TOPIC 3 THE Quantitative-Research V2.pdf

PRESENTATION RESEARCH

1. Quantitative
Research

2. Overview of Quantitative
Research: Definition
❑is a formal, objective, systematic process in which numerical data are
utilized to obtain information about the world
❑the systematic empirical investigation of observable phenomena via
statistical, mathematicaland computational techniques

3. Overview of Quantitative
Research: Definition
❑used to examine the relationship between variables with the primary goal
being to analyze and represent that relationship mathematically through
statistical analysis
❑the type of research approach most commonly used in scientific research
problems (natural sciences, social sciences, etc.)

4. Overview of Quantitative
Research
Quantitativeresearchisgenerallymadeusingscientific
methods,whichcaninclude:
❑thegenerationofmodels,theoriesandhypotheses
❑thedevelopmentofinstrumentsandmethodsfor
measurement
❑experimentalcontrolandmanipulationofvariables
❑collectionofempiricaldata
❑modelling and analysis of data

5. Characteristics of Quantitative
Research
1. The data collected is numeric,
allowing for collection of data
from a large sample size.

6. Characteristics of Quantitative
Research
2. Statistical analysis allows
for greater objectivity when
reviewing results and
therefore, results are
independent of the
researcher

7. Characteristics of Quantitative
Research
3. Numerical results can be
displayed in graphs, charts, tables
and other formats that allow for
better interpretation.

8. Characteristics of Quantitative
Research
4. Data analysis is less time-consuming and can often be done using
statistical software.

9. Characteristics of Quantitative
Research
5. Results can be generalized if the data are based on random
samples and the sample size was sufficient.

10. Characteristics of Quantitative
Research
6. Data collection methods can be relatively quick, depending on the type
of data being collected.
7. Numerical quantitative data may be viewed as more credible and
reliable, especially to policy makers, decision makers, and administrators.

11. Quantitative Research
Examplesofresearchquestionswherequantitativemethodsmaybe
appropriatelyapplied:
▪How often do college students between the ages of 20-24 access Facebook?
▪What is the difference in the number of calories consumed between male
and female high school students?
▪What percentage of married couples seek couples counseling?
▪What are the top 5 factors that influence a student’s choice of college or
university?
▪How many organized sports activities has the average 10 year old child
competed in?

12. When to Use Quantitative
Methods
Researchers should begin by asking
themselves the following questions:
➢What type of question am I asking?
➢What type of data will I need to
collect to answer the question?
➢What type of results will I report?

13. When to Use Quantitative
Methods

14. Key Issues in Quantitative
Research
Validity ReliabilityReplicability
GeneralizabilityFalsifiability

15. 1. Validity
◦refers to thestrength of the
conclusionsthat are drawn from
the results
◦How accurateare the results?
◦Do the results actually measure
what was intended to be
measured?
Key Issues in Quantitative
Research

18. ▪Conclusionvalidity-degreetowhichtheconclusioniscredibleorbelievable
▪Internal validity -extent to which the independent variable can accurately be stated to
produce the observed effect
▪Construct validity -degree to which a test of measurement accurately assess the theoretical
construct it intends to measure or it is an attempt to generalize the treatment and outcomes
to a broader concept.
▪External validity -ability to generalize the results to another setting.It examines whether the
findings of a study can be generalized to other contexts
▪Criterion-related validity (also called instrumental validity) is a measure of the quality of your
measurement methods. The accuracy of a measure is demonstrated by comparing it with a
measure that is already known to be valid
Key Issues in Quantitative
Research

19. Key Issues in Quantitative
Research
1. Validity
2. Reliability
❑consistencyofthemeasurements-towhatlevelwillthe
instrumentproducethesameresultsunderthesameconditions
everytimeitisused?
❑whether research methods can reproduce the same results
multiple times.
❑If your research methods can produce consistent results, then
the methods are likely reliable and not influenced by external
factors

23. RELIABILITY
❑Internal reliabilityrefers to how consistently different items within
a single test measure the same concept or construct. It ensures
that a test is stable across its components.
❑External reliabilitymeasures how consistently a test produces
similar results over repeated administrations or under different
conditions. It ensures that a test is stable over time and situations.

28. Key Issues in Quantitative
Research
Falsifiability/Testability
❑means that any for any hypothesis to have
credence, it must be possible to test whether that
hypothesis may be incorrect
❑A researcher should test his/her own hypothesis
to prove or disprove it before releasing results to
prevent another researcher from proving it wrong.
❑If a theory or hypothesis cannot be tested in
such a way that may disprove it, it will likely not be
considered scientific or valuable to those in the
field.

29. Key Issues in Quantitative
Research
Generalizability
❑refers to whether or not the research findings and
conclusions that result from the study are generalizable to
the larger population or other similar situations.
❑The ability to generalize results allows researchers to
interpret and apply findings in a broader context, making
the finding relevant and meaningful.

30. Key Issues in Quantitative
Research
Replicability
the reproducibility of the study
◦Will the methodology produce the same results when
used by different researchers studying similar subjects?
it ensures the validity and reliability of the results and
allows the results to be generalized

32. Quantitative
Approaches

33. DESCRIPTIVE DESIGN
❑Descriptiveresearchdesignisatypeofresearchdesignthataimsto
systematicallyobtaininformationtodescribeaphenomenon,situation,or
population.
❑describingthecharacteristicsofthepopulationorphenomenonstudied.
❑Thisdescriptivemethodologyfocusesmoreonthe“what”oftheresearch
subjectthanthe“why”oftheresearchsubject.

34. CORRELATIONAL DESIGN
❑investigatesrelationshipsbetweenvariableswithoutthe
researchercontrollingormanipulatinganyofthem
❑Acorrelationreflectsthestrengthand/ordirectionofthe
relationshipbetweentwo(ormore)variables
❑Testofrelationship

35. QUASI-EXPERIMENTAL
DESIGN
❑Quasi-experimentalmethodsareresearchdesignsthatthataim
toidentifytheimpactofaparticularintervention,program,or
event(a"treatment")bycomparingtreatedunits(households,
groups,villages,schools,firms,etc.)tocontrolunits.
❑Whilequasi-experimentalmethodsuseacontrolgroup,they
differfromexperimentalmethodsinthattheydonot
userandomizationtoselectthecontrolgroup.

36. EXPERIMENTAL DESIGN
❑trueexperimentation,usethescientificmethodtoestablishcause-effect
relationshipamongagroupofvariablesinaresearchstudy
❑Researchersmakeanefforttocontrolforallvariablesexcepttheonebeing
manipulated(theindependentvariable)
❑Theeffectsoftheindependentvariableonthedependentvariableare
collectedandanalyzedforarelationship

38. Quantitative Scales of
Measurement
Quantitative research requires that measurements be
both accurateand reliable.
Researchers commonly assign numbers or values to
the attributes of people, objects, events, perceptions,
or concepts.
This process is referred to as measurement.

39. ❑referstothevariousmeasuresusedinquantifyingthevariables
researchersuseInperformingdataanalysis.
❑Theyareanimportantaspectofresearchandstatisticsbecause
thelevelofdatameasurementiswhatdeterminesthedata
analysistechniquetobeused
❑prerequisitetoworkingwithdataandperformingstatistical
analysis
SCALES OF MEASUREMENT

40. Characteristics: Measurement Scale
IDENTITY(DESCRIPTION)
❑theassignmentofnumberstothevaluesofeachvariableina
dataset
❑MaleandFemaleforinstance.Thevalues1and2canbe
assignedtoMaleandFemalesrespectively
❑Nominalscale

41. MAGNITUDE (ORDER)
❑the size of a measurement scale, where numbers (the identity) have an
inherent order from least to highest.
❑They are usually represented on the scale in ascending or descending order.
The position in a race, for example, is arranged from the 1st, 2nd, 3rd to the
least.
❑This example is measured on an ordinal scale because it has both identity
and magnitude
Characteristics of a Measurement
Scale

42. EQUAL INTERVALS (DISTANCE)
❑thescalethathasastandardizedorder.I.e.,thedifference
betweeneachlevelonthescaleisthesame
❑Avariablethathasanidentity,magnitude,andequalintervalis
measuredonanintervalscale.
Characteristics of a Measurement
Scale

43. ABSOLUTE ZERO (ORIGIN)
❑definedasthefeaturethatisuniquetoaratioscale.
❑Itmeansthatthereisanexistenceofzeroonthescale,andis
definedbytheabsenceofthevariablebeingmeasured
Characteristics of a Measurement
Scale

44. Primary Scales of Measurement
1. Nominal Scale
❑used for identification purposes
❑categoricalscale,itassignsnumberstoattributesforeasyidentity.These
numbersarehowevernotqualitativeinnatureandonlyactaslabels.
❑Theonlystatisticalanalysisthatcanbeperformedonanominalscaleis
thepercentageorfrequencycount.Itcanbeanalyzedgraphicallyusinga
barchartandpiechart.
❑1Male,2Female/1Single2Married3Widow

45. 2. Ordinal Scale
❑rankingororderingoftheattributesdependingonthevariablebeingscaled
❑arrangedinascendingordescendingorder.Itmeasuresthedegreeof
occurrenceofthevariable
❑Satisfactiondatapoints1=happy,2=neutral,and3=unhappy.’
❑1Excellent,2Verygood,3Good,4Bad,5Poor
Primary Scales of Measurement

46. 3. Interval Scale
❑Theintervalscalecontainspropertiesofnominalandordereddata,butthe
differencebetweendatapointscanbequantified.
❑Thistypeofdatashowsboththeorderofthevariablesandtheexact
differencesbetweenthevariables.
❑AcommonexampleismeasuringtemperatureontheFahrenheitscale.Itcan
beusedincalculatingmean,median,mode,range,andstandarddeviation.
Primary Scales of Measurement

48. 4. Ratio Scale
❑Satisfiesthefourcharacteristicsofthemeasurementscale;identity,
magnitude,equalinterval,andtheabsolutezeroproperty
❑compareboththedifferencesandtherelativemagnitudeofnumbers.
❑Weight,height,timeanddistanceareallexamplesofratiovariables.
❑Dataintheratioscalecanbeadded,subtracted,dividedandmultiplied.
Primary Scales of Measurement

49. Primary scales of measurement

50. Primary Scales of Measurement

51. SCALING TECHNIQUES

52. Comparative Scales
❑Incomparativescaling,respondentsareaskedtomakea
comparisonbetweenoneobjectandtheother.
❑Examplemarketresearch,customersareaskedtoevaluateone
productindirectcomparisontotheothers.
❑Comparativescalescanbefurtherdividedintopaircomparison,
rankorder,constantsum,andq-sortscales.

53. Comparative Scales
❑PairedComparisonscaleisascalingtechniquethatpresentsthe
respondentswithtwoobjectsatatimeandasksthemtochoose
oneaccordingtoapredefinedcriterion
❑Rankorderscalingtechnique,respondentsaresimultaneously
providedwithmultipleoptionsandaskedtoranktheminorderof
prioritybasedonapredefinedcriterion.Itismostlyusedin
marketingtomeasurepreferenceforabrand,product,orfeature.

58. Comparative Scales
❑ConstantSumscaleisatypeofmeasurementscalewherethe
respondentsareaskedtoallocateaconstantsumofunitssuchas
points,pesoorchipsamongthestimulusobjectsaccordingtosome
specifiedcriterion
❑Q-Sortscaleisatypeofmeasurementscalethatusesarankorder
scalingtechniquetosortsimilarobjectswithrespecttosome
criterion.Therespondentssortthenumberofstatementsor
attitudesintopiles

60. Non-Comparative Scales

61. ❑ContinuousRatingScaleratetheobjectsbyplacingamark
appropriatelyonalinerunningfromoneextremeofthecriterion
totheothervariablecriterion.
❑Alsocalledthegraphicratingscale,itgivestherespondentthe
freedomtoplacethemarkanywherebasedonpersonal
preference.
Non-Comparative Scales

63. ❑Itemized Rating Scale

Non-Comparative Scales

64. Itemized Rating Scale
Likertscale:Thisisanordinalscalewithfiveresponsecategories,whichisusedtoorder
alistofattributesfromthebesttotheleast.Thisscaleusesadverbsofdegreelikevery
strongly,highly,etc.toindicatethedifferentlevels.
StapelScale:Thisascalewith10categories,usuallyrangingfrom-5to5withnozero
point.Itisaverticalscalewith3columns,wheretheattributesareplacedinthemiddle
andtheleast(-5)andhighest(5)isinthe1stand3rdcolumnsrespectively
SemanticDifferentialScale:Thisisaseven-pointratingscalewithendpointsassociated
withbipolarlabels(e.g.goodorbad,happy,etc.).Itcanbeusedformarketing,
advertisingandindifferentstagesofproductdevelopment.

71. Quantitative Data
❑data that can be counted or expressed numerically
❑It is commonly used to ask “how much” or “how many” and can
be used to study events or levels of occurrence.
❑Because it is numerical in nature, quantitative data is both
definitive and objective
❑statistical analysis and mathematical computations and therefore,
is typically illustrated in charts or graphs.

72. Discretedata-wholenumbersthatcan’tbedividedorbroken
intoindividualparts,fractionsordecimals;describedashaving
afinitenumberofpossiblevalues
Continuousdataarevaluesthatcanbebrokendowninto
differentparts,units,fractionsanddecimals;usuallyaphysical
measurement.
2 Main Types

73. Quantitative Data

75. DATA COLLECTION
❑systematicprocessofgatheringobservationsor
measurements
▪Theaimof the research
▪Thetype of datathat will be collected
▪Themethodsand proceduresto be used, stored, and
processed the data

76. Methods of Data Collection
❑Experiments and clinical trials
❑Surveys, interviews and questionnaires
❑Observing or recording well-defined events
❑Obtaining information from a management
information system.

77. Sampling
▪Process of selecting a sampleor portion of a larger group of
potential participants in order to generalize statements about a
broader group or population
▪In general, sample size (n) is chosen in order to reproduce some
characteristics of the whole population (N).
▪Sound sampling method will result to a bias free and reliable
results (representative of the population of interest)

78. Sampling Process
Theoretical or
Target Population
Source: Salkind(2010)
Accessible
Population
or
Sampling Frame
Select
Sample
Actual
Sample

79. SAMPLE
▪Subset of a population
▪specific group of individuals that you will collect data
from
▪sample size depends on the size andvariabilityof the
populationand research design
POPULATION
▪Group from which a sample is drawn
▪Exact population will depend on the scope of the study
▪The entire group that you want to draw conclusions
about
SAMPLING FRAME
▪the actual list of individuals that the sample will be
drawn from

80. Collecting data from a population
❑Populationsareusedwhenyourresearchquestionrequires,orwhenyou
haveaccessto,datafromeverymemberofthepopulation.
❑Usually,itisonlystraightforwardtocollectdatafromawholepopulation
whenitissmall,accessibleandcooperative
Collecting data from a sample
❑Whenyourpopulationislargeinsize,geographicallydispersed,ordifficult
tocontact,it’snecessarytouseasample.
❑Withstatisticalanalysis,youcanusesampledatatomakeestimatesor
testhypothesesaboutpopulationdata

81. REASONS FOR SAMPLING
❑Necessity:Sometimesit’ssimplynotpossibletostudythe
wholepopulationduetoitssizeorinaccessibility
❑Practicality:It’seasierandmoreefficienttocollectdatafroma
sample
❑Cost-effectiveness:Therearefewerparticipant,laboratory,
equipment,andresearchercostsinvolved
❑Manageability:Storingandrunningstatisticalanalyseson
smallerdatasetsiseasierandreliable.

82. METHODS of SAMPLING
1.Probability Sampling
2.Non-probability Sampling

83. PROBABILITY SAMPLING
Use randomizationto generate
representative samples from the
target population
Randomization increases the likely
hood of getting representative
samples
Image source: https://www.gamesworld.com.au/product/dice-single/

84. Sampling Procedures

85. Probability Sampling
1.Simple Random Sampling
▪Simplest form of probability sampling
▪Sample size (n) is taken from every possible subset of n in the
population
▪every member of the population has an equal chance of being
selected
▪Provides foundation for other complicated sampling schemes
▪Sampling frame should include the whole population

86. Simple Random Sampling

87. Probability Sampling
2.Stratified Random Sampling
◦Target population is divided into strata
◦Split population into strata and then randomly select from
each of these subgroups
◦Strata could be a sub-group of interest, attributesor
characteristics(e.g. region, age group, grade level)
◦Stratificationoften increase precision

88. Stratified Random Sampling
Stratum 1 Stratum 2 Stratum 3
Stratum 4 Stratum 5 Stratum 5

89. Simple vs Stratified Sampling
❑representtheentiredatapopulation.
❑treatsallmembersofapopulationas
equal,withanequallikelihoodof
beingsampled
❑usedwhenthereisverylittle
informationavailableaboutthedata
population,datapopulationhasfar
toomanydifferencestodivideinto
varioussubsets,orwhenthereisonly
onedistinctcharacteristicamongthe
datapopulation.
❑dividesthepopulationinto
smallergroups,orstrata,basedon
sharedcharacteristics.
❑highlightthedifferencesamong
groupsinapopulation
❑more complicated,time
consuming,andpotentiallymore
expensivetocarryout

90. Probability Sampling
3.Cluster Sampling
◦divide the sample into clusters that approximately
reflect the whole population, and then choose
sample from a random selection of these clusters
◦A cluster is similar to a stratum, clusters, such as
districts, schools, municipality
◦Clustering decreases precision

91. divide into clusters based on age, gender, location, etc., and then selects
customer a random sample from each cluster for further analysis

92. Cluster Sampling
Cluster 1 Cluster 2 Cluster 3
Cluster 4 Cluster 5 Cluster 5

93. Probability Sampling
4.Systematic Sampling
◦Proxy for simple random sampling when list of
population is non existent.
◦Choosing sample based on a regular interval
◦From the starting starting point, samples are taken
every kth unit after resulting to equally space
sampling unit within the list

94. Systematic Sampling
select members of the population
at a regular interval–for example,
by selecting every 5th person on a
list of the population

95. Nonprobability Sampling
1.Convenience
2.Quota
3.Snowball
4.Purposive

96. Nonprobability Sampling
1. Convenience
❑includes the individuals who happen to be most
accessible to the researcher
❑Reasons due to geographical proximity, availability at a
given time, or willingness to participate in the research
❑Haphazard or accidental sampling

97. Choose who or what is available during the survey or study

98. Nonprobability Sampling
2. Quota
◦Similar to stratified random sampling but with no randomization
◦Relies on the non-random selection of a predetermined (quota)
number of samples
◦Divide the population into mutually exclusive subgroups (called
strata) and then recruit sample units until you reach your quota
◦Judgmental sampling

99. enlists study participants until a relevant research category (or quota) has
recruited enough respondents to reach holistic conclusions

100. Nonprobability Sampling
3.Snowball
▪Used to collect data from people who are for reason hard
to identify
▪existing subjects provide referrals to
recruit samplesrequired for a research study
▪purely based on referrals and that is how a researcher is
able to generate a sample.
▪Therefore this method is also called the chain-referralor
network sampling method

102. 4.Purposive (Purposeful Sampling)
❑Selecting samples from the overall sample size based on the
judgment of the survey taker or researcher
❑Samples are identified base certain criteria/requirements the
study demands
❑Set out to identify members of the population who are likely to
possess certain characteristics or experiences
❑Select the individuals or cases that fit your study, focusing on a
relatively small sample
Nonprobability Sampling

104. THE END