Questions tagged [post-hoc]

"post-hoc" refers to analyses that are decided upon after the data has been collected, as opposed to "a priori".

Filter by
Sorted by
Tagged with
0
votes
1answer
14 views

How to conduct a post hoc power analysis for a just-identified path model

I am doing secondary data analysis on an existing dataset. No power analysis was conducted a priori. My sample size is low, n = 122. Thus, I plan to do a post hoc power analysis. My model is just-...
2
votes
0answers
55 views

Can I add a random effect in a mixed effect model accounting for huge differences within factors?

Update 1 Progress I tried some modifications to my models an got lost of the interaction (1|year:row) since the random intercept of row shouldn’t differ between the ...
0
votes
0answers
14 views

How can I do a pairwise comparison on a model without any interactions?

I am testing a continuous y variable against 2 factors in a GAM. It's similar to what I've shown in the dummy code with the iris data set below. I want to do a posthoc comparison to see if the species ...
0
votes
0answers
13 views

Questions about post-hoc correlations and their legitimacy

I have a questions regarding correlations. Let me start with a quick background. I have conducted a Master research project. We recruited high trait anger men which we divided into two groups. One ...
1
vote
1answer
13 views

Contextualising post-hoc tests following repeated one-way ANOVA

I have a large dataset of 631 people that have been repeatedly measured across five different variables on some continuous parameter. The means (and SDs) for these variables are as follows: ...
0
votes
0answers
12 views

Principal component regression: post-hoc on all loadings

After performing a Principal Component Analysis and Principal Component Regression, can I do a post-hoc on all the loadings for the first principle component? Or do I have to take the main loading for ...
2
votes
1answer
16 views

Are meta-analyses only secondary analyses which require uses of the post-hoc statistical methods?

Randomized clinical trials (RCT) require pre-registration with protocols, and the primary outcome is the only credible outcome, whereas secondary outcomes and sub-group analyses are only exploratory ...
2
votes
2answers
28 views

How do you compare standard deviations?

For example, if I am a scientist evaluating 2 methods to determine blood glucose and I want to compare if one is more variable, I would take, say, 6 samples from each person (subject) and use Method A ...
0
votes
0answers
18 views

When to correct for multiple kruskal tests? [duplicate]

I am running multiple (37) Kruskal wallis tests to check if there is a difference between three disease groups. I do this using groupby in R to group all the 37 ...
1
vote
1answer
27 views

Should I only select two Principal components for a regression analysis?

Why are two principal components usually selected for principle regression analysis? I read somewhere that since it is 2 dimensional data, there should only be 2 principal components extracted from ...
0
votes
0answers
9 views

Performing a regression (post-hoc) on PCA output

I have one dependent variable (y) and 7 independent variables (x1,x2,x3,x4,x5,x6,x7). I'm performing a PCA on the dataset. Once I get the Principle components, I wanted to be able to interpret the ...
0
votes
0answers
20 views

How to perform post-hoc with logistic regression in SPSS? (Two dichotomous IVs)

I performed a logistic regression in SPSS using two IVs (both dichotomous) and found a significant interaction effect. Now I want to understand where the differences come from. ⠀⠀⠀⠀⠀⠀ V1_a⠀⠀⠀⠀V1_b ...
0
votes
0answers
28 views

Tukey pairwise grouping after 2-way ANOVA

I have a dataset like this, ...
0
votes
1answer
27 views

Post-hoc test after 3-way Anova without significant interactions

I have a question regarding a post hoc test following an Anova. I ran an Anova (response variable~Factor1xFactor2xFactor3)and found that I have 2 significant main effects, but no significant ...
0
votes
0answers
9 views

Is my ANOVA post-hoc analysis considered “multiple testing”?

I was wondering if you could advise on this one. I want to test differences in volume (my dependent variable) of brain region (A, B, C, D, E) across groups (X, Y, Z). I perform a one-way "...
0
votes
1answer
95 views

Post hoc analysis for gamlss model in R

I used a gamlss model for my data and would like to do some post hoc analysis afterwards. I tried the packages emmeans and ggemmeans but both of them give me an error: "Error in match.arg(type) : ...
0
votes
1answer
82 views

Comparing simple slopes with one another (in R)

I know I can break an interaction effect to create some simple slopes (plot below). I also know I can test whether each of these simple slopes (in my case $6$) is significantly different from $0$ or ...
1
vote
1answer
16 views

Mean hypotheses tests for three different samples

I have three different samples and I would like to check if the means for them differ from each other statistically. I know it is not true if I run 3 different t-test between pairs. I searched and saw ...
2
votes
0answers
30 views

How to control the error rate when selecting the mode of a sample as the mode of the population?

I just looked out of my window and saw 4 white, 2 black, 1 green, 1 silver, 1 light blue, 1 lemon and 1 orange-white-striped car. Based on this, how confident should I be that white is the most common ...
0
votes
0answers
10 views

R: How to proceed if the Likelihood ratio test in linear mixed model is significant and I have a 3-levels factor?

I am analysing my date using linear mixed model with lme4 package in R. I created a full model with the two categorical variable Var (a,b,c) and Con (0,1,2,3,4,5,6), Var is my experimental variable ...
0
votes
0answers
13 views

How can I perform a regression analysis for two groups?

I have a problem where I have three groups (responders versus non-responders at baseline, responders versus non-responders at week8, and responders at baseline compared to responders at week8), in ...
0
votes
0answers
26 views

Post Hoc comparisons, Two way repeated measures Anova

I run a two-way repeated measures anova in R: a<-aov(acc~sound*cnd + Error(sbj/(sound + cnd)), data=d) I regressed accuracy (of participants, sbj) on cnd (...
0
votes
1answer
39 views

Should multiple testing correct with bonferroni ever reduce a p value's size?

I just did a series of 40 t-tests and then proceeded to use bonferroni correction for multiple testing and my P values reduced in size. Why does this happen? I was my impression that multiple tests ...
0
votes
0answers
25 views

When is it correct to use a pairwise Wilcoxon rank sum test?

Following this answer, I was wondering when and why one should perform a pairwise Wilcoxon rank sum test, as exemplified by the R function ...
1
vote
1answer
31 views

Between-subject design and within-subject anlyses

I have a between-subject design in which there are two groups (A, B) and two conditions (x, y). I ran an ANOVA and found no interaction whatsoever and no significant differences in the two conditions. ...
1
vote
0answers
23 views

Tukey hsd test vs DMS test

I am analyzing the differences on my dataset. This dataset has different values according to each group (called season_sized). I have no normality and heterocedasticity, so I performed a GLM to fit my ...
1
vote
1answer
71 views

Interpretation of Kruskal Wallis post-hoc pairwise comparisons - SPSS

I've run a KW test on my set on non-parametric data in SPSS, the output of the test giving me a p-value <0.05. As I have 20+ groups in my data set, I'm interested to see which group significantly ...
1
vote
0answers
20 views

exploring where and how clusters differ

After running clustering, I'd like to explore the results and hopefully get some sort of concrete idea of where (i.e. which on which of my n variables) differences ...
0
votes
0answers
13 views

Set up and analyse planned contrasts in lmer() from lme4

I would like to analyse planned contrasts in my lmer() model from the lme4package. I have three factors: group (levels: trt, ...
0
votes
0answers
9 views

How can I apply partitioning chi square test?

I have a table that has 4 groups and 5 comparisons. Groups are: monthly, several time annually, rarely and never. Comparisons are: stage 0, 1, 2, 3, 4. Chi square test were performed. There is a ...
0
votes
1answer
37 views

post hoc test on multivariate repeated measures linear mixed effects model (lmer)

I'm running a multivariate linear mixed effects analysis on data with the following structure: Where: Participants are nested within group, Time is a pre-post-post repeated measurement. The repeated ...
4
votes
2answers
149 views

Is post-selection inference a problem when robust tests are used?

It's pretty well acknowledged that error control via p-values fails when models are selected based on the data rather than decided on a priori. I've always viewed this as an issue of marginal vs ...
0
votes
1answer
69 views

Post hoc test after Chi square, please advise

I am analyzing a questionnaire survey data about online learning receptibility across different age groups. I have 4 age groups, and each has its % acceptance of the online learning susceptibility. ...
1
vote
1answer
60 views

How to do Friedman test and post--hoc test on Python? [closed]

I know that Python's SciPy library has the function for the Friedman test But, it is not enough as I need more information for posthoc test. So, how I do Friedman test and post-hoc test entirely on ...
0
votes
1answer
95 views

What post-hoc test should be used for a glmer model with a binary response, and a continuous and categorical predictor?

I'm a bit of a newbie with stats and R, so need a bit of direction to find a suitable post-hoc test for my glmer model. I'm trying to find if presence is affected by environmental factors for each ...
0
votes
0answers
28 views

How to do post-hoc comparisons for multinomial model with emmeans

When doing post-hoc pairwise comparisons for a multinomial model using emmeans package, do I use mode = "latent" or mode = "prob."? I'm interested in understanding if the response variable (with 3 ...
0
votes
0answers
23 views

Dunnett post hoc test significance

I compared the effect of different concentrations of antibiotics with the anova. As I am only interested in which concentration is significantly different compared to the control I performed a post-...
0
votes
1answer
74 views

What effect size should I report on post hoc analyses that compared estimated marginal means?

I am using SPSS, and have run an ANOVA model including three factors (two within and one between subjects). One of these factors has three levels and so I conduct post hoc tests comparing different ...
4
votes
1answer
41 views

Does a post-hoc power analysis suffice in a psychological paper?

I am a psychologist and I have the following question: Last year I was running a study. I intended to collect at least 400 participants (the anticipated effect size was hard to estimate). The study ...
1
vote
1answer
32 views

Correctly apply linear model for categorical independent variable

This question is about the way to go with a very common statistical model: Continuos dependent and categorical independent variable. In my stats class I learned to use the ANOVA: check assumptions, ...
1
vote
0answers
58 views

Is the Student–Newman–Keuls post-hoc test guaranteed to be stronger than the Tukey?

I am looking to compare two post-hoc analyses, one with the SNK test and the other with the Tukey. I have read that the SNK test is stronger but more likely to commit type 1 errors than the Tukey. ...
2
votes
1answer
17 views

Bonferroni's t critical value

Post hoc tests, like Bonferroni, allow us to detect which of the groups is the different one after ANOVA. To use it, we calculate effectively what is like the independent t-test for each of the ...
0
votes
0answers
16 views

Conducting a post-hoc test on a main effect of time (2 levels) to find out if all groups (3 levels) significantly changed over time?

Dear CrossValidated community, I have run a 3 by 2 mixed ANOVA, in which my between-factor is group (treatment1, treatment2, and treatment3) and my within-factor is time (pre and post). Let's call my ...
0
votes
0answers
20 views

Multiple hypothesis and multiple comparison with GLMMs

I have a data set with 20+ variables from the same underlying subjects (animal nests) under three treatments. I have modeled the effect of treatments on each of these variables using seperate GLMMs, ...
0
votes
0answers
64 views

Emmeans & effects packages: Post-hoc tests for Tweedie glmmTMB model

Are there any problems with using the effects and emmeans packages to interpret glmmTMB models with Tweedie distributions? I have glmmTMB models using the Tweedie distribution, and I want to draw ...
1
vote
1answer
33 views

Strange output for pairwise comparisons on glm with quasi-binomial distribution

I'm new to CrossValidated - I've read up on how to ask questions properly but sorry if I do anything slightly wrong. My data is showing whether microplastics were present or absent in the gut of fish ...
0
votes
0answers
18 views

Linear model and glht error

I am running a linear model with two continuous (Temperature and Time) and two categorical (Bacterium and Route) variables. Each categorical variable has four levels. Response variable is integer. <...
1
vote
1answer
114 views

One tailed p-values for post-hoc tests

Is it okay to calculate one tailed p-values from post-hoc tests? I read this from a source but I just want to confirm it. "First, post hoc tests by their nature are two-tailed (you use them when you ...
1
vote
0answers
24 views

Post Hoc Testing Repeated Measure Anova in R

I have a list of patients and their footfall specific velocities. Each patient has come in for two visits: the original and the retest visit. At each visit patients were asked to walk at six different ...
0
votes
0answers
30 views

What is a suitable non-parametric post-hoc test for a mixed factorial design?

I have a mixed factorial design. In total there are 3 factors: 1 factor is within-subjects (3 levels: i.e., time points) 2 factors are between-subjects (3 levels each: i.e., behaviors, environments) ...

1
2 3 4 5
11