Exam 3

Type 1 error

Rejecting the null hypothesis (H₀) when it is actually true (False Positive).

Type 2 error

Failing to reject the null hypothesis when the alternative hypothesis (Hₐ) is true (False Negative).

Which error is worse in medical testing?

Type 1 error is worse because it means approving an ineffective or harmful treatment.

t-test result format in APA

t(df) = test statistic, p = p-value (e.g., t(28) = 2.45, p < .05).

Statistical symbols to italicize in APA

t, F, p, M (mean), SD (standard deviation).

Numbers below 10 in APA style

Written as words (except for statistical results).

Two key types of statistics in APA results

Descriptive statistics (mean, standard deviation) and inferential statistics (t, F, p-values).

H₀ represents

The null hypothesis, which states there is no effect or difference.

Difference between H₀ and Hₐ

H₀ states no difference; Hₐ states there is a difference or effect.

Predicting an effect supports which hypothesis?

The alternative hypothesis (Hₐ).

If the null hypothesis is rejected, it means

The data supports the alternative hypothesis (Hₐ), indicating a significant effect was found.

Difference between directional and non-directional hypothesis

A directional hypothesis predicts a specific direction of effect, while a non-directional hypothesis predicts a difference without specifying direction.

When to use a two-tailed test

When unsure of the direction of the effect.

Reason for choosing a non-directional hypothesis

Lack of sufficient prior research to predict the direction of the effect.

IV and DV in studying sleep effects on test scores

IV: Sleep (amount or quality); DV: Test scores.

Levels needed for an IV

At least two.

Mean of 5, 10, and 15

10.

Median of 4, 6, 8, 10, 12

8.

Best measure for skewed data

Median.

Measure most affected by outliers

Mean.

Significant t-test result means

There is a statistically significant difference between the groups.

What does p < .05 indicate?

The result is statistically significant.

When to use paired samples t-test

When comparing the same group at different times (e.g., pre-test vs. post-test).

Meaning of t-test result p = .12

The result is not statistically significant.

Type of data for eye color

Nominal.

Difference between interval and ratio data

Ratio data has a true zero; interval data does not.

Scale allowing for meaningful ratios

Ratio scale.

Scale used for ranking in competitions

Ordinal scale.

If p = .03, is the result significant?

Yes, because p < .05.

If p = .08, what to do with H₀?

Fail to reject H₀ (not significant).

Meaning of a result not being statistically significant

There is not enough evidence to reject H₀.

Why is .05 used as significance cutoff?

It balances the risk of Type 1 and Type 2 errors.

Mistakenly concluding there is an effect is what error?

Type 1 error.

Failing to detect a real effect is what error?

Type 2 error.

Relation of Type 1 and Type 2 errors to hypothesis testing

They represent incorrect conclusions in hypothesis testing.

Importance of random assignment

It reduces bias and increases validity.

When to use independent t-test

When comparing two separate groups.

Key assumption of independent t-test

The two groups are independent and have equal variances.

IV if levels are "morning, afternoon, evening"

Time of day.

Importance of clearly defining levels of an IV

To ensure accurate comparisons.

How to convert an independent groups study into dependent groups study

Test the same participants at different times instead of using separate groups.

Advantage of dependent groups over independent groups

It controls for individual differences, increasing statistical power.