Book

Practical Statistics For Data Scientists

Sequence ladder

Narrative Intelligence sources live outside the figurative image sequence ladder. Adaptive placement applies to image sequences, not this reading library.

Themeresearch-bulk-chunkpa_practicalstatisticsfordatascientists

Contextresearch_analysis

What this book knows

Statistical reasoning and machine learning methods, honestly applied, let data scientists build models that predict rather than merely describe.

Sex: Absent
Work: Primary
Learning: Primary
Religion: Absent

mind-and-cognitionwork-as-meaningambition-and-status

mind-and-cognition

all things being equal, a simpler model should be used in preference to a more complicated model
PA_PRACTICALSTATISTICSFORDATASCIENTISTS-RC-086
Heteroskedasticity indicates that prediction errors differ for different ranges of the predicted value, and may suggest an incomplete model.
PA_PRACTICALSTATISTICSFORDATASCIENTISTS-RC-100
KNN classifies a record by assigning it to the class that similar records belong to. Similarity is determined by Euclidian distance or other related metrics.
PA_PRACTICALSTATISTICSFORDATASCIENTISTS-RC-135

work-as-meaning

In data science, the goal is typically to predict values for new data, so metrics based on predictive accuracy for out-of-sample data are used.
PA_PRACTICALSTATISTICSFORDATASCIENTISTS-RC-105
we have used a linear model to predict a probability, which we can in turn map to a class label by applying a cutoff rule
PA_PRACTICALSTATISTICSFORDATASCIENTISTS-RC-113

ambition-and-status

Outliers could be the result of a 'fat-finger' data entry or a mismatch of units — problems a careful data scientist must detect and correct.
PA_PRACTICALSTATISTICSFORDATASCIENTISTS-RC-098

Illuminates

6 published passages · book excerpt · research analysis

Reader resonance signals for text sources are not wired to this view yet.

Loading profile…