Lecture 12 t Test for Dependent Means

These flashcards summarize key concepts related to the dependent means t test, including definitions, study results, and statistical concepts.

What is a Dependent Means t Test also known as?

Paired-samples, matched samples, or matched pairs.

What must be true for computing a difference score in a Dependent Means t Test?

The scores must be meaningfully yoked, such as husbands-wives IQ scores or before and after conditions.

In a repeated measures design, how are participants tested?

The same participants are tested at least twice under different conditions.

What bias was identified by Hagemann et al. (2008) in their study on Taekwondo referees?

An implicit bias favoring the competitor wearing red protective gear.

What does Cohen's d represent in statistical analysis?

A measure of effect size that indicates the standard deviation difference between two means.

What was the result of Hagemann et al.'s t test regarding the clothing color effect?

The competitor in red received statistically significantly more points than when in blue.

How do repeated measures studies generally compare to other research designs in terms of effect size?

They often have much larger effect sizes due to smaller standard deviations of difference scores.

What does a confidence interval (CI) represent in statistical analyses?

A range of values that is likely to contain the population mean with a specified level of confidence.

What was the hypothesized height difference for an ideal romantic partner when reporting genders?

Typically that males desire a taller partner while females desire a partner as tall or taller.

What statistical technique is used to analyze the effect of differences in means between two groups?

T-test for dependent means.

What is a Dependent Means t Test also known as?

Paired-samples, matched samples, or matched pairs.

What must be true for computing a difference score in a Dependent Means t Test?

The scores must be meaningfully yoked, such as husbands-wives IQ scores or before and after conditions.

In a repeated measures design, how are participants tested?

The same participants are tested at least twice under different conditions.

What bias was identified by Hagemann et al. (2008) in their study on Taekwondo referees?

An implicit bias favoring the competitor wearing red protective gear.

What does Cohen's d represent in statistical analysis?

A measure of effect size that indicates the standard deviation difference between two means.

What was the result of Hagemann et al.'s t test regarding the clothing color effect?

The competitor in red received statistically significantly more points than when in blue.

How do repeated measures studies generally compare to other research designs in terms of effect size?

They often have much larger effect sizes due to smaller standard deviations of difference scores.

What does a confidence interval (CI) represent in statistical analyses?

A range of values that is likely to contain the population mean with a specified level of confidence.

What was the hypothesized height difference for an ideal romantic partner when reporting genders?

Typically that males desire a taller partner while females desire a partner as tall or taller.

What statistical technique is used to analyze the effect of differences in means between two groups?

T-test for dependent means.

What is the null hypothesis (H_0) for a dependent means t-test?

That the population mean difference score (\muD) between the two conditions is zero. (H0: \mu_D = 0)

What is the alternative hypothesis (H_1) for a dependent means t-test?

That the population mean difference score (\muD) between the two conditions is not zero. (H1: \mu_D \neq 0) (or one-tailed alternative if specified)

How is a difference score (D) calculated in a dependent means t-test?

By subtracting the score from one condition (e.g., Condition 1) from the score of the same participant in the other condition (e.g., Condition 2). For each participant: D = X2 - X1.

What is the formula for the t-statistic in a dependent means t-test?

t = \frac{\bar{D} - \muD}{s{\bar{D}}}, where \bar{D} is the mean of the difference scores, \muD is the hypothesized population mean difference (usually 0 under the null hypothesis), and s{\bar{D}} is the standard error of the mean difference.

How are degrees of freedom (df) calculated for a dependent means t-test?

df = n - 1, where n is the number of pairs (or the number of difference scores).