Questions tagged [heteroscedasticity]

Non-constant variance along some continuum in a random process, or varying between discrete groups

1,185 questions
Filter by
Sorted by
Tagged with
14 views

Residuals changes with Predicted values range in LGBM regressor

I am doing a regression problem where the target variable ranges between 0.01 to 0.15. The model gives the best value when the predicted value is around 0.1. Plotting the residuals seems to show ...
• 1
59 views

Does this graph show heteroscedasticity or homoscedasticity?

So I am using stock data for certain stocks over a period of about 13 years and now i want to check for heteroscedasticity and auto-correlation on stata. residual vs. fitted value is shown below. ...
518 views

Welch t-test p-values are poorly calibrated for $N=2$ samples

I am performing a large number of Welch's t-tests (t-test with unequal variance) on very small sample sizes, often with only two samples per condition. I am finding the p-values are poorly calibrated: ...
• 153
460 views

• 113
191 views

Which Levene statistic do I report?

I am writing a paper comparing quantitative values across $5$ groups. I have performed an ANOVA in SPSS 29 and have requested from the software the Levene statistic to judge if there is homogeneity in ...
• 503
23 views

Aggregated Regressors and standard errors

Suppose we have some aggregated regressors and some that vary across all individuals. E.g. individual data on workers and aggregated data on the level of the US-states. We could either account for ...
1 vote
47 views

Heteroscedasticity and Serial correlation test

Let’s consider linear regression model, estimated using OLS. According to information from Hayashi (Econometrics, Chapter 2) it must be the case of no serial correlation in errors to perform White’s ...
395 views

Difference between heteroskedasticity and overdispersion

Are both terms equivalent? They seem very similar to me. Or does one imply the other?
• 3,979
1 vote
15 views

Could a study be considered to be underpowered if the effect size they detect is significantly below their predicted effect size? [duplicate]

I'm assessing a paper, the authors of which state that they recruited 3000 patients because that was what the power calculation suggested was necessary to detect a 5% difference at 85% power. They ...
• 503