# prob and statistics 1

simple random sampling

every individual has an equal chance of being chosen

stratified random sampling

1. divide people into groups or strata (groups of similar individuals)
2. take a simple random sample
3. combine it to make one sample
c*good for selecting from a large population or when different strata will produce different results

cluster sampling

1. divide population into clusters
2. randomly select a cluster
3.sample all in the cluster

systematic sampling

1. pick random starting point
2. sample every Kth person

convenience sampling

surveying the people easier to reach
*not a good method because it results in bias

experiment

assign a treatment

Observation

observing what participants do naturally

explanatory variable

the variable that may explain or cause differences, we manipulate
"factor" "IV

response variable

what we measure, or the outcome
"DV

treatment

one or a combination of categories of the explanatory variable assigned by the experimenter

experimental units

smallest basic objects to which we assign different treatments in a randomized experiment

observational units

the objects or people measured in any study

participants or subjects

people

control

control sources of variation other than what's being tested, keep conditions as similar as possible
(what makes a good experiment)

randomize

allows us to equalize the effects of unknown or uncontrolled sources of variation (doesn't eliminate it but spreads it out)
(what makes a good experiment)

replicate

apply each treatment to several subjects, repeat experiment again with other subjects (more than one trial)
(what makes a good experiment)

randomized experiment

create differences in the explanatory variable and examine the results

Observation study

observe differences in the explanatory variable and notice whether these are related to differences in the response variable

data

collection of facts, measurements, or observations on a set of individuals. It could be numbers, words, or descriptions

qualitative data

-description
-can be put into categories

quantitative data

assigned a numerical value

discrete data

-can only take certain values
-whole #'s
-something thats counted
*ex: number of people

continuous data

-can take any value
-measured

population

ever member of a set
(example: period 3 stats)

sampling frame

a list of individuals from whom the sample is drawn
(example: period 3 stats roster)

sample

a subset of the population
(example:girls in period 3 stats)

census

when you collect data from every member of the population

sample survey

bias

sampling methods, by their nature, tend to over or under-emphasize some characteristics of the population
*any data with biased results cannot be used

under-coverage bias

when some portion of the population is not sampled at all or has a smaller representation in the sample

voluntary response bias

the sample is not representative, even though every individual in the population may have been offered the chance to respond
-people who feel the most strongly will volunteer

non-response bias

a common and serious source of bias
- no survey gets a response from everyone, those who don't respond may differ from those that do
*bias occurs when large fractions of people chosen don't respond

response bias

anything in a survey design that influences responses

interviewer bias

may not be as honest/ truthful based on who is asking the question
(example:teacher vs. Friend)

wording bias

steer the question in one way or another

example of simple random sampling

80 students are enrolled in stats, we want to select 5.
*Use popsicle sticks or pull names out of a hat

example of stratified random sampling

interested in high school students, survey 100, select 25 from each grade. this prevents all students from being in the same grade

example of cluster sampling

interested in ap stats students in litchfield county. pick 3 or 4 schools and survey all students in AP stats at those schools

example of systematic sampling

want to survey 1000 students at a university. take sampling frame and start at 11th person and select every tenth student
*numbers can change and it doesn't matter what number person you select

example of convenience sampling

interviewing shoppers by going o kmart and talking to those that are leaving
(doesn't represent all shoppers-- only those that shop @ kmart)

extraneous factor

a variable that is not of interest in the current study but is thought to affect the response variable

confounding variable

associated in a noncasual way. it affects the response. cant tell whether the effect was a factor, confounding variable, or both

direct control

holding extraneous factors constant so that their effects are not confounded with those of the experimental conditions

blocking

When groups of experimental units are similar, it is often a good idea to gather them together
into blocks. By blocking, we isolate the variability attributable to the differences between the blocks
so that we can see the differences caused by the treatme

randomized block design

the random assignment of experimental units to treatments is carried out separately within each block

placebo

a treatment known to have no effect

placebo effect

the tendency of many human subjects to show a response even when administered a placebo

blinding

any individual associated with an experiment who is not aware of how subjects have been allocated to treatment groups

double-blind

the subjects and those evaluated are both blinded