Sampling in Mixed Methods Research

 

Dr. G. Radhakrishnan

Principal, P.D. Bharatesh College of Nursing, Halaga, Belgaum, Karnataka.

 

INTRODUCTION:

Integration of Qualitative and Quantitative designs is called Mixed- Methods Research or Multi-Method Research (MMR). Although mixed method is not always superior, it has many advantages such as the designs complementing each other, enhanced theoretical insights, incrementality or continuity, enhanced validity, provides for rectification in case of differences/ inconsistencies in result.

 

Sampling is the process of selecting a portion of the population to represent the entire population.

 

Sampling in Mixed Methods Research depends on the Research designs chosen in the study. Green and Caracelli (1997) have identified several types of research designs that involve multi-method approach the designs cluster in to two broad categories that they label component designs and integrated designs.

—  Component designs

◦      Triangulated

◦      Complimentary

◦      Expansion

—  Integrated designs

◦      Iterative

◦      Embedded or Nested

◦      Holistic

◦      Transformative

 

 

Whatever the form of integration may be, the sampling in MMR confines to the basic Quantitative and Qualitative methods.

 

Sampling in quantitative Methods

 

A. Non-Probability sampling

Non-probability sampling is less likely than probability sampling to produce accurate and representative samples.

 

1. Convenience sampling

Convenience sampling entails using the most conveniently available people as study participants. It is also called as an accidental sampling.

 

2. Snowball sampling

It is also called as network sampling or chain sampling. With this approach early sample members are asked to identify and refer other people who meet the eligibility criteria.

 

3. Quota Sampling

A quota sample is one in which the researcher identifies population strata and determines how many participants are needed from each stratum.

 

4. Purposive Sampling

It is also called as judgmental sampling. It is based on the belief that researcher’s knowledge about the population can be used to hand-pick sample members.

 

B. Probability sampling (Random Sampling)

Probability sampling involves the random selection of elements from a population.

 

1. Simple random sampling

It involves the random selection of elements from a sampling frame that enumerates all the elements.

 

2. Stratified random sampling

It divides the population into homogeneous subgroups from which elements were selected at random.

 

3. Cluster sampling

It is also called as multistage sampling. It involves the successive selection of random samples from larger to smaller units by either simple random or stratified random methods.

 

4. Systemic sampling

It is the selection of every k^th case from a list. By dividing the population size by the desired sample size, the researcher establishes the sampling interval, which is the standard distance between the selected elements.

 

Sample size in quantitative research

Quantitative research requires a careful attention to the number of subjects needed to test the research hypothesis. Power analysis and effect size can be used to estimate sample size and reduce sampling errors

 

 

 

The researcher should use the largest sample possible. The larger the sample, the more representative of the population is likely to be. In other words, larger the sample size smaller the sample error.

 

Sampling in qualitative research

Qualitative researchers use the theoretical demands of the study to select articulate and reflective informants with certain types of experience in emergent way.

 

1. Convenience sampling

Qualitative researchers sometimes use or begin with convenience sample which is sometimes referred to in qualitative studies as voluntary sample. Voluntary samples are especially likely to be used when researchers need to have potential participants come forward and identify themselves.

 

2. Snowball Sampling

Qualitative researchers also use snowball sampling, asking early informants to make referral to other study participants.

 

3. Purposive Sampling

Most qualitative studies eventually evolve to a purposive or purposeful sampling strategy that is, hand-picking cases that will most benefit for the study.

 

4. Theoretical Sampling

It is the process of data collection for generating theory whereby the analyst jointly collects, codes, and analyzes his data and decides what data to collect next and where to find them, in order to develop his theory as it emerges.

 

Sample size in qualitative research

There are no criteria or rules for sample size in qualitative research. It depends on the purpose of the enquiry, quality of the informants and the type of sampling strategies used. Eg: Larger the sample when there is maximum variation in the information.

 

The guiding principle is data saturation (is the point where we don’t get additional information).

 

The principles of sample size in Mixed Method Research also remain same as unmixed methods.

 

Sampling in three main qualitative traditions

Sampling in Ethnography

Ethnographers may begin by initially adopting a ‘big net’ approach that is, mingling with and having conversations with as many members of the culture under study as possible.

 

Sampling in Phenomenological studies

Phenomenologists tend to rely on very small samples of participants – typically 10 or fewer.

 

All the participants must have experienced the phenomenon under study and must be able to articulate what is like to have lived that experience.

 

Sampling in Grounded theory

Grounded theory research is typically done with samples of about 20 to 30 people, using theoretical sampling. The goal in a grounded theory study is to select informants who can best contribute to evolving theory.

 

Smaller to Larger sample

—  An in depth qualitative study with few sample may lead to a quantitative study where we may require larger sample.

—   Sampling in this case largely depends on the researcher and the research method adopted

 

Larger to smaller sample

—  A quantitative study undertaken with a larger sample may give an insight for a fruitful qualitative study.

—   In this case the sample for the qualitative study is obtained from the larger sample by either randomized or non-randomized sampling technique methods.

 

Matrix crossing type of sampling scheme by research approach in Multi Method Research - Antony J O, Kathleen MTC (2007)

 

Purposive-Mixed-Probability Sampling Continuum

Charles T and Fen Y (2007) have proposed the following Purposive-Mixed-Probability Sampling Continuum with meaningful combination and explanation for mixed method research,

 

·        Zone A consists of totally qualitative (QUAL) research with purposive sampling.

·        Zone E consists of totally quantitative (QUAN) research with probability sampling.

·        Zone B represents primarily QUAL research, with some QUAN components.

·        Zone D represents primarily QUAN research, with some QUAL components.

·        Zone C represents totally integrated mixed methods (MM) research and sampling.

·        The arrow represents the purposive-mixed-probability sampling continuum. Movement toward the middle of the continuum indicates a greater integration of research methods and sampling.

·        Movement away from the center (and toward either end) indicates that research methods and sampling (QUAN and QUAL) are more separated or distinct. (Source: Teddlie-2005)

 

Mixed Methods Sampling Strategies

Relationship between QUAL and QUANT samples	Description
Identical sampling	The same participants participate in QUAL and QUANT study phases
Parallel sampling	Different samples for QUAL and QUANT study phases but participants drawn from same population
Nested sampling	A subset of the entire sample participate in an additional study
Multilevel sampling	Two or more samples recruited from different levels of the population of interest.

 

Table adapted from Onwuegbuzie and Collins (2007)

Mixed Methods Sampling Issues

Challenges and Issues

·        QUAL: Difficulties of capturing representative samples of qualitative life experiences

·        QUANT: Difficulties of obtaining data from a representative sample Validity and legitimization (dependability and conformability)

·        Ensuring sufficient sample size within the pragmatic constraints of resources (financial, staff, etc)

·        Attrition and/or incomplete information in the different study phases

CONCLUSION:

If Mixed Methods Research is considered to have advantage, a careful of sampling in it adds value to the same.

 

REFERENCES:

1.       Polit DF and Beck CT. Nursing Research: Principles and methods. 7^thed. Philadelphia. Lippincott publications. 2004. p. 289-314.

2.       Antony JO, Kathleen MTC (2007). A Typology of mixed methods sampling designs in Social Science Research. The Qualitative report. 12(2); 2007:281-316.

3.       Angel B and Lisa T. Designing and Conducting Mixed Method Studies. Workshop content. 2011.

4.       Charles T and Fen Y. Mixed methods sampling; A Typology wit examples. Journal of Mixed method Research.1 (1); 2007:77-100. Jacqui Smith. Workshop content on Mixed Methods.2012.

 

 

 

Accepted on 22.03.2014           © A&V Publication all right reserved