Abstract
Mathematically defined random chance requires that every possible alternative sampling or assignment outcome has an equal or known probability of occurring. This is very different than haphazard chance for the outcomes of which there are no such statistical expectations. Because random chance cannot be sufficiently ensured for social science research purposes is logically arguable, what is actually relied upon must be haphazard chance. This needs to be made clear for several key aspects of social science research methodology: generalizing from samples, making treatment contrasts unbiased by unmeasured on subject dimensions, meta-analysis, interpreting comparative experiments’ residual outcome variance and so their statistical significance testing, the meaning of psychological measurement unreliability and of latent variables, and the imputation of missing data.
Similar content being viewed by others
Notes
Resampling techniques treat samples as populations in order to estimate the robustness of sample estimates by multiply sub-sampling given samples in order to get a distribution of estimates, but this does not escape the problem of needing randomness for statistical significance testing: “If external validity is a goal of the analysis, then random sampling [to obtain a sample for repeated sub-sampling] is important. If internal validity is a goal (as in experimental design), random assignment is an important assumption.”, however, “If the sample that is used to generate the empirical sampling distribution does not adequately represent the population, then the elements it contains that are probabilistically different from their occurrence in the population can compromise the inference process. Thus, at a very fundamental level, all resampling procedures assume that the sample that is used to generate the empirical sampling distribution reflects the structure of the population from which it came” (Rodgers 1999, 444).
Any device for approximating the results of random sampling (see Dattalo 2009, 20–92), when random sampling is infeasible, adds this device’s problems in trying to represent the target population’s distribution (and how close cannot be known) to those of a random sampling’s attempt to do this (and how close it does so is another unknown).
Any device for approximating the results of random assignment (see Dattalo 2009, 93–148), when it is infeasible, for trying to equate the influence of unmeasured subject independent-variables on a comparative experiment’s dependent-variables across the experiment’s comparison groups adds this device’s problems in trying to do so (how close it does is one unknown) to those of a random assignment’s attempt to do this (and how close it does is another unknown).
References
Baker, J.R., Yardley, J.K., McCaul, K.: Characteristics of responding-, non-responding-, and refusing-parents in an adolescent lifestyle choice study. Eval. Rev. 25(6), 605–618 (2001)
Beltrami, E.: What is Random? Chance and Order in Mathematics and Life. Springer, New York (1999)
Bennett, D.J.: Randomness. Harvard University Press, Cambridge (1998)
Brown, G.S.: Probability and Scientific Inference. Longmans, Green, London (1957)
Chen, S.: Random number generators go public. Science 360, 1383–1384 (2018)
Dattalo, P.: Strategies to Approximate Random Sampling and Assignment. Oxford University Press, New York (2009)
Dattalo, P.: Ethical dilemmas in sampling. J. Soc. Work Values Ethics 7(1), 1–12 (2010)
Di Franco, G.: An alternative procedure for imputing missing data based on principal components analysis. Qual. Quant. 48(3), 1149–1163 (2014)
Feller, W.: An Introduction to Probability Theory and Its Applications, vol. 1, 3rd edn. Wiley, New York (1968)
Ganguli, M., Mendelsohn, A., Lytle, M., Dodge, H.: A follow-up comparison of study participants and refusers within a rural elderly population. J. Gerontol. Ser. A Biol. Sci. Med. Sci. 53(6), M465–M470 (1998)
Gellert, W., Küstner, H., Hellwich, M., Kästner, H. (eds.): The VNR Concise Encyclopedia of Mathematics. Van Nostrand Reinhold, New York (1977)
Hacking, I.: Logic of Statistical Inference. Cambridge University Press, Cambridge (1965)
Hedges, L.V.: Estimation of effect size from a series of independent experiments. Psychol. Bull. 92, 490–499 (1982)
Howard, K.I., Krause, M.S., Orlinsky, D.E.: The attrition dilemma. J. Consult. Clin. Psychol. 54, 106–110 (1986)
Howard, K.I., Krause, M.S., Saunders, S.M., Kopta, S.M.: Trials and tribulations in the meta-analysis of treatment differences: comment on Wampold et al. (1997). Psychol. Bull. 122, 221–225 (1997)
Kish, L.: Survey Sampling. Wiley, New York (1965)
Krause, M.S.: How the psychotherapy research community must work toward measurement validity and why. J. Clin. Psychol. 61, 269–283 (2005)
Krause, M.S.: Significance testing and clinical trials. Psychotherapy 48, 217–222, 234–236 (2011)
Krause, M.S.: Measurement validity is fundamentally a matter of definition, not correlation. Rev. Gen. Psychol. 16, 391–400 (2012)
Krause, M.S.: The incompatibility of fully specifying linear causal models and assuming that residual dependent variable variance is random. Qual. Quant. 47, 3201–3204 (2013a)
Krause, M.S.: The data analytic implications of human psychology’s dimensions being ordinally scaled. Rev. Gen. Psychol. 17, 318–325 (2013b)
Krause, M.S.: Case sampling for psychotherapy practice, theory, and policy guidance: qualities and quantities. Psychother. Res. 26, 530–544 (2016)
Krause, M.S.: The scientific study of the qualities of individual human lives, rather than of their average quantities in aggregations of lives. Qual. Quant. 52, 1315–1329 (2018a)
Krause, M.S.: Mathematical expression and sampling issues of treatment-contrasts: beyond significance testing and meta-analysis to clinically useful research synthesis. Psychother. Res. 28(1), 58–75 (2018b)
Krause, M.S.: Psychological measuring and measurements: their possible effects on persons measured and unmeasured: reactivity. J. Methods Meas. Soc. Sci. https://journals.uair.arizona.edu/index.php/jmmss/index (2018c)
Krause, M.S., Howard, K.I.: What random assignment does and does not do. J. Clin. Psychol. 59, 751–766 (2003)
Krause, M.S., Lutz, W.: How we really ought to be comparing treatments for clinical purposes. Psychotherapy 43, 359–361 (2006)
Krause, M.S., Lutz, W., Bőhnke, J.R.: The role of sampling in clinical trial design. Psychother. Res. 21, 143–151 (2011)
Little, R.J., D’Agostino, R., et al.: The prevention and treatment of missing data in clinical trials. N. Engl. J. Med. 367, 1355–1360 (2012)
Little, R.J., Rubin, D.B.: Statistical Analysis with Missing Data. Wiley, New York (1987)
Markides, K.S., Dickson, H.D., Pappas, C.: Characteristics of dropouts in longitudinal research on aging: a study of Mexican Americans and Anglos. Exp. Aging Res. 8(3), 163–167 (1982)
Michell, J.: Is psychometrics pathological science? Meas. Interdiscip. Res. Perspect. 6, 7–24 (2008)
Michell, J.: The quantity/quality interchange: a blind spot on the highway of science. In: Valsiner, J., Toomela, A. (eds.) Methodological Thinking in Psychology: 60 Years Gone Astray?, pp. 45–68. Information Age Publishing, Charlotte (2010)
Nickerson, R.S.: Null hypothesis significance testing: a review of an old and continuing controversy. Psychol. Methods 5, 241–301 (2000)
Nickerson, R.S.: The production and perception of randomness. Psychol. Rev. 109, 330–357 (2002)
Rodgers, J.L.: The bootstrap, the jackknife, and the randomization test: a sampling taxonomy. Multivar. Behav. Res. 34, 441–456 (1999)
Rosenthal, R.: Meta-analytic Procedures for Social Research. Sage, Beverly Hills (1984)
Schafer, J.L.: Analysis of Incomplete Multivariate Data. Chapman & Hall, New York (1997)
Schafer, J.L., Graham, J.W.: Missing data: our view of the state of the art. Psychol. Methods 7, 147–177 (2002)
Seaman, S., Galati, J., Jackson, D., Carlin, J.: What is meant by” missing at random”? Stat. Sci. 28, 257–268 (2013)
Sechrest, L., Davis, M.F., Stickle, T.R., McKnight, P.: Understanding “method” variance. In: Bickman, L. (ed.) Research Design: Donald Campbell’s Legacy, vol. 2, pp. 63–87. Sage, Thousand Oaks (2000)
Stuart, A., Ord, J.K., Arnold, S.: Kendall’s Advanced Theory of Statistics, Volume 2a: Classical Inference and the Linear Model, 6th edn. Arnold, London (1999)
Thompson, M.G., Heller, K., Rody, C.A.: Recruitment challenges in studying late-life depression: do community samples adequately represent depressed older adults? Psychol. Aging 9(1), 121–125 (1994)
Volchan, S.B.: What is a random sequence? Am. Math. Mon. 109(1), 46–63 (2002)
Worrall, J.: Why there’s no cause to randomize. Br. J. Philos. Sci. 58, 451–488 (2007)
Author information
Authors and Affiliations
Ethics declarations
Conflict of interest
The author declares that he has no conflict of interest.
Additional information
The author is now a Ph.D. independent scholar and an emeritus fellow of AAAS, APA, and APS.
Rights and permissions
About this article
Cite this article
Krause, M.S. Randomness is problematic for social science research purposes. Qual Quant 53, 1495–1504 (2019). https://doi.org/10.1007/s11135-018-0824-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11135-018-0824-4