Not everything that counts can be counted, and not everything that can be counted counts.

He uses statistics as a drunken man uses lamp posts - for support rather than for illumination.

Information is useless unless you know how to interpret it.

Prefer stats than narratives. We have two kinds of forecasters: The ones who don't know and the ones who don't know they don't know.

Correlation is not causation, but it's a good place to start looking.

The most dangerous statistical error is confusing statistical significance with practical importance.

Data never speaks for itself - it whispers, and we must learn to listen carefully to what it's actually saying.

Statistics are the grammar of science - they give structure to our observations but require interpretation to create meaning.

The average is the statistical version of 'nobody in particular' - often useful, sometimes misleading, always incomplete.

Sample size matters more than mathematical sophistication. A beautiful analysis of bad data is still wrong.

Probability is the language of uncertainty, and statistics is the art of drawing conclusions despite it.

Outliers are not noise - they're signals that your model is incomplete or your understanding is flawed.

Statistical thinking is recognizing that every number has a story, and every story has numbers left untold.

Confidence intervals reflect our uncertainty, not the truth's variability. The map is not the territory.

Data can only answer the questions we think to ask. The most important insights often come from questions we haven't considered.

Statistical literacy is as essential as reading literacy in a world drowning in data but starving for wisdom.

The plural of anecdote is not data, but the right anecdote can reveal what the data conceals.

Statistical models are like caricatures - they emphasize certain features while ignoring others. Choose your distortions wisely.

Numbers don't lie, but liars use numbers. The truth is in the methodology, not the results.