Psych 202: Exam 3 Review - Hypothesis Testing, Effect Size, and 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

1/20

flashcard set

Earn XP

Description and Tags

Vocabulary practice flashcards covering statistical and practical significance, Cohen's d, t-test assumptions, hypothesis testing errors, and test identification from Psych 202 lecture review.

21 Terms

1
New cards

Statistical Significance

An evaluation of how unlikely an observed sample result would be if the null hypothesis were true, assessed using test statistics and pp-values.

2
New cards

Practical Significance

An assessment of the actual magnitude or real-world meaningfulness of an observed effect, evaluated using effect sizes rather than sample-size-dependent test statistics.

3
New cards

Unstandardized Effect Size

An effect size expressed directly in original, raw units of measurement (for example, participants donating 75 cents75\text{ cents} more than a fair rate of $5\$5).

4
New cards

Standardized Effect Size

A scale-free measure of effect magnitude that divides the difference between compared entities by natural variability (standard deviation).

5
New cards

Cohen's dd

The most common standardized effect size metric for tt-tests, calculated using the formula d=M−μσd = \frac{M - \text{μ}}{\text{σ}}, representing the difference between the observed mean and expected population value divided by the standard deviation.

6
New cards

Cohen's Benchmarks

Conventional guidelines for interpreting standardized effect sizes in psychology: 0.200.20 represents a small effect, 0.500.50 represents a moderate effect, and 0.800.80 represents a large effect, rarely exceeding 11 in psychological research.

7
New cards

Independence of Observations

An assumption underlying all tt-tests requiring that individual respondents do not impact one another, which is established through research design rather than verified by a statistical check.

8
New cards

Normality Assumption

An assumption underlying all tt-tests stating that the continuous outcome variable is normally distributed, commonly assessed by examining histograms and checking the skewness statistic.

9
New cards

Data Transformation

A remedial procedure used when the normality assumption is violated, in which mathematical operations are applied to the outcome variable scores to make the distribution more normal.

10
New cards

Non-parametric Test

An alternative statistical testing procedure used when underlying parametric assumptions (such as normality) are violated and cannot be adequately resolved.

11
New cards

pp-value

The probability of observing sample results as extreme as, or more extreme than, those obtained, given that the null hypothesis (H0H_0) is true.

12
New cards

Null Hypothesis (H0H_0)

A statistical hypothesis stated in terms of population parameters proposing that no true effect, association, or difference exists in the population.

13
New cards

Alternative Hypothesis (H1H_1)

A statistical hypothesis stated in terms of population parameters proposing that a true effect, association, or difference exists in the population.

14
New cards
<p>Type I Error ($$\alpha$$)</p>

Type I Error (α\alpha)

An error occurring when a researcher incorrectly rejects a true null hypothesis (a 'False Positive'), claiming an effect exists when there is no actual population effect.

15
New cards
<p>Type II Error ($$\beta$$)</p>

Type II Error (β\beta)

An error occurring when a researcher fails to reject a false null hypothesis (a 'False Negative'), failing to detect an effect that truly exists in the population.

16
New cards
<p>Correct Rejection (Statistical Power)</p>

Correct Rejection (Statistical Power)

The correct decision made when a researcher rejects the null hypothesis when H0H_0 is indeed false in the population.

17
New cards

One-Sample tt-Test

A parametric test comparing a single sample mean (MM) against a known or specified population parameter (μ\mu).

18
New cards

Independent-Samples tt-Test

A parametric test comparing the means of two completely separate, unrelated participant groups (such as psychology students versus math students).

19
New cards

Paired/Dependent-Samples tt-Test

A parametric test comparing two sets of scores obtained from the same participants (such as repeated-measures pre-test/post-test designs) or matched pairs.

20
New cards

Estimated Standard Error (sMs_M)

An estimate of the average distance between a sample mean and the population mean, calculated as sM=sns_M = \frac{s}{\sqrt{n}}.

21
New cards

Critical Value (tcritt_{\text{crit}}) Rule

The NHST criterion dictating that researchers reject H0H_0 if the calculated test statistic is outside the critical value (p<.05p < .05) and fail to reject H0H_0 if it is within the critical value (p>.05p > .05).