Statistics

Create a free account to open this chapter.

• Deterministic vs. statistical questions ~8 min
• Populations, samples, and the inference gap ~8 min
• Parameters vs. statistics ~8 min
• Descriptive vs. inferential statistics ~8 min
• Observations, variables, and the data matrix ~8 min
• Qualitative vs. quantitative variables ~8 min
• Discrete vs. continuous variables ~8 min
• Levels of measurement ~10 min
• What a statistic cannot tell you ~8 min

Create a free account to open this chapter.

• Census vs. sample ~6 min
• Observational studies vs. experiments, previewed ~8 min
• Simple random sampling ~8 min
• Stratified sampling ~8 min
• Cluster sampling ~8 min
• Systematic sampling ~6 min
• Convenience and voluntary-response sampling ~8 min
• Undercoverage and sampling bias ~8 min
• Nonresponse and response bias ~8 min
• Choosing a sampling design ~8 min

Create a free account to open this chapter.

• Experimental units and treatments ~8 min
• Control groups and the placebo effect ~8 min
• Randomization and why it works ~8 min
• Replication and blocking ~8 min
• Matched-pairs designs ~8 min
• Confounding variables ~8 min
• Blinding and double-blinding ~6 min
• Causation vs. correlation: a first pass ~8 min
• Ethical considerations in experiments ~6 min
• Reading a study's design critically ~8 min

Create a free account to open this chapter.

• Raw data to a frequency table ~8 min
• Relative and cumulative frequency ~8 min
• Choosing class intervals ~8 min
• The histogram ~8 min
• Bar charts and pie charts, categorical data ~8 min
• Dot plots and stem-and-leaf plots ~8 min
• Line graphs and time series ~8 min
• The box plot, previewed ~8 min
• Scatterplots, previewed ~6 min
• Choosing the right display ~8 min

Create a free account to open this chapter.

• The mean ~6 min
• The median ~8 min
• The mode ~6 min
• Mean from a frequency table ~8 min
• The trimmed mean ~8 min
• Mean vs. median under skew ~8 min
• Resistant vs. non-resistant measures ~8 min
• Choosing a measure of center ~8 min

Create a free account to open this chapter.

• The range ~6 min
• Deviations from the mean ~7 min
• Variance, defined ~8 min
• Standard deviation and its units ~7 min
• Population vs. sample standard deviation ~8 min
• The interquartile range ~7 min
• The mean absolute deviation ~6 min
• Comparing spread across datasets ~7 min
• Why standard deviation, not variance, for interpretation ~6 min

Create a free account to open this chapter.

• Percentiles and quantiles ~7 min
• Quartiles and the five-number summary ~7 min
• The interquartile range, revisited ~6 min
• The 1.5×IQR outlier rule ~8 min
• The z-score ~7 min
• Standardizing a distribution ~6 min
• Comparing scores across different distributions ~8 min
• Reading a box plot ~7 min

Create a free account to open this chapter.

• A statistic is a random variable, revisited ~7 min
• Simulating the sampling distribution of a mean ~8 min
• Simulating the sampling distribution of a proportion ~7 min
• Conditions for the normal approximation ~8 min
• Standard error, applied ~7 min
• Effect of sample size on standard error ~7 min
• Bias vs. variability in an estimator ~8 min
• Where probability ends and statistics begins ~6 min

Create a free account to open this chapter.

• Point estimates vs. interval estimates ~6 min
• What a margin of error is ~6 min
• Building a confidence interval from a standard error ~8 min
• Confidence level, defined ~7 min
• What 95% confidence does mean ~8 min
• What 95% confidence does not mean ~8 min
• Confidence level vs. precision ~7 min
• Reading a reported confidence interval ~7 min

Create a free account to open this chapter.

• The one-sample z interval, known sigma ~7 min
• Why sigma is rarely known in practice ~6 min
• The Student's t distribution ~8 min
• Degrees of freedom ~7 min
• The one-sample t interval ~8 min
• Conditions for a valid t interval ~7 min
• Sample size and interval width ~7 min
• Choosing z vs. t ~6 min

Create a free account to open this chapter.

• The sample proportion as an estimator ~6 min
• The one-proportion z interval ~8 min
• Conditions for a valid proportion interval ~7 min
• Margin of error for a proportion ~6 min
• Choosing a sample size in advance ~8 min
• Proportions in polling, an applied read ~6 min

Create a free account to open this chapter.

• The null and alternative hypotheses ~7 min
• Assuming the null to judge the evidence ~7 min
• The test statistic ~7 min
• The p-value ~8 min
• Significance level, alpha ~7 min
• The critical-region view ~7 min
• Type I and Type II errors ~8 min
• The power of a test ~8 min
• Statistical vs. practical significance ~7 min
• One-tailed vs. two-tailed tests ~8 min

Create a free account to open this chapter.

• The one-sample z test for a mean ~7 min
• The one-sample t test for a mean ~7 min
• The one-sample test for a proportion ~7 min
• Matching a test to its conditions ~6 min
• The test-interval duality ~7 min
• Interpreting a p-value correctly ~6 min
• Common p-value misreadings ~6 min
• Writing a full test conclusion ~6 min

Create a free account to open this chapter.

• Independent vs. paired samples ~6 min
• The sampling distribution of a difference in means ~7 min
• The two-sample t test, independent samples ~8 min
• Pooled vs. unpooled variance ~8 min
• The paired t test ~7 min
• The two-sample z test for proportions ~7 min
• Confidence interval for a difference ~7 min
• Effect size, a first look ~6 min
• Choosing the right two-group procedure ~8 min

Create a free account to open this chapter.

• Contingency tables ~6 min
• Expected counts under independence ~7 min
• The chi-square statistic ~7 min
• The chi-square distribution's shape ~6 min
• The chi-square goodness-of-fit test ~8 min
• The chi-square test of independence ~8 min
• The chi-square test of homogeneity ~8 min
• Conditions and common misuses ~7 min

Create a free account to open this chapter.

• Scatterplots and association, revisited ~6 min
• Strength and direction of a linear relationship ~7 min
• The Pearson correlation coefficient ~8 min
• Interpreting r ~7 min
• Correlation is not causation, formalized ~7 min
• Outliers and influential points on r ~7 min
• When correlation is the wrong tool ~7 min

Create a free account to open this chapter.

• The least-squares line ~7 min
• Slope and intercept, interpreted ~6 min
• Making a prediction from the line ~5 min
• Residuals ~6 min
• The residual plot ~6 min
• R^2, the proportion of variance explained ~7 min
• Standard error of the regression ~6 min
• Conditions for a valid linear model ~7 min
• Extrapolation ~6 min
• Influential points on the regression line ~7 min

Create a free account to open this chapter.

• Adding a second predictor ~8 min
• Interpreting a partial-slope coefficient ~8 min
• Multiple R^2 and adjusted R^2 ~9 min
• Categorical predictors as dummy variables ~8 min
• Multicollinearity ~8 min
• Interaction effects, a first look ~8 min
• Prediction vs. explanation ~8 min
• Reading a multiple-regression output table ~8 min

Create a free account to open this chapter.

• Comparing more than two means at once ~7 min
• Within-group and between-group variation ~8 min
• The F-statistic ~8 min
• Reading an ANOVA table ~7 min
• One-way ANOVA ~8 min
• Post-hoc comparisons, a first look ~8 min
• Conditions for ANOVA ~8 min

Create a free account to open this chapter.

• When parametric conditions fail ~6 min
• Rank-based methods, the idea ~6 min
• The sign test ~7 min
• The Wilcoxon signed-rank test ~8 min
• The Mann-Whitney U test ~8 min
• Trade-offs against a parametric test ~7 min

Create a free account to open this chapter.

• What software adds beyond a hand calculation ~6 min
• Reading a regression output table ~8 min
• Reading an ANOVA output table ~7 min
• Reading a hypothesis-test output block ~7 min
• Data-cleaning judgment calls ~7 min
• Reproducibility as a habit, not a tool ~6 min

Create a free account to open this chapter.

• Misinterpreting a p-value ~6 min
• Misinterpreting a confidence interval ~6 min
• Selection bias and survivorship bias ~7 min
• Simpson's paradox ~8 min
• The ecological fallacy ~7 min
• Regression to the mean ~7 min
• The multiple-comparisons problem ~7 min
• Misleading visualizations ~6 min
• Small-sample overreach ~6 min
• Overfitting a model ~7 min