Stats - Exam 1

What are the main types of variables?

Nominal (categorical) ex: eye color, Ordinal (rank order) ex: class rank, Numeric/Equal-Interval (continuous) ex: test scores, reaction time

What are the different shapes of frequency distributions?

Unimodal (1 peak), Bimodal (2 peaks), Multimodal (many peaks), Rectangular (flat).

What does a positive skew look like?

Tail points to the right; most scores are low with few very high scores.

What does a negative skew look like?

Tail points to the left; most scores are high with few very low scores.

What are floor and ceiling effects?

Floor effect: scores pile at the low end. Ceiling effect: scores pile at the high end.

What graphs best display frequencies?

Histogram (for numeric/interval variables), Bar Chart (for nominal/ordinal).

Why isn’t the sum of deviation scores a good measure of variability?

Because deviations around the mean always sum to 0.

What is variability?

How spread out the scores are in a distribution.

What do scatterplots show?

Relationships between two variables.

What are the types of relations seen in scatterplots?

Positive linear, Negative linear, Curvilinear, No relation.

What is correlation predictive strength?

How strongly two variables are related; measured by correlation coefficient r.

Why is 'correlation is not causation' important?

Even if two variables are related, it does not prove one causes the other.

What is a correlation matrix?

A table showing correlations between multiple variables.

What are the three measures of central tendency?

Mean, Median, Mode.

When is it best to report the median?

When data is skewed or has outliers.

When is the mode most useful?

For nominal (categorical) data.

How do you compute standard deviation?

Find deviations from the mean, square them, average them (variance), then take the square root.

What is a Z-score?

The number of standard deviations a score is from the mean.

What does comparing Z-scores tell you?

Which score is relatively higher or lower across different distributions.

What does r² mean?

Proportion of variance in one variable explained by another variable.

Histogram

• Used for numeric/equal-interval (continuous) variables.

• Bars touch each other (because the values are on a number line and flow continuously).

• Example: showing the distribution of exam scores (0–100).

Bar graph

• Used for categorical/nominal or ordinal variables.

• Bars are separated (because categories are distinct and not continuous).

• Example: showing how many students are in psychology vs. biology vs. engineering.

What PROPROTION OF THE VARIANCE of stress can be ACCOUNTED FOR by sleep?

Example question of r²

Direction problems

Even if two variables are correlated, you can’t say which one causes the other

Third-variable problems

A correlation might exist because of a third variable influencing both.