chapters 1-4 Flashcards
population
ALL set of items of interest
census
measures every member of a population
sample
measures from a subset of the population, and then used to find out info about all the population
census +
completely accurate
census -
- time consuming
- expensive
- cant be used when testing destroys item
- hard to process large quantities
sample +
- cheaper
- less time
- less data to process
sample -
- less accurate
- sample not large enough to represent small subgroups
3 types of random sampling
- simple random
- systematic
- stratified
how to carry out a simple random sample
- get sample frame
- number each member from 1-n
- use a random number generator to generate x random numbers between 1 and n
- select those who correspond
what is random sampling
each member of pop has an equal chance of being selected
simple random + and -
+
- no bias
- easy and cheap
- each sampling unit known and equal
-
- not suitable for large
- sampling frame needed
systematic
- chosen at regular intervals from an ORDERED list
- eg sample size 20 from 100
-100/20 so every 5th person - random for 1st person, eg if its the 2nd then it goes 2,7,12
systematic +
- simple quick
-suitable for large
systematic -
- sampling frame needed
stratified sampling
- population split into MUTUALLY EXCLUSIVE strata and random sample from each
-eg questionnaire for 80 workers in diff groups - num from each group = group/total * 80 (round to nearest whole)
- number each worker
- random number generator
stratified sampling + -
+
- proportional representation of each group
- reflect population structure
-
- distinct stratta
quota sampling
- interviewer chooses sample that reflects pop
- do same calc as stratified
- but ignore extra x caught when quota for each is full
quota + -
+
- small sample still representatie
- not sampling frame
- quick, easy, cheap
-
- bias
- pop in groups
- non responses not recorded
opportunity sampling
sample from people available at time who fit criteria