US E OF MIXED METHOD E OF MIXED METHOD S S US
US E OF MIXED METHOD E OF MIXED METHOD S S
How
How to choose an approach or methodto choose an approach or method
D
Depepenends ds on on ththe e rereseseararch ch ququesestitionons s anand d ththe e rereseseararch ch skskilill l of of ththee researcher.
researcher.
Appro
Appropriateness priateness of of MMethodethod
Some methods are better suited to a study of certain research questions than Some methods are better suited to a study of certain research questions than others. Some might even be totally inappropriate to your r
others. Some might even be totally inappropriate to your research question.esearch question.
So type of research methodology depends on:
So type of research methodology depends on:
Research Questions/problem
Research Questions/problem
V
Variables ± ariables ± qualitative or qualitative or quantitativequantitative
T
Type of data ± ype of data ± nominal, ordinal, interval or nominal, ordinal, interval or ratioratio 1.
1. N N ominal-scaled dataominal-scaled data T
These are mainly qualitative and assigned to hese are mainly qualitative and assigned to a number of categories of equal a number of categories of equal importance,importance, for example, gender [male, female].
for example, gender [male, female].
2
2. . OOrrddiinnaall--ssccaalleed d ddaattaa
Ordinal-scaled data are mainly qualitative and assigned to coded categories. Ranking is Ordinal-scaled data are mainly qualitative and assigned to coded categories. Ranking is implied between categories, for example, Class [1
implied between categories, for example, Class [1ststyears, 2years, 2ndnd years, 3years, 3rdrd years, Honours].years, Honours].
3.
3. Interval-scaled dataInterval-scaled data T
These are quantitative; they possess both order and distance but no origin, for example,hese are quantitative; they possess both order and distance but no origin, for example, IQ scores and temperature (say, in degrees Centigrade).
IQ scores and temperature (say, in degrees Centigrade).
4.
4. Ratio-scaled dataRatio-scaled data
Ratio-scaled data are quantitative wit
Ratio-scaled data are quantitative with a zero h a zero origin, for example, age, height and weight.origin, for example, age, height and weight.
T
They possehey possess ss all all the propethe propertirties es of of the othethe other r datdata a tytypespes. . ³Ra³Ratiotio´ ´ is is regregardarded ed as as thethe strongest level of data and
strongest level of data and ³nominal´ the weake³nominal´ the weakest.st.
Whe
When n ththe e phphenoenomenmenon on beibeing ng invinvesestitigatgated ed is is nonot t welwell l undundererststooood, d, aa qualitative research can be used first to generate preliminary hypotheses, qualitative research can be used first to generate preliminary hypotheses, and then quantitative research is used
and then quantitative research is used to test specific hypotheses.to test specific hypotheses.
Fo
For r cocomprmprehehenensisive ve ststudiudies, es, it it is is bebetttter er to to ususe e botboth h appapproroacachehes s (i.(i.e.e.
qualita
qualitative and quantitive and quantitative), tative), a situatia situation where, the quanon where, the quantitativtitative methode method helps to test hypotheses and to make the study more objective and the helps to test hypotheses and to make the study more objective and the qualitative method helps to give a complete understanding or in-depth qualitative method helps to give a complete understanding or in-depth information on the phenomenon being studied ± in all its dimensions.
information on the phenomenon being studied ± in all its dimensions.
Complex studies, having many different research questions may use
Complex studies, having many different research questions may use both approaches to answer particular questions or to address particular both approaches to answer particular questions or to address particular research problems.
research problems.
E.g., poverty is multidimensional in nature, i.e., it has social, political and
E.g., poverty is multidimensional in nature, i.e., it has social, political and economic dimensi
economic dimensions. So, a ons. So, a poverty study may need both apoverty study may need both approacpproaches tohes to be studied ±
be studied ± a situation where the qualitative reseaa situation where the qualitative research methods are usedrch methods are used to investigate the social and political issues and help the voice of the poor to investigate the social and political issues and help the voice of the poor to be heard and quantitative methods are used to study the economic to be heard and quantitative methods are used to study the economic issues.
issues.
According to Lee (1999), within a single study multiple qualitative and According to Lee (1999), within a single study multiple qualitative and
qua
quantintitattative ive tectechniqhniques ues that that invoinvolve lve compcomplemelementantary ry datdata-ga-gatheatheringring act
activivititieies s can can be be appapplilied ed ththat at cocompempensnsatate e for for ththe e weweaknaknessesses es of of individual tactics.
individual tactics.
The data becomes more comprehensive and quite informative.
The data becomes more comprehensive and quite informative.
E.
E.g. g. The The fafactctorors s afaffecfectiting ng an an ororgaganiznizatiationaonal l phephenomenomenonon n can can bebe quantitatively investigated ± using a field experiment and regression quantitatively investigated ± using a field experiment and regression analysis and qualitative techniques used to inform about additional, analysis and qualitative techniques used to inform about additional, little known variables, processes and conditions that might surround little known variables, processes and conditions that might surround the effects investi
the effects investigated by the quantitative gated by the quantitative techniques.techniques.
Normally a semi-structured questionnaire is used to include bothNormally a semi-structured questionnaire is used to include both closed and open-ended questions.
closed and open-ended questions.
Note:
Note:
Social experiences and the realities of the world are multidimensional and Social experiences and the realities of the world are multidimensional and so if phenomena are viewed only along a single dimension we cannot have a so if phenomena are viewed only along a single dimension we cannot have a complete picture of what is going on around us
complete picture of what is going on around us..
Qu dimensions and scales of social existence are related.
dimensions and scales of social existence are related.
TThe particular strength of qualitative research lies in the knowledge providedhe particular strength of qualitative research lies in the knowledge provided regarding the dynamics of social processes, change and social context, and in its regarding the dynamics of social processes, change and social context, and in its ability to answer µhow¶ and µwhy¶ question
ability to answer µhow¶ and µwhy¶ questions in s in those domains.those domains.
TThere are two core elements to the logic of qualitative explanation: one relateshere are two core elements to the logic of qualitative explanation: one relates to a qualitative logic of comparison, e.g., between cases, situations, contexts, to a qualitative logic of comparison, e.g., between cases, situations, contexts, over time, etc and the second
over time, etc and the second relates to the significance of context.relates to the significance of context.
Un
T
This entails the use of contextual explanation, where emphasis is on his entails the use of contextual explanation, where emphasis is on explainingexplaining ho
how w difdiffefererent nt dimdimenensisionons s of of cocontntexext t totogegethther er lilink nk up up totogegethther er wiwith th ththee processes or
processes or questions driving the questions driving the studystudy..
Using mixed methods to µtriangulate¶ or to corroborate each other suggests an Using mixed methods to µtriangulate¶ or to corroborate each other suggests an integrated fram
integrated framework, where each method and form oework, where each method and form of data is used to highlightf data is used to highlight a specific part of the picture.
a specific part of the picture.
T
There might however be tensions arising from differences in approaches tohere might however be tensions arising from differences in approaches to data collection because of using
data collection because of using differendifferent t sets of assumptions.sets of assumptions.
T
To overcome any such potential difficulty the solution is in how explanationso overcome any such potential difficulty the solution is in how explanations are done.
are done.
Explanations do not have to be internally consistent to have a meaning and Explanations do not have to be internally consistent to have a meaning and capacity to explain.
capacity to explain.
If indeed the realities of the world are multidimensional ± political, social, If indeed the realities of the world are multidimensional ± political, social, cu
cultltururalal, , ececononomomicic, , etetc, c, thethen n exexplplananatiationons s ararisisining g frfrom om mmixixed ed datdata- a-collection methods would be likewise
collection methods would be likewise (see Cho and(see Cho and TTrent, 2006; Dixon-rent, 2006; Dixon-W
Woods, et. al. 20oods, et. al. 2006, Moran-Ellis, 2006; Mason, 20006, Moran-Ellis, 2006; Mason, 2006 in Kimani, 206 in Kimani, 2009).09).
Remember:
Remember:
Using a quantitative research design is an excellent way of finalizing
Using a quantitative research design is an excellent way of finalizing results and proving or disproving
results and proving or disproving a hypothesis, anda hypothesis, and
Scientific experiments are useful for testing the data gained by a series
Scientific experiments are useful for testing the data gained by a series of qualitative experiments, leading to a final answer, and a narrowing of qualitative experiments, leading to a final answer, and a narrowing down of possible directions for follow up research to take.
down of possible directions for follow up research to take.