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

1
vote
0answers
11 views

When can one use Hochberg's or Hommel's method for adjusting P values?

The p.adjust function in R can produce P value adjustments based on methods from Hochberg and Hommel, which are both more powerful than methods from Bonferroni and ...
3
votes
1answer
25 views

Is this a Random or Purposive Sample? Inclusion-Exclusion Criteria and the Sampling Frame

Introduction I am confused about when a sample is a random sample (i.e. probability sample) and when it is a purposive sample (i.e. non-probability sample). My understanding is that the former allows ...
2
votes
2answers
84 views

Can my Bayesian prior reflect what the data should say rather than what it could say?

Can my Bayesian prior reflect what the data should say rather than what it could say? For example, assume I collect data where $Y_i$ is whether or not student $i$ passed the test and $X_i$ is whether ...
0
votes
0answers
29 views

Is the stationarity condition necessary for estimating logit/probit model?

I'm going to estimate both a logit and a probit model. Since both the models contain lagged explanatory variables, I want to know if the stationarity condition for this variables has to be verified. ...
2
votes
1answer
43 views

Power analysis on chi-squared test with low cell counts

I am hoping to perform a chi-square test of independence on data in a 2x2 contingency table with the following values: ...
0
votes
0answers
15 views

Is it necessary for covariates in an ANCOVA model to be normally distributed? [duplicate]

I am running an ANCOVA model and am trying to remain true to all the statistical assumptions. I noticed that one of my covariates is not normally distributed, I know that the X and Y variables should ...
1
vote
0answers
21 views

Does negative binomial regression assume sample independence?

I'm working with a negative binomial multiple regression and I'm wondering about the assumption of spatial independence of samples. White and Bennetts (1996) say that the assumption of spatial ...
0
votes
0answers
32 views

Nonlinearity in OLS-models

I have a question connected to the OLS-Model's assumption of Linearity between parameters. What should be done if the assumption is not fulfilled? My second question is if I can use multinomial ...
1
vote
0answers
46 views

Can I interact my randomly-assigned variable with another variable in TSLS?

I'm working on an IV setup that uses random courtroom assignment as an instrument for whether a defendant goes to jail or not. (Similar to here and others). I have about five years of courtroom data, ...
0
votes
0answers
20 views

Is Naive Bayes robust?

We know that according to Naive Bayes assumption input features are assumed to be independent of each others given the target variable $y$. Now, If we intentionally add a duplicate (exact copy of ...
4
votes
2answers
51 views

Can a one-way ANOVA be performed in these circumstances

I am supporting a psychology experiment, and having problems analyzing some of the data. By way of background, I’m a programmer at a research organization who’s taken several stat courses recently. ...
5
votes
2answers
98 views

Assumptions behind multinomial logistic regression

What are the proper assumptions behind multinomial logistic regression? And what are the best tests to satisfy these assumptions in any statistical software? What are other suitable models, if those ...
1
vote
0answers
32 views

Assumptions to be checked under Tobit model

Some researchers suggest that OLS assumptions must also be satisfied for other estimations (like Tobit, probit/logit, Heckman two-stage model). From the discussion here I understand that it makes no ...
2
votes
1answer
32 views

What is the nature of the normality assumption in models for longitudinal data?

I'm working on a longitudinal dataset to which I've been fitting non-linear mixed effects model in R. Regarding normality, I have a few questions: Can I assume that a longitudinal data is normally ...
0
votes
1answer
67 views

OLS assumptions

It is known that conducting post-estimation tests for OLS assumptions (Multicollinearity, heteroscedasticity, and endogeneity) is necessary. But is it statistically necessary to carry out these OLS ...
1
vote
0answers
24 views

Central limit theorem: applicability for assumptions of different tests

Since many statistical procedures (e.g. t-test, ANOVA, Pearson’s r (for efficient estimates)) require the normal distribution of the tested variables ('normality-assumption') one may ask if (at least) ...
1
vote
0answers
39 views

Is a model including a square root of a variable linear in the parameters? [duplicate]

Is the model $$ y = \gamma_0 + \gamma_1 + \sqrt x + \varepsilon $$ linear in parameters? ( $\varepsilon$ is the error term.)
3
votes
2answers
74 views

Is it an assumption of the normal linear model that explanatory variables are uncorrelated with the errors?

Some books seem to include an assumption for the normal linear model which I have never seen before. They say that there must be no correlation between between the explanatory variables and the ...
1
vote
0answers
9 views

Three percentage indicators into one (or two measures) in regression moder

I am working with a data set resembling the extract below: ...
4
votes
3answers
134 views

Violation of Gauss-Markov assumptions

Which of the Gauss-Markov assumptions is violated in this picture? If all other Gauss-Markov assumptions are satisfied, is the OLS estimator for $\beta_1$ unbiased and consistent? Why? In the ...
5
votes
1answer
65 views

How bad can heteroscedasticity be before causing problems?

I have two questions about heteroscedasticity in multiple regressions. According to my trusty textbook (Using Multivariate Statistics 2007, p.127), it says that deviations from ...
3
votes
1answer
57 views

What if a transformed variable yields more normal and less heteroskedastic residuals but lower $R^2$?

I am trying to decide whether to use a square root transformed dependent variable in multiple linear regression. Transforming $y$ leads to more normally distributed residuals and also to less ...
36
votes
4answers
2k views

Why do we care so much about normally distributed error terms (and homoskedasticity) in linear regression when we don't have to?

I suppose I get frustrated every time I hear someone say that non-normality of residuals and /or heteroskedasticity violates OLS assumptions. To estimate parameters in an OLS model neither of these ...
-1
votes
1answer
83 views

How can I determine if categorical data is normally distributed?

Is it true that a normality check should be used for continuous data only (ratio, interval level of measurement) and not for categorical data (nominal, ordinal)? Is there any way to check the ...
2
votes
1answer
21 views

Covariate related to independent variable - best solutions

I have 2 groups (tinnitus sufferers and controls) who are significantly different in age - I would normally control for age as a covariate (as it is a cognitive task) but it violates the assumption of ...
1
vote
0answers
113 views

Checking the proportional odds assumption holds in an ordinal logistic regression using polr function

I have used the ‘polr’ function in the MASS package to run an ordinal logistic regression for an ordinal categorical response variable with 15 continuous explanatory variables. I have used the code ...
2
votes
1answer
131 views

Does the Mann-Whitney U-test require the groups to have the same distribution?

If one of my data sets is normally distributed and the other is not, can I do a Mann-Whitney U-test on them, or would they both have to be non-normal?
0
votes
0answers
20 views

Is 0 mean of residuals assumption crucial for every model?

I am writing a seminar paper about sales forecasting. I am doing couple of models and I am choosing which one gives the best forecasts (Decomposition method, SARIMA, Brown Exponential Smoothing, Holt ...
8
votes
2answers
166 views

How do residuals relate to the underlying disturbances?

In the least squares method we want to estimate the unknown parameters in the model: $$Y_j = \alpha + \beta x_j + \varepsilon_j \enspace (j=1...n)$$ Once we have done that (for some observed ...
2
votes
2answers
257 views

How to prove linearity assumption in regression analysis for a continuous dependent and nominal independent variable?

I want to check the assumptions for applying linear regression analysis. So, among others I check the linear dependency between my dependent (which is continuous) and my independent (nominal or dummy) ...
1
vote
1answer
115 views

Logistic Regression Assumptions

I am preparing a presentation on logistic regression. I applied logit model to a data set and now want to check whether my model meets logistic regression assumptions. I don't exactly know how to do ...
3
votes
2answers
127 views

What really happens when we transform the data using $f(x) = \sin(\sqrt{x})$?

I need to perform a two-way ANOVA on my data ($Y$: sleeping hours). My data is quite normal $p$-value = $0.07$ with Shapiro-Wilk test but when I run the normality test for my residual, $p$-value is ...
2
votes
0answers
24 views

Evaluating survival models in the presence of covariate-dependent censoring

I have a censored survival analysis problem with the following characteristics: Failure times are discretized The censorship distribution depends on certain covariates I don't have a ...
1
vote
1answer
60 views

Heckman 2-step Error Assumption

first question on StackExchange; thank you for having me. I am trying to really nail the intuition for the Heckman sample selection model. One little thing that is bothering me is the assumption ...
0
votes
0answers
65 views

Variance assumption and normal assumption not met, Kruskal or Welch-Anova?

I have 7 different groups of playing time data that is not normal. Lets say its really not normal..like a lot. The variance is also not equal and fails the bartlett test by a landslide. Sample ...
1
vote
0answers
33 views

Assumptions for nlme

I want to analyze a repeated measure design with two independent variables (var1, var2) where the subjects had to solve three ...
0
votes
0answers
43 views

What effect, if any, do outliers have on mediation analysis with bootstrapping?

I am running a mediation analysis spread over 6 models. Analysis is performed using the PROCESS macro. Each model includes 1 IV, 2 parallel mediators, and 1 DV. In a couple of the IVs, a number of ...
0
votes
0answers
63 views

Is my sample suitable for elastic net? What are the assumptions?

I was hoping to use multiple regression to identify significant predictors but I have a tiny sample size (group 1 n=9, group 2 n=37) so I'll be unable to do this. I have read that regularisation ...
3
votes
2answers
517 views

What causes non-normality of the error term in OLS?

In data, what causes the error term to be non-normally distributed in regression? Along the same lines, what solutions are there for non-normal residuals? For example, is it caused solely by a ...
2
votes
0answers
32 views

Cox Proportional Hazards Assumptions - Simplest Tests in R

I have no stats background, and have been looking into Cox models. $$ h(t) = h_0(t)e^{\beta_1 x_1 + \beta_2 x_2 + ...}$$ (Where $h$ is an individual hazard function, $h_0$ is the baseline hazard ...
3
votes
3answers
92 views

Counterexample against binomial assumptions

The question is from a Master-level Probability Course. It is well known that the underlying assumption for the binomial distribution is that there are n independent Bernoulli trials. More ...
0
votes
2answers
48 views

Simulating violations of regression assumptions

I'm wondering if anyone could provide some code (preferably in R) which demonstrates violated assumptions leading to type 1 errors. Some concrete examples of errors arising from assumption violations ...
0
votes
0answers
46 views

How to make assumptions about the measured data

I just finished a 1-yr continuous measurement of the hourly concentration of air pollutants and environmental influencing factors, such as temperature, relative humidity etc. For the next step, I ...
1
vote
2answers
289 views

Why do we have to assume normality for a one-sample t-test?

As a consequence of the central limit theorem the sampling distribution of the sample means will always be normal whatever is the distribution of the variable we measure. From our sample we can ...
3
votes
0answers
483 views

What does “independent observations” mean?

I'm trying to understand what the assumption of independent observations means. Some definitions are 1 "the occurrence of one event doesn't change the probability for another". 2 "sampling of one ...
0
votes
0answers
14 views

ANCOVA: what do I do when my covariate and DV do not correlate?

I was planning to use an ANCOVA for my study, however, the CV and DV do not correlate. In this case can I instead use an ANOVA?
0
votes
0answers
86 views

Need to transform data before running mediation/model with bootstrapping (PROCESS)?

I am reading through Hayes' book on mediation and moderation analysis (2013) which describes the PROCESS macro he created to use bootstrapping in order to arrive to confidence intervals to check the ...
2
votes
2answers
213 views

Importance of multiple linear regression assumptions when building predictive regression models

As far as I know, one can differentiate between two main goals of the regression analysis: The goal is understanding causal relations between variables. Here, one has to check several common ...
0
votes
1answer
47 views

Rules of thumb for PERMANOVA

I'm currently assessing the best option for looking at some community composition data, and determining how they differ among locations. Ultimately, as I'm simply looking to see if there is a ...
1
vote
0answers
68 views

Struggling with non-normality in generalized linear model

Dear statistics experts, I am looking for correlations between certain measures of brain structural integrity (fractional anisotropy, given as ratio between two hemisphere ==> rational data range ...