Flashcards
(374 cards)
What is “statistics” according to Dictionary.com?
The practice or science of collecting and analysing numerical data in large quantities, especially for inferring proportions in a whole from a representative sample.
How else is “statistics” defined in mathematics?
A branch of mathematics dealing with the collection, analysis, interpretation, and presentation of masses of numerical data.
Why do we need statistics in large datasets?
To distinguish between randomness and systematic features or patterns in the data.
What are the four main tasks of statistical analysis?
1) Design experiments and collect data; 2) Describe data (summary stats, graphs, tables); 3) Tests of hypotheses; 4) Model fitting (associations, prediction, classification).
Name two online video resources to learn statistics basics.
StatQuest with Josh Starmer (YouTube) and GraphPad Tutorials (YouTube).
What book helps non-mathematicians learn statistics?
“Statistics without Tears” by Derek Rowntree.
What software will you learn for statistical analysis in this course?
GraphPad Prism.
Give an example of how statistics appear in daily life.
Health apps tracking steps and heart rate, or national statistics websites reporting COVID-19 cases.
What is a “population” in statistics?
The entire group you wish to study (often too large to measure every member).
What is a “sample”?
A representative subset of the population used to infer properties about the whole.
Define an “event” in probability.
A set of possible outcomes from an experiment (e.g., rolling a die and getting a “4”).
How is probability of an event calculated?
Number of favorable outcomes ÷ total number of possible outcomes.
What range of values can probability take?
From 0 (impossible) to 1 (certain).
If a fair die is rolled, what’s the probability of getting a “2”?
1/6 ≈ 0.167.
What are “odds”?
Probability of event occurring divided by probability of it not occurring (p/(1–p)).
Convert probability p=0.2 to odds.
Odds = 0.2 / 0.8 = 0.25 (or 1:4).
How do you find probability from odds?
p = odds / (1 + odds).
What is a “random variable”?
A mapping from each outcome in the sample space to a numerical value.
Name three common probability distributions.
Normal (Gaussian), binomial, Poisson.
What percentage of data falls within ±1 standard deviation in a normal distribution?
About 68.3%.
What is a “diagnostic test” in biostatistics?
A procedure to determine presence/absence of a disease in subjects.
Define “sensitivity” of a test.
True positives / (True positives + False negatives): ability to detect disease when present.
Define “specificity” of a test.
True negatives / (True negatives + False positives): ability to rule out disease when absent.
What is Positive Predictive Value (PPV)?
True positives / (True positives + False positives): probability you have disease if test is positive.