Lecture: Independent Samples T-Tests

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/17

flashcard set

Earn XP

Description and Tags

Vocabulary flashcards covering between-subject designs, one-sample and independent samples t-tests, parametric test assumptions, normality, homogeneity of variance, and non-parametric equivalents.

18 Terms

1
New cards

Between-Subject Design

An experimental design in which different participants take part in each experimental condition, preventing order effects but generally providing less statistical power.

2
New cards

Within-Subject Design

An experimental design where participants take part in all conditions, providing more statistical power because each participant acts as their own control, but carrying the risk of order effects.

3
New cards

Continuous Data

Numerical measurements on a scale (interval or ratio data) that can take decimal values and be summarized using means, medians, and standard deviations.

4
New cards

tt Statistic

The ratio representing the variance explained by the independent variable relative to the unexplained variance (t=variance explained by our IVunexplained variancet = \frac{\text{variance explained by our IV}}{\text{unexplained variance}}).

5
New cards

Parametric Test

A primary choice statistical test that relies on specific mathematical assumptions (parameters) about data distribution, such as normality and homogeneity of variance.

6
New cards

Non-Parametric Test

An alternative statistical test used when parametric assumptions are violated, typically evaluating medians or ranked scores rather than means.

7
New cards
<p>Galton Board</p>

Galton Board

A physical apparatus with pegs demonstrating that randomly dropped ball bearings naturally fall into a bell-shaped normal distribution curve by chance.

8
New cards

Shapiro-Wilk Test

A formal statistical test of normality evaluating the probability that an observed distribution arose by chance, where a non-significant result (p>0.05p > 0.05) indicates normality.

9
New cards

Kolmogorov-Smirnov Test

An alternative statistical test of normality reported in SPSS Tests of Normality output alongside the Shapiro-Wilk test.

10
New cards

One-Sample T-Test

A parametric test used to determine whether the mean of a single continuous sample differs significantly from a specified number or known threshold.

11
New cards

One-Sample Wilcoxon Signed-Rank Test

The non-parametric equivalent to the one-sample t-test, which compares an observed sample median against a hypothesized median when normality is violated.

12
New cards

Independent Samples T-Test

A parametric test used in a between-subject design to determine whether the difference between the means of two distinct groups is statistically significant.

13
New cards

Homogeneity of Variance

An assumption for between-subject parametric tests requiring the spread or variance of scores to be approximately equal across all experimental conditions.

<p>An assumption for between-subject parametric tests requiring the spread or variance of scores to be approximately equal across all experimental conditions.</p>
14
New cards

Levene's Test

An inferential test assessing equality of variances between groups, where p>0.05p > 0.05 indicates no significant difference in variances (assumption met).

15
New cards

Q-Q Plot (Quantile-Quantile Plot)

A graphical diagnostic plot comparing ordered sample quantiles against expected normal values, where compliant data fall along a diagonal straight line.

<p>A graphical diagnostic plot comparing ordered sample quantiles against expected normal values, where compliant data fall along a diagonal straight line.</p>
16
New cards

Equal Variances Not Assumed Row

The adjusted row in SPSS independent samples t-test output reported when data violate Levene's test, which adjusts degrees of freedom without requiring a non-parametric test.

17
New cards

Mann-Whitney U Test

The non-parametric alternative to the independent samples t-test, which tests for differences between two independent groups using mean ranks and medians.

18
New cards

Sample Size Assumption (Independent Samples T-Test)

The requirement that each condition in an independent samples t-test must contain a minimum sample size of N=12N = 12 participants (at least 2424 participants total).