Thinking Like an Investigator · 15 minutes
Measurement and Representation
Does numeric coding make a variable continuous?
Begin module →Master learning library
Evergreen modules organized around questions investigators need to answer.
Thinking Like an Investigator · 15 minutes
Does numeric coding make a variable continuous?
Begin module →Samples and Populations · 16 minutes
Why does an estimate change when the population stays fixed?
Begin module →Samples and Populations · 17 minutes
What does 95% confidence look like over repeated samples?
Begin module →Samples and Populations · 18 minutes
Who gets represented, and how much independent information is present?
Begin module →Evidence · 18 minutes
What does a p-value measure, and what does it not measure?
Begin module →Relationships · 13 minutes
Among whom is the percentage being calculated?
Begin module →Relationships · 17 minutes
How far are observed counts from independence?
Begin module →Relationships · 14 minutes
What evidence can a small, sparse 2×2 table provide?
Begin module →Relationships · 15 minutes
How large is the difference in proportions?
Begin module →Relationships · 16 minutes
Should the contrast be absolute, relative-risk, or odds based?
Begin module →Evidence · 15 minutes
Is an association detectable, important, or both?
Begin module →Causal Reasoning · 15 minutes
What claim does the study design support?
Begin module →Causal Reasoning · 17 minutes
What job does a third variable perform in the analytical argument?
Begin module →Causal Reasoning · 18 minutes
Which path are you trying to block without opening another?
Begin module →Causal Reasoning · 18 minutes
How can different group composition distort a crude comparison?
Begin module →Regression · 15 minutes
How can the same chance be expressed on three different scales?
Begin module →Regression · 16 minutes
How can a linear predictor produce probabilities between zero and one?
Begin module →Regression · 18 minutes
How does one model relate a binary outcome to several explanatory variables?
Begin module →Regression · 16 minutes
Why does an odds ratio depend on baseline risk when translated to probability?
Begin module →Regression · 17 minutes
What probability does the fitted model imply for a defined profile or population?
Begin module →Regression · 16 minutes
Did the coefficient change because of adjustment or because the sample changed?
Begin module →Regression · 19 minutes
Does a candidate model fit adequately and answer the intended question?
Begin module →Regression · 14 minutes
What quantity does the research question require?
Begin module →Regression · 15 minutes
How can a two-group mean difference be written as a model?
Begin module →Regression · 15 minutes
What does a one-predictor slope add to correlation?
Begin module →Regression · 18 minutes
What does OLS estimate?
Begin module →Regression · 16 minutes
What does holding constant mean?
Begin module →Regression · 15 minutes
What does a residual reveal?
Begin module →Regression · 15 minutes
Is a straight-line mean relationship plausible?
Begin module →Regression · 15 minutes
Does outcome variability change across fitted values?
Begin module →Regression · 15 minutes
Does one observation have disproportionate influence?
Begin module →Regression · 15 minutes
Can the data distinguish the included predictors?
Begin module →Regression · 16 minutes
How should a predictor enter the model?
Begin module →Regression · 15 minutes
What does the outcome scale mean?
Begin module →Regression · 16 minutes
Would a reasonable alternative change the conclusion?
Begin module →Evidence · 15 minutes
When does model comparison become specification searching?
Begin module →Regression · 18 minutes
Does an association differ across groups?
Begin module →Evidence · 17 minutes
Can you defend the analysis as an investigator?
Begin module →Relationships · 14 minutes
What can shape reveal before any test is run?
Begin module →Relationships · 14 minutes
What relationship can a single correlation coefficient hide?
Begin module →Relationships · 16 minutes
Are we measuring a linear relationship or a monotonic ordering?
Begin module →Relationships · 14 minutes
When does the mean stop describing a typical observation?
Begin module →Relationships · 13 minutes
Which observations belong together?
Begin module →Relationships · 16 minutes
Are you comparing means, paired changes, or relative positions?
Begin module →Relationships · 17 minutes
How large and how uncertain is the difference in means?
Begin module →Relationships · 13 minutes
How far apart are the middle values of two populations?
Begin module →Relationships · 18 minutes
What changes when we replace observed values with their ranks?
Begin module →Relationships · 16 minutes
Are group means separated relative to variation within groups?
Begin module →