Test Review

Front 1

Confidence interval

Back 1

Estimated range of values which is likely to include an unknown population parameter, the estimated range being calculated from a given set of sample data

We say we are 95% confident that the population mean lies between.....

Front 2

Point estimates

Back 2

A statistic that is used to estimate an unknown constant or parameter. Once data is collected we call it a point estimate. Sample mean for example

As an estimate of population mean (sample mean)

An estimate of success probability ( is sample proportion)

In order to be useful necessary for point estimate to describe how far off from true value.

Front 3

T distribution

Back 3

Used for small samples for approximately normal population

Front 4

Chi square distribution

Back 4

Probability distribution based on variance or sample variance.

a probability density function that gives the distribution of the sum of the squares of a number of independent random variables each with a normal distribution with zero mean and unit variance, that has the property that the sum of two or more random variables with such a distribution also has one, and that is widely used in testing statistical hypotheses especially about the theoretical and observed values of a quantity and about population variances and standard deviations

Front 5

Bernoulli distribution

Back 5

Experiment that can result in one of two outcomes. Success p and failure (1-p)

Front 6

Binomial distribution

Back 6

N bernoulli trials that are independent, each trial has same success p.

Front 7

Poison distribution

Back 7

Approximation to binomial distribution when n is large and p is small

Front 8

Independent

Back 8

When trials dont impact one another

Front 9

Discrete versus continuous distributions

Back 9

Fixed values versus over a range

Front 10

Geometric distribution

Back 10

Sequence of independent bernoulli trials each success p, X is number of trials up to and including first success. X discrete random variable with geo dis with parameter p.

Front 11

Negative binomial distribution

Back 11

Extension of geometric trials up to and including rth success

Front 12

Multinomial trials

Back 12

Like bernoulli but can have k outcomes

Front 13

Normal distribution

Back 13

Good for many continuous populations. Bell shaped curve. Mean may have any value and variance may have any positive value.

Front 14

Z

Back 14

Z-score of x. Item sampled from normal population with mean 0 and std. dev 1

Front 15

Lognormal distribution

Back 15

Data that contains outliers. X=lnY has N(mu,sigma^2) distribution

Front 16

Uniform distribution

Back 16

Two parameters a and b with a<b. X is random variable with continuous uniform distribution then uniformly distributed on (a,b)

Front 17

Statistic

Back 17

A quantity calculated from the data

Front 18

Accuracy of estimator

Back 18

Measured by bias and precision is measured by its standard deviation or uncertainty.

Front 19

Mean square error

Back 19

Want to be as small as possible. Measures overall goodness of an estimator. Combines both bias and uncertainty.

Front 20

Central limit theorem

Back 20

If n is sufficiently large the sum of random samples is approximately normal.

Front 21

Continuity correction

Back 21

To include endpoints in probability calculation extend each endpoint by 0.5. Adjustment made when approximating a discrete distribution with a continuous one.

Front 22

Stimulation

Back 22

The process of generating random numbers and treating them as if they were data generated by an actual scientific distribution.