Statistical Analysis and Testing

These flashcards cover important terms and concepts relevant to statistical analysis and hypothesis testing as discussed in the lecture.

Null Hypothesis (H0)

A statement that there is no effect or no difference, which is tested against an alternative hypothesis.

p-value

The probability of obtaining a test statistic as extreme as the one observed, assuming the null hypothesis is true.

Type I Error

Incorrectly rejecting the null hypothesis when it is actually true.

Type II Error

Failing to reject the null hypothesis when it is false.

Statistical Power

The probability of correctly rejecting the null hypothesis when it is false, calculated as 1 - β.

Effect Size

An objective measure of the magnitude of an effect, indicating the size of a difference or relationship.

Alpha Level (α)

The threshold for significance in hypothesis testing; the probability of making a Type I error.

Familywise Error Rate

The probability of making one or more Type I errors across multiple comparisons.

ANOVA (Analysis of Variance)

A statistical method used to compare three or more group means to see if at least one is different.

F-ratio

The ratio of variance explained by an experiment to the residual variance, used in ANOVA.

Bonferroni Correction

A method to adjust the significance level when multiple comparisons are made, reducing the Type I error rate.

One-Tailed Test

A hypothesis test that predicts the direction of an effect; significance is assessed at one end of the distribution.

Two-Tailed Test

A hypothesis test that assesses for an effect in both directions; significance is evaluated at both ends of the distribution.

Mann-Whitney U Test

A non-parametric test used to compare differences between two independent groups.

Wilcoxon Signed-Rank Test

A non-parametric test used to compare two related samples to assess whether their population mean ranks differ.

Resampling Techniques

Methods that allow statistical analysis with fewer assumptions by repeatedly sampling from the data.

Bootstrap Resampling

A technique for estimating the distribution of a statistic by repeated sampling with replacement from the original sample.

Permutation Tests

A method used to compare two groups by rearranging the data points to determine the null distribution.

Open Science Practices

Research practices that promote transparency, accountability, and accessibility in scientific research.

Publication Bias

The tendency for journals to publish only significant results, leading to a misrepresentation of research findings.

P-Hacking

The practice of manipulating data or analysis to achieve a desired p-value, often leading to misleading results.

Multiverse Analysis

A method of assessing the robustness of research findings by testing multiple analysis paths.

Reproducibility Crisis

A situation in which researchers are unable to replicate or reproduce results from previous studies.