Use a variety of sources to answer the questions, 2) not copy directly out of any book, 3) include sources to responses and cite them at the end of his writing, and 4) provide more details about how you applied his knowledge of research to his independent study.  His goal is to demonstrate through writing his research knowledge and that he applied that knowledge to his independent study.

Question # 5

Validity and generalizability aspects of quantitative, qualitative and mixed methods research:

Quantitative research

Validity and reliability are two important aspects in order to approve and validate the quantitative research. Moskal & Leydens (2002) defined the validity as “the degree to which the evidence supports that the interpretations of the data are correct and the manner in which interpretations used are appropriate”. In other words, Joppe (2000) stated that validity is the one if the obtained results are truthful and believable. He also adds that to determine the validity, the researchers generally poses a series of questions, and will often look for the answers in the research of others to know whether the measurements are accurate or not (p. 1). Joppe (2000) also defined reliability as how consistent the results are when the experiment is repeated a number of times under same methodological conditions, then the instrument is said to be reliable. Kirk and Miller (1986) identified three types of reliability referred to in quantitative research, which relate to: (1) producing the same results under same measurement conditions (2) the stability of a measurement with respect to time; and (3) the similarity of measurements in a given time period (p. 41-42). Charles (1995) argued that reliability is the consistency with which an individual’s scores remain relatively the same and can be determined through the test-retest method at two different times. HE refers to this type of instrument as stable instrument. He also stated that a high degree of stability indicates a high degree of reliability, which means the results are repeatable.

According to Creswell (2003) there are several threats of validity that proves or raises issues about the accuracy of the data or results or application of statistical tests to conclude the effects of an outcome. They are internal threats, external threats, statistical conclusion threats, and construct validity threats. Campbell and Stanley (1963) states that the basic requirement to interpret an experiment is to clearly define internal validity. Internal validity threats are experimental procedures, treatments, or experiences of the participants that threaten the researcher’s ability to draw correct inferences from the data in an experiment. These are raised due to usage of inadequate procedures like changing the instrument or a tool during an experiment, changing the control group participants under study etc. Because of these inadequate procedures, the experimenter should find whether the experiment make a difference in this instance or not.

External validity threats arise when the researcher concludes incorrect inferences from the sample data to other persons. It addresses the question of generalizability that to whom can we generalize the obtained results. A statistical conclusion validity threat arises when experimenters draw inaccurate inferences from the data because of the violation of the assumptions of the statistical test being used for the collected data. Construct validity threat arises when investigators use inadequate definitions and measure variables based on those inadequate definitions.

In general, methods of establishing validity in quantitative research are:

• Experiment review

• Data triangulation

• Participant feedback

• Regression analysis

• Statistical analysis

In my study, I clearly defined and took care of the internal validity threats that can arise from the data collected and the tools used for collecting the data. In order to avoid this threat in Microsoft Excel, as the random data generated keeps on changing, I copied the data on multiple sheets so as to make sure the data was not lost for further analysis. I took care of the external validity by inferring the data to their respective parts, products and machines correctly and obtained results after performing a careful analysis. I applied descriptive statistics analysis and drew line graphs between the numbers of products, delay time and interpreted the results clearly.

Qualitative research

Golafshani (2003) argues that the concepts of validity and reliability related to the quantitative research may not be applicable or support for qualitative research. Winter (2000) points out that the necessary tools such as precision; credibility and transferability are considered to validate the qualitative research. Transferability refers to the extent in which the obtained results can be used by other researchers. Credibility is nothing but the data, data collection and the results obtained are trustworthy and believable. All the technical issues such as validity, reliability, triangulation and generalizability show the effect of credibility. In terms of the quantitative research, reliability means, the result is replicable. But, in terms of the qualitative research, reliability is testing the information for high quality which otherwise looks confusing making the reader change the track of the study. Stenbacka (2001) relates that in the quantitative study, quality or reliability refers to evaluating the purpose of explaining, while in qualitative study, it serves the purpose of generating understanding of the information. Creswell & Miller (2000) stated that the strength of the qualitative study depends on the accuracy of the findings in view of the researcher, participant or the readers. Moskal & Leydens (2002) defined the validity as “the degree to which the interpretations of the data accurately describe the phenomenon under investigation”. I qualitative research, internal validity refers to the match between the researchers observations, interpretations, categories and reality. In addition to validity, Moskal & Olds (2002) used trustworthiness as an alternate method to validate the study which states that the made interpretations are accurate. Patton (2001) states that validity and reliability are two factors qualitative researchers should be aware of in designing, analyzing, interpreting, and judging the quality of study. According to Seale (1999), to ensure reliability in qualitative research, the research needs to examine the trustworthiness. He adds that trustworthiness of the research report becomes important if the validity and reliability of the study is discussed.

Testing or maximizing the validity of the qualitative research: Stenbacka (2003) suggested that the structure of documenting and doing a high quality research work leads to a generalizability if the validity and trustworthiness are maximized. To do this, a data triangulation method has to be implemented to control bias and to establish valid propositions. Creswell & Miller (2000) defined data triangulation as the formation of themes or categories using a validity procedure for convergence among multiple and different sources of information. It involves comparison of results obtained from different data methods such as surveys, interviews, observations etc.

So, to establish multiple ways of truth for a qualitative research, researcher needs to redefine, implement and test the validity, reliability, generalizability and data triangulation concepts thoroughly.

Methods for establishing the validity and to enhance the credibility of qualitative research are:

• Negative case analysis – Presenting the negative information that runs counter to the themes

• Audit trail – Clarifying the bias that the researcher brings to the study

• Prolonged field experience – Spending prolonged time in the field to develop an in-depth understanding of the phenomenon under study

• Data triangulation – triangulate different data sources of information by examining evidence from the sources and using it to build a coherent justification

• Member checking – to determine the accuracy of the qualitative findings

Mixed methods research: