Public Policy final

Only words I need, sorry baes

Sampling error

Errors that come from the method of sampling. This type of error is avoidable by taking random samples; can be avoided by taking LARGE samples

nonsampling error

Errors that occur even if a random method is employed

Undercoverage

Occurs when some members of the population are left out of the sampling frame. By the way, sampling frame is the list from which the sample is actually chosen

Nonresponse

The subject not answering or refusing to answer

Stratified sample

First break the sampling frame into groups.  Within each group the subjects should be similar.

Cluster sample

Using natural groups, such as boxes of apples. 

Systemic sample

Choose one random subject from the sampling frame, then take every nth subject

Experiments

Randomly assign different treatments to groups to see if they respond differently. CAN DETERMINE CAUSE AND EFFECT

Observational study

CANNOT DETERMINE CAUSE AND EFFECT

Confounding with lurking variables

Impossible to tell if the response variable is caused by the treatment or another variable

Statistically significant

A difference seen in the measured effects in two treatment groups is too big to have happened by random chance.

Matched pair

Two subjects that are the same and get different treatments

Block

A group of two or more subjects that are alike

Categorical variable

simply places an individual into one of several groups or categories. Graphs for categorical variables include bar charts and pie charts

Quantitative variable

take on numerical values for which arithmetic operations such as adding and averaging make sense. Graphs for quantitative data include histograms and line graphs

Distribution of a quantitative variable

An explanation or graphical display of data. 

Histogram

Similar to a bar chart, but used for quantitative data.  Bars touch b/c there is no space between continuous numbers.

Class width

The width of each bar on the x-axis in a histogram. (Highest value in bar minus lowest value in bar). 

SOCS

Shape, outlier, center, spread

Five number summary

Distribution consists of the smallest observation, the first quartile, the median, the third quartile, and the largest observation, written in order from smallest to largest. In symbols, the five-number summary is: Min, Q1, Med, Q3, Max

Density curve

A shape that has a total area of 1

Normal curve

A special type of density curve which occurs naturally and is used to estimate probabilities

Z score

standard deviation from the mean

DUFS

• Direction: positive (up), negative, neither

• Unusual feature: Points that do not follow the trend

• Form: linear or non linear

• Strength: Strongly linear, moderately, or weakly

Correlation Coefficient

A number from -1 to +1 used to describe the strength of a linear relationship between two quantitative variables

Regression line

A straight line that describes how a response variable, y, changes as eXplanatory variable, x, changes. Often used to predict  the value of y for a given value of x

Residual

Space between regression line and actual data points. Smaller residuals are better

Regression formula

y = a + bx

a = y intercept

b = slope

Extrapolation

Prediction too far outside the boundaries od the explanatory data. This can lead to poor predictions and should be avoided.

Index number

Describes the percent change from a base period

Market basket

A collection of goods and services whose total cost we follow

Fixed market basket

The index number for a market basket

CPI

An index number for the cost of everything that American consumers buy

CPI formula

Dollars at time A = Dollars at time B (CPI at time A / CPI at time B)

Random phenomenon

Individual outcomes are uncertain, but there is, nonetheless, a regular distribution of outcomes in a large number of repetitions. 

Personal probability

the outcome of a number between 0 and 1 that expresses an individuals judgement of how likely the outcome is

Expected value

average of the possible outcomes in which outcomes with higher probability count more.  

Law of large numbers

if a random phenomenon with numerical outcomes is repeated many times independently, the mean of the actually observed outcomes approaches the expected value.  

Sampling frame

A list from which your sample is taken.  Not everyone in the frame is chosen.  The subjects that are chosen become your sample.

Percent change formula

(Amount of change (subtract) / Starting value) (100)