basic statistics concepts - Nc State University · Basic Statistical Concepts CRSC- SAMSI Workshops Jiezhun (Sherry) Gu Department of Statistics. 5/31/2005 2 What is statistics? Statistics

5/31/2005 1

Basic Statistical ConceptsCRSC- SAMSI Workshops

Jiezhun (Sherry) GuDepartment of Statistics

5/31/2005 2

What is statistics?

Statistics is the science of making inference based on the data.

5/31/2005 3

What is sample space?

The set S, of all possible outcomes of a particular experiment is called the sample space for the experiment.

5/31/2005 4

What is an event?

An event is any collection of possible outcomes of an experiment, that is, any subset of S (including S itself).

5/31/2005 5

Frequentist interpretation of probability: Probability is the language used to capture certain phenomena with unpredictable outcomes, such phenomena are said to be random. Bayesian interpretation of probability: degree of plausibility that an event will occur.

What’s probability?

5/31/2005 6

What is random variable?

5/31/2005 7

Property of random variable

continuity:

5/31/2005 8

Property of random variableIndependency:

(1) Two events A and B are independent iff P(A ∩B)=P(A)P(B)(2) Two random variables X and Y are independent iff for any numbers a and b the events [X ≤ a] and [Y ≤ b] are independent events as defined above. (3)Similarly an arbitrary collection of random variables -- possible more than just two of them -- is independent precisely if for any finite collection X1, ..., Xn and any finite set of numbers a1, ..., an, the events [X1 ≤ a1], ..., [Xn ≤ an] are independent events as defined above.

5/31/2005 9

Property of random variable

Univariate or Multivariate

5/31/2005 10

Probability function on random variable:

Probability density function, when random variable is continuous.Probability mass function, when random variable is discrete.

5/31/2005 11

DEF: Populations and Samples

A data sample is taken from a population.

5/31/2005 12

DEF: Parameters & Statistics

5/31/2005 13

Statistical summary

Sample mean

Sample variance

2 2

1

1 ( )1

n

ii

S X Xn =

= −− ∑

1

1 n

ii

X Xn =

= ∑

5/31/2005 14

Statistical summary

A confidence interval is an interval constructed about the parameter estimate in a manner such that (1-α) % of all samples will produce an interval containing the true parameter.

5/31/2005 15

What is Model?

5/31/2005 16

Deterministic Models

Deterministic models are fixed; same inputs always result in the same output.

5/31/2005 17

Stochastic Models

Stochastic models have random output based on the probability distribution of the random variable.

Parametric statistical model

Nonparametric statistical model

5/31/2005 18

Normal distribution

5/31/2005 19

Standard Normal

5/31/2005 20

Central Limit theorem

As the sample size gets very large, the distribution of the sample means becomes normal.

5/31/2005 21

What statistics Can Do?

If we know our model, we can make predictions about future outcomes.

5/31/2005 22

What statistics Can Do?

5/31/2005 23

What statistics Can Do?

5/31/2005 24

What statistics Can Do?

Confidence Interval- Large Sample

5/31/2005 25

What statistics Can Do?

Confidence Interval- Small Sample

5/31/2005 26

Thank You