Research Methods
Foundational Concepts in Quantitative Methodology
Arnes Hadzic
Generalizability - It is primarily a methodology used to characterize and quantify specific sources of error that contaminate the observed measurement of interesest in order to have future research be more error free. In other words, if something has often happened in the past, it will likely happen in the future (Lee & Baskerville, 2003). In research that is extremely important because once researchers have collected enough data to support their hypothesis, they can develop a premise to predict the outcome in similar situations with a certain degree of accuracy (Lee & Baskerville, 2003). In order to increase our confidence in the generalizability of a study, it would have to be repeated with the same program but different test subjects in different settings and yield similar results.
Type I Error - Errors in research are important; not always will a researcher get everything he is looking for without issues along the way. Type I error occurs when the null hypothesis is falsely rejected, basically, Type I errors are false-positive findings (Reber, 1985, p. 337). In other words, a researcher may be going along looking at a topic and come up with a result and notices that a difference exists, but, in truth there is no difference. So, the null hypothesis is wrongly rejected when it is true. For example, if a researcher was interested in examining the relationship between music and emotion, he or she may believe that there is a relationship (Rosenthal & Rosnow, 1991, p. 624). However, a more specific proposition is needed in order to be able to do further research on this notion. A researcher gets a Type I error if they falsely reject the notion that music at a fast tempo and at a slow tempo is the same in happiness, basically saying there is no relationship between the two.
Type 2 Error - It is used with the context of hypothesis testing that describes the error that occurs when one accepts a
Arnes Hadzic
Generalizability - It is primarily a methodology used to characterize and quantify specific sources of error that contaminate the observed measurement of interesest in order to have future research be more error free. In other words, if something has often happened in the past, it will likely happen in the future (Lee & Baskerville, 2003). In research that is extremely important because once researchers have collected enough data to support their hypothesis, they can develop a premise to predict the outcome in similar situations with a certain degree of accuracy (Lee & Baskerville, 2003). In order to increase our confidence in the generalizability of a study, it would have to be repeated with the same program but different test subjects in different settings and yield similar results.
Type I Error - Errors in research are important; not always will a researcher get everything he is looking for without issues along the way. Type I error occurs when the null hypothesis is falsely rejected, basically, Type I errors are false-positive findings (Reber, 1985, p. 337). In other words, a researcher may be going along looking at a topic and come up with a result and notices that a difference exists, but, in truth there is no difference. So, the null hypothesis is wrongly rejected when it is true. For example, if a researcher was interested in examining the relationship between music and emotion, he or she may believe that there is a relationship (Rosenthal & Rosnow, 1991, p. 624). However, a more specific proposition is needed in order to be able to do further research on this notion. A researcher gets a Type I error if they falsely reject the notion that music at a fast tempo and at a slow tempo is the same in happiness, basically saying there is no relationship between the two.
Type 2 Error - It is used with the context of hypothesis testing that describes the error that occurs when one accepts a
References: Beckstead, J. W. (2007). A note on determining the number of cues used in judgment analysis studies: The issue of type II error. Cohen, J. (1973). Statistical Power Analysis and Research Results. American Educational Research Journal. Cluster sampling. (n.d.). Retrieved February 26, 2014, from https://www.princeton.edu/~achaney/tmve/wiki100k/docs/Cluster_sampling.html Gay, L Kerlinger, F. N. (1986). Foundations of behavioral research (3rd ed.). Fort Worth: Holt, Rinehart and Winston, Inc. Johnson, D. H., Gibbs, J. P., Herzog, M., Lor, S., Niemuth, N. D., Ribic, C. A., . . . Thompson, W. L. (2009). A Sampling Design Framework for Monitoring Secretive Marshbirds. Waterbirds. doi:10.1675/063.032.0201 LaFountain, R Laycock, G. (2000). Hypothesis-based Research: The Repeat Victimisation Story. Lee, A. S., & Baskerville, R. L. (2003). Generalizing Generalizability in Information Systems Research. Information Systems Research. Mitra, S. K., & Pathak, P. K. (1984). The Nature of Simple Random Sampling. Annals of Statistics, 12(4), 1536-1542. doi:10.1214/aos/1176346810 Purposive sampling | Lærd Dissertation Reber, A. S. (1985). Dictionary of psychology. New York: Penguin Books. Rosenthal, R., & Rosnow, R. L. (1991). Essentials of behavioral research: Methods and data analysis (2nd ed.). New York: McGraw-Hill, Inc. Schmidt, F. L. (1996). Statistical significance testing and cumulative knowledge in psychology: Implications for training of researchers. Psychological Methods. doi:10.1037//1082-989X.1.2.115 Shaver, J Smalheiser, N. R. (2002). Informatics and hypothesis-driven research. Embo Reports. Whalberg, H. J. (1984). Improving the productivity of America 's schools. Educational Leadership, 41(8), 19-27. Whysong, G. L., & Brady, W. W. (1987). Frequency Sampling and Type II Errors. Journal of Range Management, 40(5), 472-474. doi:10.2307/3899614 Wuensch, K