial link function Second ...
0
votes
0answers
46 views

Fit of negative binomial regression model

I have ran a negative binomial regression. I'm guessing the use of a negative binomial regression is not ideal given my design, but I'm hoping I can 'get away with it', as it seems to be working ...
1
vote
1answer
49 views

What are the important conditions in ANOVA fixed effects?

I am working with an ANOVA model. I want to run a fixed effects ANOVA in which I have a ratio dependent variable and three independent variables with two and three levels. Obviously, before analyzing ...
3
votes
0answers
32 views

How can one test the assumptions of a zero-inflated negative binomial model in R?

I have fitted a zero-inflated model with a random effect using a negative binomial distribution in R, using the function glmmadmb. This is due to a large number of zeros and over dispersion. For a ...
4
votes
1answer
102 views

Normality assumption in linear regression

As an assumption of linear regression, the normality of the distribution of the error is sometimes wrongly "extended" or interpreted as the need for normality of the y or x. Is it possible to ...
2
votes
1answer
66 views

transformation to normality of the dependent variable in multiple regression

Is it really important to normalize dependent variables in multiple regression or are there any exceptions? My model is providing better results with more significant hypothesis when the DVs are not ...
6
votes
2answers
167 views

Choosing between $z$-test and $t$-test

Background: I'm giving a presentation to colleagues at work on hypothesis testing, and understand most of it fine but there's one aspect that I'm tying myself up in knots trying to understand as well ...
9
votes
4answers
327 views

Regression residual distribution assumptions

Why is it necessary to place the distributional assumption on the errors, i.e. $y_i = X\beta + \epsilon_{i}$, with $\epsilon_{i} \sim \mathcal{N}(0,\sigma^{2})$. Why not write $y_i = X\beta + ...
1
vote
1answer
35 views

should both scores of 2 time points be of same scale in mixed ANOVA

I am running mixed ANOVA as repeated measurement analysis for cognitive score at 2 time points for 2 groups (blood pressure low vs. High). The the score at time 1 was normally distributed and at time ...
3
votes
2answers
150 views

Linearity between predictors and dependent variable in a linear model

I run the following linear model in R : lm(formula = NA. ~ PC + I(1/SPCI), data = DSET) The p-value for each predictor is significant, and it works fairly well ...
2
votes
4answers
172 views

Is “ independent and identically distributed” an assumption or a fact ?

This is in the context of two random variables. A frequent assumption (e.g. of the error term in ANOVA) is of independent and identically distributed random variables. There is a question on this site ...
1
vote
1answer
75 views

What could cause different conversion rates for the same content in separate split tests?

We have an events based tracking system for our website, with split testing built-in and we are using ABBA for the calculations. The problem comes up when we are doing consecutive split tests. For ...
5
votes
2answers
189 views

ANCOVA in observational studies: what are the assumptions?

Using ANCOVA when groups differ on the covariate is controversial, although Tabachnick and Fidell write that this is a plausible function of ANCOVA in quasi-experimental (or observational) studies. As ...
1
vote
0answers
38 views

How to check the assumption of equal error variance might be violated?

I want use this box plot to check it. Thank you
0
votes
1answer
130 views

Checking assumptions LMM: residual plot with diamond shape

I am running a linear mixed model and want to check its assumptions. The model I run is comparing if males and females behave differently over time (timeclass=1,2,3,4): ...
0
votes
0answers
37 views

Mean of residuals in quantile regression are significantly differ from 0

Is it necessary to have mean of residuals which is equal to 0 in Quantile regression?
2
votes
3answers
871 views

Checking assumptions lmer/lme mixed models in R

I ran a repeated design whereby I tested 30 males and 30 females across three different tasks. I want to understand how the behaviour of males and females is different and how that depends on the ...
7
votes
2answers
212 views

Why some people test regression-like model assumptions on their raw data and other people test them on the residual?

I am a Phd Student in experimental psychology and I try hard to improve my skills and knowledge about how to analyze my data. Until my 5th year in Psychology, I thought that the regression-like ...
0
votes
2answers
355 views

What are the assumptions of ARIMA modeling for forecasting time series?

What are the assumptions of ARIMA / Box-Jenkins modeling for forecasting time series?
0
votes
1answer
17 views

Name of a tool to find out the best power to use in order to normalize a variable

It should be an easy question. I am looking for the name of a tool. It is used to normalize a variable with the best possible power. I think it uses an iterative process to find out this best power. ...
0
votes
1answer
80 views

Inspecting assumption of homoscedasticity

Using a Fligner test to infer about the respect of the assumption of homoscedasticity is not very smart given that the Fligner test tests to the null that there is no difference of variance between ...
3
votes
0answers
112 views

Assumption violations with heteroscedastic data and OLS regression

I'm trying to model the typical performance of an experimental approach I've developed. I have a total of 3000 observations for 72 different case studies. My observations consist of a reading for ...
1
vote
1answer
45 views

Fligner.test with R

Why does this: fligner.test(a ~ b + c + d, data=df) and this fligner.test(a ~ b + d, data=df) always equal for whatever ...
1
vote
0answers
74 views

Anova. Homoscedasticity not respected

I'd like to perform an ANOVA with a normally distributed response variables and several explanatory variables. Some of the explanatory variables are continuous and some are categorical (factor(..)). ...
1
vote
0answers
142 views

Diagnosis of normality assumption and fitting linear regression in R

I am using the data veteran from R package survival. How can I diagnose the normality ...
1
vote
0answers
52 views

Need to verify sample is representative of known population of animals

I'm a biologist trying to verify that the age, gender, and family group of my samples from a population of whales is representative of the population, in order to make inferences in the discussion. ...
2
votes
1answer
140 views

What is an intuitive explanation of why we want homoskedasticity in a regression?

I've read that homoskedasticity means that the standard deviation of the error terms are consistent and don't depend on the x-value. Question 1: Can someone explain intuitively why this is necessary? ...
1
vote
1answer
86 views

In regression, if the residuals are correlated with X then what assumption has most likely been violated?

independence homoscedasticity This question is from an online quiz with one "correct" answer, but I'm not sure I agree. I understand that the answer is homoscedasticity, but isn't independence ...
2
votes
4answers
215 views

Linear regression with strongly non-normal response variable

I have carried out a linear regression. The plot below shows the distribution of the response variable: I believe the response variable is beta distributed, therefore virtually the exact opposite ...
0
votes
0answers
75 views

MANOVA multivariate normality

I'm running some analysis of student data and I'm having some questions regarding multivariate normality assumption of MANOVA. Should it be done using values of dependent variables or their residuals? ...
0
votes
3answers
93 views

Simple regression assumptions (homoscedasticity)

There is a simple regression model table I was looking at in a textbook with IQ values grouped into 5 intervals and each group had an N number associated with it. There was also information given ...
1
vote
3answers
52 views

Choice of a less true model over the truer model if it predicts better and my purpose is prediction

Sometimes a less true model predicts better than a truer model (When will a less true model predict better than a truer model?). So should I choose a less true model over the truer model if it ...
1
vote
0answers
24 views

ANCOVA with repeated measures IV, violation of slopes

I am running a 2x2x5 mixed factorial ANCOVA, with one within-groups variable, and two between groups variable. I want to check for violation of homogeneity of regression slopes. My covatiate does not ...
0
votes
0answers
60 views

Violation of too many assumptions?

I'm trying to determine whether I should be using an ANOVA or a non-parametric test. My DV is rating of confidence on a Likert scale (1-5), and 4 categorical IVs (n = 496). Data distribution within ...
1
vote
0answers
43 views

Transforming data to meet regression assumptions for SEM including interaction effects

If you are fitting a SEM and wish to add an interaction effect between two variables, I understand that you convert the variables to z-scores, multiply them together and insert this new variable into ...
0
votes
0answers
24 views

Schoenfield Residuals test for discrete-time hazard model

I have estimated a discrete-time hazard model. Now I would like to test the data for the proportionality assumption of the model. I have found a test, using the Schoenfield residuals to test this ...
0
votes
0answers
44 views

Test for unobserved heterogeneity in proportional hazard model in R

I have modeled a discrete-time proportional hazard model in R. Now I would like to test the assumption of no unobserved heterogeneity. Does anyone know a test for unobserved heterogeneity? Does ...
0
votes
0answers
54 views

Augmented component plus residual plots

To test for linearity, it has been suggested that augmented component plus residual plots are the best option (acprplot in Stata). Should this analysis be done for ...