Understanding Non-Random Sampling: Quota and Opportunity Sampling Explained

so the other type of sampling is non-random sampling okay and there are two types of

non-random sampling they're almost the same thing though so this first type we're gonna look at is called

quota sampling now let me just draw your attention to this bit at the bottom of

the page here the word quota is a fixed share or a number of something so we're talking

about getting getting a quota something is going to be something to do with that so i've said consider the following

scenario you wish to conduct a survey in the uk on whether being left-handed affects iq

iq is like an intelligent question it's how intelligent you are so we need to choose people to assess

why would a random sampling be problematic the reason it would be problematic is

because we don't know the sampling frame i.e we don't have a list of all the left-handed and non-left-handed

people in the uk you could have a phone directory or you could have like a list of residents

but it's we don't have anywhere where it says you've ever had to save your left-handed

or right-handed so you can't do a random sample because in a random sample you need a list of

people to be able to pick them from whether that's a stratified sample a simple random sample

or a systematic sample you always need a sampling frame so if you don't have a sampling frame

quota sampling is going to be something you're going to want to try and do so for this scenario we'd like to use

quota sampling i.e as with stratified sampling you divide the population into groups according to

the characteristic of interest and then you determine the size of each group in the sample to reflect the

proportions within the population so in this case our quotas would be left-handed and right-handed

but instead of doing random sampling in within each group we actively choose people within each

group via suitable means so you could maybe do advertising or you could ask people

until the quota for each group is filled up so the difference with this one is you

still do a stratified sample to begin with but to be able to get the people you can't pick them from a list

you have to try and get those people to come to you have to do an advert or you have to try and find them somewhere to

do it so i've said for example an interviewer could meet people assess the group that

they are in and then allocate them into the appropriate quota so they could put them

into the group of being left or right-handed if a person refuses to be interviewed or

if the quota is already full they just move on to the next person so this is one way you're kind of having to

get the people to fill up the quotas to fill up the groups so here is a summary of what quotes of

sampling is the population is divided into groups according to characteristic

a quota of items or people in each group is set to try and reflect the group's proportion in the whole population

it's carried out by an interviewer selecting the actual sampling units the advantage is that the advantages are

that it allows a small sample to still be representative of the population it's still got that stratified sample

feature no sampling frame is required that's probably the most important one it's quick easy and inexpensive and it

allows for easy comparison between different groups and the population because you've already put them into

their strata the disadvantages is that there's some non-random sampling can introduce

bias because there's there if you're doing an advert for people who are left-handed

they may be a particular kind of person who responds to an advert which means that there may be some bias

in there population must be divided into groups which can be costly or inaccurate and increasing the scope of the study

increases the number of groups adding time or expenses non-responses are not recorded if

someone says they don't want to be included in the survey they are not included and that that is

just means that they're not then their answers aren't even going to be considered

so that's what quota sampling is and here's an example of what quota sampling might look like in an

exam question so it says that a lake contains three species of fish there are estimated to be 1400

trout 600 bass and 450 pike in the lake three different types of fish a survey

of the health of the fish in the lake is carried out and a sample of 30 fish is chosen

give a reason why stratified rambling random sampling cannot be used so the reason they can't do stratified

random sampling is because we don't have a sampling frame for the fish in the lake we could never

have a list of every fish who lives in a lake so we can't do the stratified rambling

random sampling we need to state an appropriate sampling method for the survey

well it's going to be quota sampling and then it says give one advantage and one disadvantage of this sampling method so

the advantages you could say is the sample can be obtained quickly the costs are kept to a

minimum the administration of the survey is easy meaning doing the survey is easy the disadvantage is

it's not possible to estimate the sampling errors the process isn't random and the surveyor may not be

able to identify the species of fish easily but i think the most obvious one there is that the process is not random

then it just says explain how this sampling method could be used to select the sample of 30 fish

you must show you're working so this thing that we've got here where you're calculating the quota

is like the same thing as stratified sampling you'll be finding how many fish from each group that you need

so they've worked out you would need 17 trout seven bass and six

pikes then when you do the rounding then so it says fish are caught from the lake until the quarter of 17 trout seven bass

and six pike are reached if a fish is caught and the species quota is full

then this is ignored and the fish is put back into the lake so it's the same thing as stratified

sampling apart from you just have to kind of get the stuff and then if you've got space in that

quota you do the survey or you keep the fish otherwise you put it back in you don't

do the survey the second type is really similar to quota sampling

but it's called opportunity sampling it says that a variant of quota sampling is called opportunity or sometimes called

convenience sampling this is where we find people at the same

time the survey is being carried out so it's opportunity opportunity because you know

if someone is opportunistic it means they just take advantage of what the opportunity is

or convenience because it's convenient to do it at the same time as the survey and this is most similar to things like

exit polls at polling stations in politics when people leave after they voted

someone in some places will say who did you vote for and then they will record their answer this is an example of an

opportunity sample or a convenience sample this is not a suitable method for the left-handed

example because we were trying to say how left-handedness related to iq

and if you were going to try and do that left-handed example giving the likely time-consuming nature

of assessment coupled with with the resources required we'd likely arrange with the people

uh taking part before the actual assessment tasks took place because you wouldn't want to just find

someone like oh you're left-handed do you mind spending an hour with me finding out what your iq

is it's not convenient to do it at that time because it's quite a big test

so let's look at these things opportunity or convenience sampling what it is the sample is taken from people

who are available at the time of the study who meet the criteria how do you carry

it out the interviewer selects the actual sampling units according to the set criteria

uh the advantage is that it's easy to carry out and inexpensive and its disadvantages as it's unlikely

to provide a representative sample and it's highly dependent on the individual researcher

the most common thing that we think of for convenience sampling or opportunity sampling

is if um i don't know people coming out of a supermarket and they would say oh do you buy walkers

crisps and they would do the survey immediately for people who are like just happen to

be there at the supermarket so that's kind of the difference between those two things that

you've got there the main thing that makes a difference between the random sampling and the

non-random sampling is that random sampling you need to have a sample sampling frame you need to have

a list of every one non-round random sampling you don't need to have a list of every one

just like the fish in the lake or whether people are left-handed or right-handed

you're just gonna find them and then see if you can get them to fill up so we're gonna just try questions from

exercise 1c and that's going to be your homework just to do those and then when we come back next lesson we'll be doing

some other bits as well okay