Measurements and Instruments for a Quantitative - Research Paper Example

? Measurements and Instruments for a Quantitative Research Plan Grade (3rd, April. Measurements and Instruments for a Quantitative Research Plan Quantitative Research refers to the investigation and measurement of social phenomena, through the use of computational, statistical and mathematical techniques (Black, 1999). While selecting the suitable instruments for undertaking a Quantitative Research, various aspects should be put into consideration. The practical application of the instruments to the study phenomena should be the fundamental consideration, which serves to assess whether the instrument selected for use is practically applicable to the nature of the study and the objectives that are to be met. The second aspect that needs to be considered, while undertaking a Quantitative Research, is the reliability of the instruments selected for use. This aspect deals with the consistency of the instruments applied, to investigate whether such instruments fully measure what they are supposed to measure (Creswell, 2009). Validity is yet another vital consideration that should be made while selecting the appropriate instruments to be applied in a Quantitative Research. Validity refers to the degree and extent to which, the instrument applied performs as expected. The concept of full validity is rarely achievable, necessitating its measure, in terms of percentage that the instrument measures to the expectation (Black, 1999). Therefore, to incorporate all the three aspects of practicality, reliability and validity in assessing the suitability of the instruments applicable in a Quantitative Research, there is a need to select a research instrument that is comprehensive, and that covers the entire population characteristics. Suitable measurement and instrument for the Quantitative Research Plan In consideration of the above requirements for a suitable instrument for Quantitative research, a Cross-Sectional Study has been selected as the most suitable instrument for the study. A Cross-Sectional Study refers to a research method that is applied to observe the whole population and its various characteristics, or at least a sub-set of the population, as opposed to merely selecting a small sample of the population to be representative of the whole (Babbie, 2011). Strengths and limitations of the measurement instrument This instrument of measurement is suitable for application in a Quantitative Research, since it helps to investigate a certain social phenomenon in the whole population, or a combination of several phenomena and characteristics that are exhibited by the population. The greatest advantage of the applying this instrument of measurement is that it ensures that the whole population is covered, and that different characteristics exhibited by the population are put into consideration (Babbie, 2011). The reliability and validity of any study, is highly dependent on the percentage of the population that the study has put into consideration, to arrive at certain conclusions. The greater percentage of the population is covered, the higher are the reliability and validity of the study. Therefore, considering that a Cross-Sectional Study covers the whole population, or at least a subset of the population, it stands higher chances of being reliable and valid, as an instrument of measure for use in Quantitative Research. This informs why a Cross-Sectional Study was selected as the suitable instrument for this study. However, the limitation of Cross-Sectional Study as an instrument of measure used in Quantitative Research is that it requires much time, resources and management, since it is destined to cover the entire population, or at least a sizeable sub-set of the population (Babbie, 2011). Additionally, considering that it can be applied to measure several attitudes and characteristics of social phenomenon, it is associated with a high degree of generalization. Scale that is appropriate for use in Quantitative Research Plan Likert scale serves as the most suitable scale applicable in this study. It refers to a scale that is applied in research, which utilizes the questionnaire as the research tool (Bowling, 1997). It is a system of classifying the responses obtained from respondents, based on a range of score that they capture. A Likert scale can entail the classification of the attitudes of individuals towards a certain social phenomenon, where the individuals are required to give their attitude based on how they agree with the phenomenon. The scores applied in a Likert scale can be established in the range of disagreeing to strong agreement, with each response being allocated a numerical score, which is then summed up, to indicate the feeling of the entire participants, regarding the social phenomenon in question (Likert, 1932). The reason for selecting the Likert scale, as the suitable scale for this study, is the consideration that Likert scale gives more information regarding the attitude and characteristics of individuals, relating to a certain social phenomenon, as opposed to merely getting neutral responses, which may not reflect the true attitude or other perceived characteristic of the individual (Burns & Grove, 1997). The other advantage that accounts for the selection of the Likert scale as the most appropriate scale for the study is the fact that Likert scale eliminates the unnecessary generalization of answers and responses that are given by respondents in a research study. Answers given by respondents could be very general and ambiguous, thus making it difficult for the researcher to interpret the true meaning of the responses. However, the application of the Likert scale guards against this occurrence, through ensuring that the answer given by respondents reflects their true will and meaning. Therefore, the application of a Likert scale precludes any chances of misconceptions (Frankfort-Nachmias & Nachmias, 2008). Content validity, empirical validity and construct validity for the study There are various concepts of validity that should be assessed under the Likert scale, to determine whether the scale is actually valid for this type of study. The first type of the validity test is the empirical validity, which seeks to assess how well the scores that are obtained on a test correlate with the behavior that is being measured (Campbell, 1957). This serves to indicate whether the test clearly relate with the desired characteristics, attitudes and phenomena that are to be established by the study. For example, an empirical validity can be tested through assessing how well the aptitude scores of a job interviewee match with his/her academic records. If the interviewee scores highly in the aptitude test, and still has good grades in his/her academic records, then the scores in the aptitude tests have passed the empirical validity test (Creswell, 2009). Therefore, the empirical validity of the Likert scale can be measured through correlating the scores obtained from the research questionnaire with attitude and characteristics of the social phenomenon to be measured. When the relationship proves to be positive, then, the Likert scale passes the empirical validity test and is thus suitable and valid for the study. Content validity is yet another aspect of the validity test for the Likert scale that should be assessed. This entails the assessment of the test content, to determine whether the content includes the necessary representative information of the domain to be covered (Campbell, 1957). A study can only pass the content validity test, if the tests applied in the questionnaire are fully representative of the domain information that is being sought. Therefore, the items, integrated into the questionnaire tests, have a great impact on the content validity of the study. To assess whether the Likert scale applied in the study passes the content validity test, the actual content of the questionnaire is compared to the characteristics of the social phenomenon that is being studied, and the degree of comparison registered. Where the degree of comparison between the social phenomenon being studied, and the content of the questions and questionnaire proved to be high, then the Likert scale passes the content validity test. Conversely, when a great disparity between the characteristics of the phenomenon being studied and the content of the tests in the questionnaire exists, the content validity is said to be missing. The last validity test to be undertaken on the Likert scale is the construct validity test, which determines whether the construct scale applied for the study is appropriate. Construct validity is attained, where a construct actually becomes operational. In this case, if the theoretical framework provides that a certain theory measures a given construct, then the construct validity test is passed so the theory is put into practice, and the construct in question proved to be measured (Creswell, 2009). Construct validity is assessed through the comparison of the relationship that exists between the responses and different items of the questionnaire. For example, if the study measures the IQ level of individuals as the social phenomenon, the construct validity test would be passed while the IQ questionnaires are to cover questions and tests that measure the intelligence of the individual. Therefore, construct validity in this study will be measured through assessing how the tests and the questions formulated in the questionnaire relate to the responses that have been given. Demonstrating that the scale is reliable A research instrument or research scale is said to be reliable, if it consistently measures what it was expected to measure (Creswell, 2009). To assess the reliability of the Likert scale as applied in this study, some essential tests are carried out. First, a scale is reliable, if it covers a greater number of items that it seeks to measure. Therefore, the higher the number of participants involved in a study, the higher the reliability of the scale and the instruments of research used. This is because, by covering the entire population or a percentage that is close to the entire population, the study becomes more dependable (Anastasi, 1996). The objectivity of the scores and the ratings placed in the Likert scale questionnaire also determines the reliability of the scale. In case the scores are found to be highly objective, meaning they measure the actual objective for which the study was designed, the scale proves to be reliable (Campbell, 1957). Lastly, trick is another aspect that influences the reliability of a study and the scale applicable. The more tricky the questions and the scores applied, the lesser the reliability of the scale, since the respondents are forced to guess or answer out of lack of full knowledge. Therefore, the objectivity, the trickiness and the percentage of the population covered, will be applied to assess the reliability of the instruments of Quantitative Research, and of the Likert scale applied. Which test is appropriate, and what population is used for the scale and test Criterion test is the most appropriate for this study, since validity and reliability of the scale is measured through assessing how the tests of the study compare and match with the outcomes (criteria). This entails assessing whether the tests are giving results that were actually desired by the criteria applied. The population used for the scale and test is either the entire population, or a sub-set of the population that represents a great percentage, considering that Cross-Sectional Study seeks to cover all items of the population (Babbie, 2011). References Anastasi, A. (1986). Evolving concepts of test validation. Annual Review of Psychology, 37, 1-15. Babbie, E. R. (2011). The basics of social research. Australia: Wadsworth / Cengage Learning. Black, T. R. (1999). Doing quantitative research in the social sciences: An integrated approach to research design, measurement and statistics. London: SAGE Publications. Bowling, A. (1997). Research Methods in Health. Open University Press, Buckingham. Burns, N., & Grove, S. K. (1997). The Practice of Nursing Research Conduct, Critique, & Utilization. W.B. Saunders and Co., Philadelphia. Campbell, D. T. (1957). Factors relevant to the validity of experiments in social settings. Psychological Bulletin, 54, 297-312 Creswell, J.W. (2009). Qualitative, Quantitative, and Mix Methods Approaches. (3rd ed). Thousand Oaks, CA: Sage Publications. Frankfort-Nachmias, C., & Nachmias, D. (2008). Research methods in the social sciences (7th ed). New York: Worth Publishers. Likert, R. (1932). A Technique for the Measurement of Attitudes. Archives of Psychology, 140: 1–55. Read More