quantitative research (Definition, characteristics, research methods & analysis)

Question 1

what is the difference between qualitative and quantitative data?

Answer 1

qualitative;
- words, understanding
- purposive sampling
- social sciences, soft, subjective
- inquiry from the inside
- meaning of behaviours, broad focus
- discovery, gaining knowledge, understanding actions
- practitioner as human instrument to gather data, prescriptive, personal

quantitative;
- numbers, explanation
- statistical sampling
- physical sciences, hard, objective
- inquiry from the outside
- cause and effect relationships
- theory/explanation testing and development
- researcher descriptive, impersonal

Question 2

what does quantitative research involve?

Answer 2

involves a systematic examination of phenomena through testing a hypothesis

development of statistical models to explain observable phenomena

Question 3

what are the common types of statistics

Answer 3

descriptive
comparative
relationship/causal

Question 4

what is descriptive statistics

Answer 4

• wanting to understand a situation, facts
• describe your study participants
• when you want to describe what is going on or what exists

e.g. how many tennis coaches are working in the UK?
what is the most popular sportswear brand amongst uni students in the UK?

what is the average number of goals on a PL football game?

Question 5

what are comparative statistics?

Answer 5

two or more things are compared with the aim of finding something about one or all of them

e.g. is water a better hydration option during long (over 60 mins) sport activities than sports drinks?

Question 6

what is relationship statistics?

Answer 6

• relationships or the causal associations between variables
• understand the nature of and relationships between variables
• most relevant when thinking about interventions

e.g. does plyometric training improve sprint speed in rugby players?

Question 7

what is the research process?

Answer 7

specify -> design -> collect -> visualise -> build -> analyse -> report

Question 8

what is involved in the research process?

Answer 8

specify clearly a question of interest
design a suitable means of gathering data
collect data in unambiguous and organised manner
visualise data in an appropriate form
build a statistical model
analyse data using this model
report data in simple English, the answers and use graphs where appropriate to ease interpretation

Question 9

what are statistics?

Answer 9

science that involves collecting, summarising, analysing and interpreting data

Question 10

what is a statistic?

Answer 10

a single number summarising a variable of interest

mean/sd = descriptive statistics

Question 11

why do we undertake research using statistics?

Answer 11

to test a hypothesis?
are the results real?
do the results matter?

Question 12

what is data?

Answer 12

collection of facts or information

Question 13

what is a variable?

Answer 13

variables of interest:
what is being observed or measured?
a characteristic associated with a group being studied

Question 14

what is an explanatory or independent variable?

Answer 14

what you are manipulating or what you think is associated with outcome

Question 15

what is the response or dependent variable?

Answer 15

outcome variable, what you’re measuring

Question 16

what are the data types?

Answer 16

qualitative (non numerical)
quantitative (numerical)

Question 17

what are the two types of qualitative data?

Answer 17

nominal
ordinal

Question 18

what is categorical (nominal) data?

Answer 18

named categories (non numeric) no order
e.g. favourite running shoe brand, countries

Question 19

what is ordered categorical (ordinal) data?

Answer 19

numbered/named categories
natural order
e.g rate of perceived exertion

Question 20

what are the quantitative data types?

Answer 20

discrete (interval)
continuous (ratio)

Question 21

what is discrete (interval data)?

Answer 21

integer values (whole numbers) does not have to start at zero e.g. time of day

have units

Question 22

what is continuous (ratio) data?

Answer 22

variables can take any value and start at zero e.g. height, BMI, age, crowd size

Question 23

why does data type matter?

Answer 23

the type of variable will dictate what sort of research questions you ask, how you visualise them and statistical analytic method you use.

Question 24

what do hypothesis tests involve?

Answer 24

apply them to experimental data and make statistical decisions using these hypotheses.
precise criteria for rejecting the null hypothesis related to the p value and significance p < 0.05

Question 25

what is the null hypothesis?

Answer 25

default position
no relationship
no difference

Question 26

what is the alternative hypothesis

Answer 26

there is a relationship
there is a difference

Question 27

how do you do a hypothesis test?

Answer 27

use statistical methods and experimental data to make a decision using precise criteria

Question 28

what is an example of a null hypothesis (H0)

Answer 28

there will be no difference in the uptake of smart trainers during the COVID pandemic compared to pre pandemic

Question 29

what is the alternative hypothesis (H1 or Ha)

Answer 29

there will be a difference in the uptake of smart trainers during the COVID pandemic compared to pre pandemic

Question 30

what is a population

Answer 30

total set of observations that can be made

Question 31

what is a sample

Answer 31

a selected subgroup of a population
- simple random
- stratified random
- convenience sample

Question 32

what is a parameter?

Answer 32

• a single number that summarises a variable of interest
  e.g. fastest time on cricket pitch 400m dash Strava segment is 51 seconds
• number 1 ranked athlete is Dan Putman

Question 33

what are the questions for measurement of data concepts?

Answer 33

can you measure it?
how should you measure it?
is there an established definition?

Question 34

how do you measure reliability?

Answer 34

stability (test-retest) - collect data same way on same person with a time difference is it going to be the same?

inter-observer consistency - if two different researcher collect data same way same person are they going to get the same data?

Question 35

what are the types of validity?

Answer 35

internal validity: problems due to manipulation or other causes (variables)? e.g. have people stopped smoking due to your intervention or an external one?

external validity: generalisability to a wider population? comparability with other literature

Question 36

why do we need to sample?

Answer 36

• human variability - sample to cover this variability?
• sample likely to differ from population
• confidence in generalisation
• want to make claims about general population

Question 37

what are the inferences in quantitative research?

Answer 37

population:
- every member of the population has the same chance of being selected in the sample -> take a sample -> random sample -> statistics (might be more than one - mean, sd, t value or f value)
using stats make an estimation and inferences about the population

Question 38

what are inferential statistics?

Answer 38

“allows one to draw conclusions or inferences from data. This means coming to conclusions (such as estimates, generalisations, decisions, or predictions) about a population on the basis of data describing a sample.”

Question 39

what is a population?

Answer 39

distinct group of individuals, from which a statistical sample is drawn for a study. A population is built up of elementary units which cannot be further decomposed.

Question 40

what is a population total?

Answer 40

sum of all the elements in the sample frame

Question 41

what is a population mean?

Answer 41

average of all elements in a sample frame or population (usually only estimated)

Question 42

what is a sample?

Answer 42

a subset of the population

Question 43

what is a sampling frame?

Answer 43

a list of all the units in the population form which teh sample is selected (telephone directory)

Question 44

what is a representative sample?

Answer 44

a sample that accurately reflects the population

Question 45

what is a probability sample?

Answer 45

random selection procedure, each unit has equal chance of selection

Question 46

what is a non-probability sample?

Answer 46

sample not selected using random selection method

Question 47

why and how to sample?

Answer 47

select to reduce bias
select to have enough statistical power to test hypotheses (sample size)
select to be logistically feasible
select to cover all relevant groups adequately (representative)

Question 48

what is a sampling error?

Answer 48

aka random error

the error that occurs when you analyse a sample instead of a population

Question 49

how do we select a sample?

Answer 49

population characteristics must be clearly defined

a poorly defined population or its parameters lead to weak sample data

Question 50

what is the error triangle?

Answer 50

sampling variability
sampling error
non-sampling error - mistakes in data collection unrelated to sampling

Question 51

what is sampling variability?

Answer 51

different samples from the same population do not always produce the same mean and SD e.g. class heights

Question 52

what is a sampling error

Answer 52

the mean of a sample will not be the same as the mean of a population; can be minimised but not eliminated using good selection criteria

Question 53

what is a non-sampling error?

Answer 53

errors not connected with the sampling methods e.g. questions asked in a bad or leading way
measurement error
errors made in coding or recording data

Question 54

what is a random sample?

Answer 54

• everybody in the population has the same chance of being selected
• allocate everybody a number
• random number generator

Question 55

what is stratified random sample?

Answer 55

• if we want to select members of the population with specific characteristics we may want to stratify the sample

take a sample from specific groups in the population

Question 56

how large should samples be?

Answer 56

• populations with greater variability need a larger sample size
• greater precision requires larger sample size but not proportional increase in precision with sample size though
• needs to fit budget and resources