📖 Statistical Analysis – Q&A Study Set

Descriptive vs. Inferential

Q: What is the main purpose of descriptive statistics?

A: To summarize and organize data so it’s easier to interpret (e.g., mean, median, mode, SD).

to summarize and organize data so it’s easier to understand

Descriptive vs. Inferential

Q: What is the main purpose of inferential statistics?

A: To make conclusions about a population based on sample data (e.g., t-test, ANOVA).

to use data from a sample to make conclusions or predictions about a larger population.

Distributions

Q: What is a distribution?

A: A frequency count of scores or attributes.

the way data values are spread out or arranged, showing how often each value occurs.

Distributions

Q: Name two common graphs used to show distributions.

A: Histogram and bar chart.

Distributions

Q: What does a mesokurtic distribution mean?

A: A normal, bell-shaped curve.

Central Tendency

Q: Which measure of central tendency is most affected by outliers?

A: The mean.

Central Tendency

Q: Which measure is best for skewed distributions?

A: The median.

Central Tendency

Q: Which measure is best for categorical data?

A: The mode.

Variability

Q: What does standard deviation tell us?

A: How spread out the scores are around the mean.

Variability

Q: If all values in a group are the same, what is the SD?

A: Zero.

Normal Curve

Q: What percentage of data falls within ±2 SD of the mean?

A: About 95%.

Normal Curve

Q: Why are normal curves important for parametric statistics?

A: Many tests assume normally distributed data.

because many parametric tests assume data follows a normal distribution, which allows accurate predictions, comparisons, and probability calculations.

Levels of Measurement

Q: Give an example of nominal data.

A: Pass/fail; type of error.

Levels of Measurement

Q: What level of measurement includes true zero?

A: Ratio (e.g., vowel duration, Hz).

Levels of Measurement

Q: What level of measurement are severity ratings (mild, moderate, severe)?

A: Ordinal.

Parametric vs. Nonparametric

Q: When do you use parametric tests?

A: When data are normal, interval/ratio, and variances are equal.

Parametric vs. Nonparametric

Q: When do you use nonparametric tests?

A: When data are skewed or ordinal/nominal.

Analyzing Differences

Q: What test compares two groups with small samples?

A: t-test.

Analyzing Differences

Q: What test compares more than two groups?

A: ANOVA.

Analyzing Differences

Q: What do post hoc tests show?

A: Which specific group differences are significant.

Post hoc tests show which groups are different from each other after the main test says there is a difference.

(like ANOVA).

Significance Testing

Q: What does alpha (α) represent?

A: Probability of making a Type I error (rejecting null when it’s true).

Alpha (α) represents the significance level, or the probability of making a Type I error — rejecting the null hypothesis when it is actually true.

Significance Testing

Q: What’s the conventional alpha for exploratory studies?

A: 0.05.

Significance Testing

Q: What’s the difference between one-tailed and two-tailed tests?

A: One-tailed - directional prediction; two-tailed - nondirectional.

Significance Testing

Q: Does statistical significance mean clinical significance?

A: No, a statistically significant result may not be meaningful in practice.

Correlation & Regression

Q: What does Pearson’s r measure?

A: The strength and direction of the relationship between two interval/ratio variables.

Pearson’s r measures the strength and direction of the linear relationship between two variables.

Correlation & Regression

Q: What does r² represent?

A: Percent of variance shared between two variables.

Correlation & Regression

Q: What is regression used for?

A: Predicting an outcome variable using one or more predictor variables.

Regression is used to predict the value of one variable (the outcome) based on another variable (the predictor) and to see how strongly they are related.

Effect Size & Power

Q: What is Cohen’s d?

A: An effect size that measures the difference between two group means in SD units.

it tells you how big the difference is between two group means in standard deviation units.

Effect Size & Power

Q: What value of Cohen’s d is considered large?

A: 0.80.

Effect Size & Power

Q: What does power analysis determine?

A: The sample size needed to detect an effect at a given alpha level.

it helps balance study size so you don’t test too few people (risk missing an effect = Type II error) or too many people (wasting time/resources).

Graphs & Results

Q: When should you use a bar graph?

A: To show group differences in means, percentages, or frequencies.

Graphs & Results

Q: When should you use a line graph?

A: To show changes over time, trends, or interactions.