Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
1c UNPRINTED
Statistics
| Question | Answer |
|---|---|
| Population | Group of people or things that you are finding information about (e.g. all employees in an office, all items produced in a factory). To investigate the hypothesis data can be collected from the whole population (census) or part of the population (sample) |
| Sample | Smaller group of population used to collect data, by sampling Collected data can be used as estimates + conclusions for whole population Quicker, cheaper + more practical but less accurate + may be biased Sample must fairly represent population |
| Biased sample | doesn't represent whole population To avoid this, only choose items from the sample frame (sample from the correct population) and select it at random. A bigger sample is more representative. It is more reliable data, but less practical to collect. |
| Variability between samples | Two samples randomly chosen from the same population won't have the same data |
| Sample frame | A list or map of all the members of the population, made before a sample is chosen. It’s easier to do this with a small (easier to list it all) and well-defined (know what to include) population. |
| Judgement sampling | Judgement is used to choose a sample Useful when investigating something obscure + specific as representative sample ischosen Quick + maybe only suitable method but researcher may be unreliable and biassed if good judgement and knowledge isn't used |
| Opportunity (convenience) sampling | Sample taken from a section of population present at a particular place or time, useful for convenience + ease but not random Easier for interviewer + doesn't need a sample frame, but it can be very biassed as there is no attempt at being representative |
| Cluster sampling | Cluster randomly picked from sample frame+all members sampled Multiple clusters prevent bias Closer cluster member distribution is to whole population,less bias Only need cluster list+sample cluster members Convenient, less travel timebut can be bias |
| Quota sampling | Population divided into groups with a common theme Interviewer interviews some of people from each group Final choice of sample members is by interviewer so not entirely random Quick, decent representation + good w/no sample frame, but easy bias |
| Random sampling | Every person/item in population has equal chance of being chosen Full sample frame needed. It is completely unbiased and should represent the population, but it's not always convenient and may be impossible to access everyone or list the whole population |
| Systematic sampling | Random starting point chosen + sample taken at regular intervals afterwards Good for large population + quality control checks on mass production line Unbiased + can be done by a machine, but the nth item may coincide with a pattern leading to bias |
| Simple random sampling | a method for choosing a random sample that is easiest with a small, well-defined population. Each item should have the same likelihood of inclusion, so duplicate numbers should be skipped |
| Simple random sampling method | 1Assign number to every member in sample frame 2Use computer, random number table/list, dice/cards etc. to create a list of random numbers 3Match the numbers of the members in the sample frame to the numbers on the random list to create a sample |
| Stratified sampling | Used on categorised/grouped populations Gives different groups a proportional representation Useful when different groups may give different results More than one category can be stratified from |
| Stratified sampling (pros and cons) | If there are easy to define categories, a representative sample is likely and results can be compared across groups, but it can be expensive due to the extra detail and hard if categories aren't obvious. |
| Method for choosing stratified sample | 1Split population into categories 2Calculate the number to sample from each category using: (number in category / total number) * sample size 3Use random sampling to choose the sample members from each category |
| Strata | another word for category |
Created by:
FlashCardFun!