Chapter 16 Data Analysis

Descriptive statistics

Used to describe and summarize sample data and characteristics.

Inferential statistics

Used to predict, test hypotheses, and generalize beyond the study sample.

Nominal measurement

Categorical data with no inherent numeric value, used as labels.

Ordinal measurement

Relative rankings of categories with unequal intervals and no absolute zero.

Interval measurement

Numeric scale with equal intervals but no absolute zero.

Ratio measurement

Numeric scale with equal intervals and an absolute zero.

Mode

The most frequent value in a distribution.

Median

Score where 50% of the scores are above and 50% below.

Mean

The arithmetic average of all the scores in a distribution.

Normal distribution percentages

About 68% fall within 1 SD, 95% within 2 SD, and 99.7% within 3 SD.

Null hypothesis

Hypothesis stating no actual relationship between variables or differences between groups.

Research hypothesis

that which the researcher believes will be the outcome of the study

P-value

Probability that study findings are due to chance, typically 0.05 or less.

Type I Error

Incorrectly rejecting a true null hypothesis.

Type II Error

Incorrectly accepting a false null hypothesis.

alpha level

aka Significance level (α), the risk of making a Type I error, is usually set at 0.05 (5%).

Parametric statistics

Powerful tests used with normally distributed interval or ratio data.

Non-parametric statistics

Less powerful tests used with nominal or ordinal categorical data.

t-test

Statistically tests whether the mean scores of two groups are different.

ANOVA

Tests whether group means differ by comparing variation between and within groups.

Chi-square

Determines whether categorical frequency differs from what is expected by chance.

Pearson correlation

Measures the linear association between two interval-level variables.