All Questions
Tagged with hypothesis-testing regression
818 questions
0
votes
0
answers
49
views
Standard error is too small on "perfect" data
While studying linear regression, I encountered this weird situation.
I am fitting a data to a linear model $\beta_0 + \beta_1 x$, and running a Wald test to check if $H_0: \beta_0 = 0$. Here is a ...
- 101
11
votes
4
answers
647
views
Generally, are we supposed to remove all nonsignificant paths in an SEM analysis?
Given that we favour parsimony in science, should we remove nonsignificant paths that are nonsignificant if they do not result in significantly worse model fit?
After we remove the nonsignificant ...
- 331
2
votes
1
answer
58
views
Comparing logistic regression coefficients
I have data representing a population of individuals and a binary outcome of interest. The covariates themselves are often probabilities. For example, covariates 1 through 5 are an estimate of the ...
5
votes
1
answer
228
views
In SEM, is there any point in interpreting path coefficients if the model shows poor fit in the first place?
If there were some path coefficients that were significant but the whole model shows poor fit, can I still use the result from the significant path?
By extension, if the model evidenced poor fit in ...
- 331
4
votes
1
answer
72
views
Statistical significance of multiple models over multiple datasets
I have a table of mean performances of 6 models over 10 datasets. While I've seen tables like these in research papers, they always display significant results in bold. What I'm not sure of is how ...
3
votes
2
answers
40
views
Modeling disease vs. microbiome: which should be the outcome?
I have a question related to microbiome research, an area where many researchers assess whether taxa abundances differ between disease and control groups. I often see statistical models where taxa ...
- 116
1
vote
0
answers
22
views
Relationship between adding more regressors to a linear regression model and the F-statistic of the model
I was thinking about the impact on different parameters in a linear regression model when we add more regressors, but I'm a bit unsure of what happens to the F-statistic.
I know that for $Y=\beta_0+\...
- 11
0
votes
0
answers
19
views
Is possible to test the differente between two coefficients for different regressions at R? [duplicate]
I have two regressions and I need to test if there are a difference between the coefficients.
df1 = data.frame( estimate = c(0.04854144, -0.00105855,0.00051479),
std.error = c(0.00918019, 0....
- 1
4
votes
1
answer
155
views
Moderate test statistic but low p-value in an F-test
I am running a multiple regression on simulated data in R. The sample size is 100. There is one relevant regressor and 18 irrelevant ones. I am testing the joint significance of the 18 irrelevant ...
- 69.5k
3
votes
1
answer
79
views
Significance in multiple regression but not in single regression
I first run a multiple regression: y ~ a + b + x and find both a and b to be significant (p&...
- 143
0
votes
1
answer
37
views
How to test association between one dependent categorical variable and several independent categorical variables? [duplicate]
I have a dataset with bus trips. I want to test whether there is a correlation between the bus trip type and other variables: It looks like that (with 250k rows)
Trip type
land use
Closest POI
fast
...
- 1
1
vote
2
answers
34
views
Are Type 1 errors associated with model accuracy for linear models
It is at the least uncommon for discussion of statistical significance of predictors to mention model accuracy. However, my intuition is that I would be more comfortable believing in the importance of ...
- 11
3
votes
2
answers
302
views
Is downsampling a valid approach to compare regression results across groups with different sample sizes? If so, how?
I have a large dataset of countries, each categorized into one of two regions, and I'm interested in how the effect of a predictor variable
𝑋 differs between the two regions. I plan to fit separate ...
0
votes
0
answers
35
views
How can I get the main effects of a GEE model and pool across imputed datasets R
With mice I imputed 5 datasets, and stored these as a list in data_list. I want to predict outcomes stored in ...
Noa
1
vote
1
answer
35
views
Why estimates of data via residuals has 50/50 effect on significance compared to original data?
I am generating data according to the following model
In the real dataset, variable I is unknown and the goal is to study the relationship between I and D, B11, to see if it is significantly non-zero....
- 425
1
vote
1
answer
54
views
Two way anova or paired t-tests
i am looking to see if there is a difference in dissolved oxygen levels between pool surface (S) and bottom (B) samples at four sites (an up and downstream site in two creeks). There are 3 replicate ...
- 11
1
vote
1
answer
39
views
Hypothesis testing categorical variables: Should we include them in logistic regression models?
I have observational data with binary treatment/control where users are exposed to a new program and covariates like the below:
Race of the user (about 5 races)
<...
3
votes
1
answer
71
views
What statistical test can I use? If any?
I'm currently investigating mortality rates in my local area compared to England.
Mortality rates in my local area have always been higher than England however recently I've noticed a widening gap ...
- 51
2
votes
0
answers
52
views
Comparing slopes of regression models on different data
Let's say, we have two dependent variables: $y_1$ and $y_2$, and these dependent variables depend on their own exogenous regressors:
$$y_1 = \beta_0 + \beta_1 x_1 + \epsilon_1$$
$$y_2 = \gamma_0 + \...
- 227
1
vote
0
answers
60
views
Least-bad stepwise procedure for a simulation that shows issues with stepwise regression
I am well-aware of the issues that stepwise regression causes. I want to demonstrate some of them via simulation in a particular situation.
I am thinking of a regression where I have some categorical ...
- 67.1k
3
votes
1
answer
67
views
Choose to resolve and report only some hypotheses
I have carried out a 2 x 2 x 4 x 4 experiment with 12 subjects to perform a linear mixed model. Would it be correct to perform the complete analysis but report only the results of the 2 x 2 ...
- 91
1
vote
0
answers
31
views
R - Why is bgtest showing no autocorrelation when order is set to a higher number, but shows autocorrelation at order = 1
Upon reading, I saw that bgtest (Breusch-Godfrey test, from lmtest pkg) can diagnose autocorrelation of higher orders than just 1, which is the maximum order the dwtest (Durbin-Watson test, from ...
0
votes
0
answers
17
views
Statistical test for variability among more than one group
I am very new to statistics and still learning. Below are the funnel graphs which shows the effect/percentage of polypharmacy(patients with two or more drugs) against practice/hospital population size....
- 141
0
votes
1
answer
113
views
Z-score and standard error in linear regression
I am reading Elements of statistical learning, and in the chapter on linear regression, I cannot understand the following:
We have estimated the regression parameters $\beta_1, ..., \beta_p$ from $N$ ...
- 13
3
votes
1
answer
125
views
Can using Fisherian inference help me to be more confident of an underpowered result?
I am running a discontinuous regression to see the effect of a cash transfer on an outcome using a poverty index as the running variable. The problem is that the score is not a very good predictor of ...
1
vote
1
answer
46
views
Which technique to use for models that include Likert-scale items?
I have three or more independent variables (a Likert scale was used) and GWA as my dependent variable, to see what variables are influencing student compliance with respect to a school's grade ...
- 11
0
votes
0
answers
16
views
Which statistical test to use for comparison of influence of two independent variables?
I am conducting a research of "Comparison of Influence of Parents' and Teacher's Attitude Towards Math to Anxiety of Students in Math" Now my null hypothesis: There is no difference in ...
0
votes
1
answer
88
views
Prove Wald statistic = number of linear restrictions times F statistics
I'm considering $F[J,n-k]= \displaystyle \frac{(e_{*}^{'}e_{*}-e'e) \backslash J}{e'e\backslash (n-k)}$, where $J$ stands for number of restrictions. I want to prove $W=(Rb-q)'(Rs^2(X'X)^{-1}R')^{-1}(...
- 131
0
votes
0
answers
37
views
Is it possible to conduct an F test without fitting a restricted model?
Say I'm fitting the following regression:
$$
Y = \beta_0 + \beta_1X_1 + \beta_2X_2 + \beta_3X_3 + \beta_4X_4
$$
If I was interested in testing the hypothesis that $\beta_2 = 0$, I know I can do things:...
- 21
7
votes
2
answers
118
views
LR statistics add up for nested models. What about the Wald test?
Consider models M0, M1, M2.
Let M0 $\subset$ M1 $\subset$ M2, i.e. let the models nest each other.
I test the following pairs of models using the likelihood-ratio (LR) test: M0 vs. M2, M0 vs. M1, M1 ...
- 69.5k
0
votes
0
answers
54
views
How to test if the slope = 1 and intercept = 0 for linear model, based on major axis (MA) regression?
I understand the output of simple linear models gives results about testing if slope and intercept equal to 0:
...
0
votes
0
answers
16
views
How to translate the set of contrasts over model coefficients into definitions of two nested models for Likelihood Ratio testing?
With the data as below:
Categorical predictor: "Group" with 2 levels: Group 1 and Group 2
Categorical predictor: "Treatment" with 3 levels: A, B, C
Categorical binary response: &...
- 11
1
vote
0
answers
49
views
How to test specific contrasts about levels of categorical variables through nested models? [closed]
This is not about obtaining any dataset. I HAVE the dataset.
This is not about debugging code, this is about EXPLAINING the way to obtain statistical relationship between the nested models (LRT ANOVA) ...
- 11
3
votes
2
answers
146
views
Replicate t or F test from regression using regression likelihoods
I've heard that the t-test and F-test we use to get the significance of our regression results are derived from the likelihood ratio test, but I'm having trouble replicating the p-value of the t/F ...
- 425
1
vote
0
answers
28
views
Degrees of freedom for estimation
In the context of estimators, why is it that in general dividing by the degrees of freedom(instead of the sample size) leads to unbiasedness? I see the value in substituting degrees of freedom for ...
1
vote
1
answer
50
views
Mediation: only c path and b path are significant?
I have done a mediation analysis in which nature contact is the independent variable, worrying is the mediator and depressive symptoms the dependent variable. I performed a mediation via PROCESS.
The ...
- 11
0
votes
0
answers
17
views
Mixing MLE and Hypothesis Testing
In my field of biology, we have spatial data with known distances, so we know a general formula for our error structure that we can use in a generalized least squares context, it is
$$
(1-\lambda)\...
- 425
2
votes
1
answer
84
views
Regression with single-observation dummies: F-test under heteroskedasticity
I have a linear regression model with an intercept and a few dummy variables. Each of the dummies indicate a single observation, so the fit is perfect for these observations. Having fit the model, the ...
- 69.5k
2
votes
2
answers
62
views
Determining if slopes are zero or slopes are equal- can one actually accept a null hypothesis?
I am not a statistician and would like some help discussing best practices with colleagues.
My understanding is that if I run a linear regression
y = ax +b
the p value I get for x is testing HO:a=0 vs ...
- 21
1
vote
0
answers
74
views
Statistical significance of hierarchical (multi-level) associations
Association rule mining is a common technique in Data mining used to find itemsets which appear together very frequently in large transaction databases (e.g. in Table 3 we see that in a transactions ...
3
votes
2
answers
149
views
Large increase in joint significance when introducing robust covariance matrix estimator
I have a linear regression model where $Y$ is regressed on five dummies $X_3,X_4,X_5,X_{10},X_{20}$. (In R, I actually regress $Y$ on a factor $X$ that produces the 5 dummies.) My sample size is 24 (...
- 69.5k
4
votes
3
answers
534
views
Why do we use an F distribution instead of just chi-squared when testing multiple hypotheses from regression?
After estimating a multiple-regression using ordinary least squares (OLS), the classical test for joint significance of multiple variables is to run an F test using restricted and unrestricted ...
- 123
1
vote
1
answer
88
views
How to express Hotelling T² test as a Likelihood ratio between two multivariate linear models?
Is it possible, given that Hotelling's T² (or Hotelling-Lawley Trace for that matter) is just a generalization of Student's T, to reformulate the same testing procedure (to test if two vectors differ) ...
- 25
2
votes
1
answer
38
views
I would like to test for isometric growth in fish using b value from linear regression against a b value of 3 using t test
I have data on length/weight for male fish and want to compare by $b$ value for slope of regression against 3 to test for isometric growth. I tried using hoCoef ...
- 21
3
votes
3
answers
148
views
Sampling distribution of Coefficient of determination in general
I was studying the properties of multiple linear regression, and stumbled across the F statistics often used for the tests. We are testing for the regression coefficients (let's say there are $p$ ...
- 31
1
vote
1
answer
81
views
Comparing Deming/Orthogonal Regression to Null Hypothesis
I have some data of with the relationship
Y=commonFactor+error1 and X=Alpha+Beta*commonFactor+error2
I want to test the hypothesis that Beta is non-zero, or that there is a significant relationship ...
- 425
1
vote
0
answers
18
views
Poor RMSEA/Fit for Simple Poisson Regression
I am running a simple Poisson regression. $X$ = time, $Y$ = count data. This is a huge dataset with many years. There is significance between $X$ and $Y$. But model shows poor fit via high RMSEA value....
- 11
3
votes
1
answer
208
views
Mixed effect logistic regression model
I am very new to the world of statistics and I need some help. I am currently doing an experiment and I have to analyze the data, but I honestly do not know anything about statistics (I have tried to ...
- 175
2
votes
1
answer
84
views
Statistical Test or Regression for Intervention Effectiveness?
I'm looking to model the effectiveness of an intervention on human behavior. I have control groups and treatments groups for the outcome of interest and pre and post measurements (just 1 for each) for ...
- 23
2
votes
2
answers
90
views
Is a binomial logistic regression valid in this case, and how do I use it / interpret its results?
I am facing the unusual problem that my $p$ values are too good. They are so good that I must be doing something wrong, but I don't know what.
I am working with natural language data from a text ...
- 145