Chapter 1 - Data Collection Flashcards
How can you define a population
The whole set of items that are of interest
Define a sample
A sub-set of the population meant to represent the whole population
What is a sampling unit
A single unit of the sample (for example if you have a sample of apples, one apple is a sampling unit)
What are two methods to take data from a population
a sample and a census
what does it mean to take a census
taking data from the entire population
what are the advantages of a census
it provides fully accurate data about the population
disadvantages of a census
it is costly, inefficient, and labour intensive due to the high volume of data needed to process
it does not work when the testing process destroys the item
what are the advantages of testing a sample
it is less costly
it is more efficient
there is less data to process
disadvantages of testing a sample
it may not be fully representative of the whole population
what is a sampling frame
when sampling units are named or numbered individually into sub-sets or lists within the sample
what are the 3 methods of random sampling
stratified sampling
systematic sampling
simple random sampling
why must samples be taken randomly
to eliminate bias from the testing
how can you define simple random sampling
a simple random sample of size n is one where every sample of size n has an equal chance of being selected
how can you carry out random sampling without bias
each unit in a sampling frame is assigned a unique number and a selection of these numbers is chosen at random
this can be done using a random number generator or a lottery system
define a lottery system
a system where members of the sampling frame are written out on tickets and are placed into a “hat”
then the desired number of units is drawn at random
how can you define systematic sampling
sampling in which the required units are chosen from a list at regular intervals
how can you carry out systematic sampling
order the sampling units in a list, if the population is 100 and you need a sample size of 20, you need to take every (100÷20=) 5th unit in the list
the first person to be chosen should be random, so you need to generate a random number between 1 and 5 (in this case) to start with.
if 2 is generated, you choose the 2nd, 7th, 12th, 17th etc. unit
what is stratified sampling
a population is divided into mutually exclusive strata (groups) (such as male and female) and a random sample is taken from each
what calculation is needed to find out the number of people needed to be sampled from each strata
number sampled in a strata = (number in stratum ÷ number in population) × overall sample size
advantages of random simple sampling
free of bias
every unit has an equal chance to be selected
simple and easy to implement for small populations
disadvantages of simple random sampling
unsuitable when population or sample size is too large
sampling frame needed
advantages of systematic sampling
simple to implement
suitable for large population and sample sizes
disadvantages of systematic sampling
sampling frame is needed
may introduce bias if sample frame is not random
advantages of stratified sampling
sample will accurately reflect the population structure
guarantees a proportional representation of groups within a population
disadvantages of stratified sampling
population must initially be classed into defined strata
selection from each stratum suffers from the same disadvantages as simple random sampling
what are the two methods of non random sampling
quota sampling
opportunity sampling
describe quota sampling
an interviewer or researcher selects a sample that reflects the characteristics of the population
how do you carry out quota sampling
the population is divided into groups according to a characteristic, the size of the group determines the proportion of the sample that should have that characteristic
the interviewer meets, assesses and allocates each unit into the appropriate quota until all quotas are full
if a unit refuses to be interviewed, they are not counted as part of the data
define opportunity sampling
it consists of taking the sample from people who are available at the time the study is carried out and who fit the criteria you are looking for
how do you carry out opportunity sampling
select the first people who are available or volunteer and use them as a sample to represent the population
advs of quota sampling
allows a small sample to represent whole population accurately
no sampling frame required
quick, simple, inexpensive
allows for easy comparison between different groups within a population
disadvs of quota sampling
may introduce bias as non random
population must be divided into groups - may be costly or inaccurate
increasing scope of study will increase number of groups which adds time or expense
non responses are not recorded
disadvs of opportunity sampling
unlikely to provide a representative sample
highly dependent on individual researcher
advs of opportunity sampling
easy
inexpensive
what is quantitative data
numerical data (measured using numbers as values)
what is qualitative data
non numerical data (colour, letter, shape etc.)
what is continuous data
give examples
data which can take any value in a given range (including decimal values)
height, weight, length, time
what is discreet data
give examples
data which can only take specific values in a range
number of people, shoe size, goals scored, correct answers on a test
how does a grouped frequency table display data
in one column, quantitative data is grouped into “classes” at the expense of losing the specific values
in the other column, the frequency (f) displays the number of instances in the class in the same row
what do class bounds tell you
they indicate the lowest and highest values that belong to each class
how can you find the midpoint of a class
add the class bounds and divide by 2 (the average of the bounds)
what are the UK weather stations from the large data set in order from north to south, which ones are coastal which are inland
Leuchars coastal
Leeming inland
Heathrow inland
Hurn coastal
Camborn coastal
what are the other global weather stations, which hemisphere are they in, are they coastal or not
jacksonville, north, coastal
Beijing, north, inland
Perth, south, coastal
what does n/a mean
not available
what years and months are measured in the large data set
months may to October
years 1987 and 2015
