Archive for August, 2009

Reliability Coefficients: Starting from the Beginning

August 31, 2009

[This posting was prompted by questions concerning a previous blog entry, Reliability Revisited, and provides background on reliability that only Rasch measurement practitioners are likely to possess.] Most measurement applications based in ordinal data do not implement rigorous checks of the internal consistency of the observations, nor do they typically use the log-odds transformation to convert the nonlinear scores into linear measures. Measurement is usually defined in statistical terms, applying population-level models to obtain group-level summary scores, means, and percentages. Measurement, however, ought to involve individual-level models and case-specific location estimates. (See one of my earlier blogs for more on this distinction between statistics and measurement.)

Given the appropriate measurement focus on the individual, the instrument is initially calibrated and measures are estimated in a simultaneous conjoint process. Once the instrument is calibrated, the item estimates can be anchored, measures can be routinely produced from them, and new items can be calibrated into the system, and others dropped, over time. This method has been the norm in admissions, certification, licensure, and high stakes testing for decades (Fisher & Wright, 1994; Bezruczko, 2005).

Measurement modelling of individual response processes has to be stochastic, or else we run into the attenuation paradox (Engelhard, 1993, 1994). This is the situation in which a deterministic progression of observations from one end of the instrument to the other produces apparently error-free data strings that look like this (1 being a correct answer, a higher rating, or the presence of an attribute, and 0 being incorrect, a lower rating, or the absence of the attribute):

00000000000

10000000000

11000000000

11100000000

11110000000

11111000000

11111100000

11111111000

11111111100

11111111110

11111111111

In this situation, strings with all 0s and all 1s give no information useful for estimating measures (rows) or calibrations (columns). It is as though some of the people are shorter than the first unit on the ruler, and others are taller than the top unit. We don’t really have any way of knowing how short or tall they are, so their rows drop out. But eliminating the top and bottom rows makes the leftmost and rightmost columns all 0s and 1s, and eliminating them then gives new rows with all 0s and 1s, etc., until there’s no data left. (See my Revisiting Reliability blog for evaluations of five different probabilistically-structured data sets of this kind simulated to contrast various approaches to assessing reliability and internal consistency.)

The problem for estimation (Linacre, 1991, 1999, 2000) in data like those shown above is that the lack of informational overlaps between the columns, on the one hand, and between the rows, on the other, gives us no basis for knowing how much more of the variable is represented by any one item relative to any other, or by any one person measured relative to any other. In addition, whenever we actually construct measures of abilities, attitudes, or behaviors that conform with this kind of Guttman (1950) structure (Andrich, 1985; Douglas & Wright, 1989; Engelhard, 2008), the items have to be of such markedly different difficulties or agreeabilities that the results tend to involve large numbers of indistinguishable groups of respondents. But when that information is present in a probabilistically consistent way, we have an example of the phenomenon of stochastic resonance (Fisher, 1992b), so called because of the way noise amplifies weak deterministic signals (Andò & Graziani, 2000; Benzi, Sutera, & Vulpiani, 1981; Bulsara & Gammaitoni, 1996; Dykman & McClintock, 1998; Schimansky-Geier, Freund, Neiman, & Shulgin, 1998).

We need the noise, but we can’t let it overwhelm the system. We have to be able to know how much error there is relative to actual signal. Reliability is traditionally defined (Guilford 1965, pp. 439-40) as an estimate of this relation of signal and noise:

“The reliability of any set of measurements is logically defined as the proportion of their variance that is true variance…. We think of the total variance of a set of measures as being made up of two sources of variance: true variance and error variance… The true measure is assumed to be the genuine value of whatever is being measured… The error components occur independently and at random.”

Traditional reliability coefficients, like Cronbach’s alpha, are correlational, implementing a statistical model of group-level information. Error is taken to be the unexplained portion of the variance:

“In his description of alpha Cronbach (1951) proved (1) that alpha is the mean of all possible split-half coefficients, (2) that alpha is the value expected when two random samples of items from a pool like those in the given test are correlated, and (3) that alpha is a lower bound to the proportion of test variance attributable to common factors among the items” (Hattie, 1985, pp. 143-4).

But measurement models of individual-level response processes (Rasch, 1960; Andrich, 1988; Wright, 1977; Fisher & Wright, 1994; Bond & Fox, 2007; Wilson, 2005; Bezruczko, 2005) employ individual-level error estimates (Wright, 1977; Wright & Stone, 1979; Wright & Masters, 1982), not correlational group-level variance estimates. The individual measurement errors are statistically equivalent to sampling confidence intervals, as is evident in both Wright’s equations and in plots of errors and confidence intervals (see Figure 4 in Fisher, 2008). That is, error and confidence intervals both decline at the same rate with larger numbers of item responses per person, or larger numbers of person responses per item.

This phenomenon has a constructive application in instrument design. If a reasonable expectation for the measurement standard deviation can be formulated and related to the error expected on the basis of the number of items and response categories, a good estimate of the measurement reliability can be read off a nomograph (Linacre, 1993).

Wright (Wright & Masters, 1982, pp. 92, 106; Wright, 1996) introduced several vitally important measurement precision concepts and tools that follow from access to individual person and item error estimates. They improve on the traditional KR-20 or Cronbach reliability coefficients because the individualized error estimates better account for the imprecisions of mistargeted instruments, and for missing data, and so more accurately and conservatively estimate reliability.

Wright and Masters introduce a new reliability statistic, G, the measurement separation reliability index. The availability of individual error estimates makes it possible to estimate the true variance of the measures more directly, by subtracting the mean square error from the total variance. The standard deviation based on this estimate of true variance is then made the numerator of a ratio, G, having the root mean square error as its denominator.

Each unit increase in this G index then represents another multiple of the error unit in the amount of quantitative variation present in the measures. This multiple is nonlinearly represented in the traditional reliability coefficients expressed in the 0.00 – 1.00 range, such that the same separation index unit difference is found in the 0.00 to 0.50, 0.50 to 0.80, 0.80 to 0.90, 0.90 to 0.94, 0.94 to 0.96, and 0.96 to 0.97 reliability ranges (see Fisher, 1992a, for a table of values; available online: see references).

G can also be estimated as the square root of the reliability divided by one minus the reliability. Conversely, a reliability coefficient roughly equivalent to Cronbach’s alpha is estimated as G squared divided by G squared plus the error variance. Because individual error estimates are inflated in the presence of missing data and when an instrument is mistargeted and measures tend toward the extremes, the Rasch-based reliability coefficients tend to be more conservative than Cronbach’s alpha, as these sources of error are hidden within the variances and correlations. For a comparison of the G separation index, the G reliability coefficient, and Cronbach’s alpha over five simulated data sets, see the Reliability Revisited blog entry.

Error estimates can be made more conservative yet by multiplying each individual error term by the larger of either 1.0 or the square root of the associated individual mean square fit statistic for that case (Wright, 1995). (The mean square fit statistics are chi-squares divided by their degrees of freedom, and so have an expected value of 1.00; see Smith (1996) for more on fit, and see my recent blog, Revisiting Reliability, for more on the conceptualization and evaluation of reliability relative to fit.)

Wright and Masters (1982, pp. 92, 105-6) also introduce the concept of strata, ranges on the measurement continuum with centers separated by three errors. Strata are in effect a more forgiving expression of the separation reliability index, G, since the latter approximates strata with centers separated by four errors. An estimate of strata defined as having centers separated by four errors is very nearly identical with the separation index. If three errors define a 95% confidence interval, four are equivalent to 99% confidence.

There is a particular relevance in all of this for practical applications involving the combination or aggregation of physical, chemical, and other previously calibrated measures. This is illustrated in, for instance, the use of chemical indicators in assessing disease severity, environmental pollution, etc. Though any individual measure of the amount of a chemical or compound is valid within the limits of its intended purpose, to arrive at measures delineating disease severity, overall pollution levels, etc., the relevant instruments must be designed, tested, calibrated, and maintained, just as any instruments are (Alvarez, 2005; Cipriani, Fox, Khuder, et al., 2005; Fisher, Bernstein, et al., 2002; Fisher, Priest, Gilder, et al., 2008; Hughes, Perkins, Wright, et al., 2003; Perkins, Wright, & Dorsey, 2005; Wright, 2000).

The same methodology that is applied in this work, involving the rating or assessment of the quality of the outcomes or impacts counted, expressed as percentages, or given in an indicator’s native metric (parts per million, acres, number served, etc.), is needed in the management of all forms of human, social, and natural capital. (Watch this space for a forthcoming blog applying this methodology to the scaling of the UN Millennium Development Goals data.) The practical advantages of working from calibrated instrumentation in these contexts include data quality evaluations, the replacement of nonlinear percentages with linear measures, data volume reduction with no loss of information, and the integration of meaningful and substantive qualities with additive quantities on annotated metrics.

References

Alvarez, P. (2005). Several noncategorical measures define air pollution. In N. Bezruczko (Ed.), Rasch measurement in health sciences (pp. 277-93). Maple Grove, MN: JAM Press.

Andò, B., & Graziani, S. (2000). Stochastic resonance theory and applications. New York: Kluwer Academic Publishers.

Andrich, D. (1985). An elaboration of Guttman scaling with Rasch models for measurement. In N. B. Tuma (Ed.), Sociological methodology 1985 (pp. 33-80). San Francisco, California: Jossey-Bass.

Andrich, D. (1988). Rasch models for measurement. (Vols. series no. 07-068). Sage University Paper Series on Quantitative Applications in the Social Sciences). Beverly Hills, California: Sage Publications.

Benzi, R., Sutera, A., & Vulpiani, A. (1981). The mechanism of stochastic resonance. Journal of Physics. A. Mathematical and General, 14, L453-L457.

Bezruczko, N. (Ed.). (2005). Rasch measurement in health sciences. Maple Grove, MN: JAM Press.

Bond, T., & Fox, C. (2007). Applying the Rasch model: Fundamental measurement in the human sciences, 2d edition. Mahwah, New Jersey: Lawrence Erlbaum Associates.

Bulsara, A. R., & Gammaitoni, L. (1996, March). Tuning in to noise. Physics Today, 49, 39-45.

Cipriani, D., Fox, C., Khuder, S., & Boudreau, N. (2005). Comparing Rasch analyses probability estimates to sensitivity, specificity and likelihood ratios when examining the utility of medical diagnostic tests. Journal of Applied Measurement, 6(2), 180-201.

Cronbach, L. J. (1951). Coefficient alpha and the internal structure of tests. Psychometrika, 16(3), 297-334.

Douglas, G. A., & Wright, B. D. (1989). Response patterns and their probabilities. Rasch Measurement Transactions, 3(4), 75-77 [http://www.rasch.org/rmt/rmt34.htm].

Dykman, M. I., & Mcclintock, P. V. E. (1998, January 22). What can stochastic resonance do? Nature, 391(6665), 344.

Engelhard, G., Jr. (1993). What is the attenuation paradox? Rasch Measurement Transactions, 6(4), 257 [http://www.rasch.org/rmt/rmt64.htm].

Engelhard, G., Jr. (1994). Resolving the attenuation paradox. Rasch Measurement Transactions, 8(3), 379.

Engelhard, G. (2008, July). Historical perspectives on invariant measurement: Guttman, Rasch, and Mokken. Measurement: Interdisciplinary Research & Perspectives, 6(3), 155-189.

Fisher, W. P., Jr. (1992a). Reliability statistics. Rasch Measurement Transactions, 6(3), 238 [http://www.rasch.org/rmt/rmt63i.htm].

Fisher, W. P., Jr. (1992b, Spring). Stochastic resonance and Rasch measurement. Rasch Measurement Transactions, 5(4), 186-187 [http://www.rasch.org/rmt/rmt54k.htm].

Fisher, W. P., Jr. (2008, Summer). The cash value of reliability. Rasch Measurement Transactions, 22(1), 1160-3 [http://www.rasch.org/rmt/rmt221.pdf].

Fisher, W. P., Jr., Bernstein, L. H., Qamar, A., Babb, J., Rypka, E. W., & Yasick, D. (2002, February). At the bedside: Measuring patient outcomes. Advance for Administrators of the Laboratory, 11(2), 8, 10 [http://laboratory-manager.advanceweb.com/Article/At-the-Bedside-7.aspx].

Fisher, W. P., Jr., Priest, E., Gilder, R., Blankenship, D., & Burton, E. C. (2008, July 3-6). Development of a novel heart failure measure to identify hospitalized patients at risk for intensive care unit admission. Presented at the World Congress on Controversies in Cardiovascular Diseases [http://www.comtecmed.com/ccare/2008/authors_abstract.aspx#Author15], Intercontinental Hotel, Berlin, Germany.

Fisher, W. P., Jr., & Wright, B. D. (Eds.). (1994). Applications of probabilistic conjoint measurement. International Journal of Educational Research, 21(6), 557-664.

Guilford, J. P. (1965). Fundamental statistics in psychology and education. 4th Edn. New York: McGraw-Hill.

Guttman, L. (1950). The basis for scalogram analysis. In S. A. Stouffer & et al. (Eds.), Studies in social psychology in World War II. volume 4: Measurement and prediction (pp. 60-90). New York: Wiley.

Hattie, J. (1985, June). Methodology review: Assessing unidimensionality of tests and items. Applied Psychological Measurement, 9(2), 139-64.

Hughes, L., Perkins, K., Wright, B. D., & Westrick, H. (2003). Using a Rasch scale to characterize the clinical features of patients with a clinical diagnosis of uncertain, probable or possible Alzheimer disease at intake. Journal of Alzheimer’s Disease, 5(5), 367-373.

Linacre, J. M. (1991, Spring). Stochastic Guttman order. Rasch Measurement Transactions, 5(4), 189 [http://www.rasch.org/rmt/rmt54p.htm].

Linacre, J. M. (1993). Rasch-based generalizability theory. Rasch Measurement Transactions, 7(1), 283-284; [http://www.rasch.org/rmt/rmt71h.htm].

Linacre, J. M. (1999). Understanding Rasch measurement: Estimation methods for Rasch measures. Journal of Outcome Measurement, 3(4), 382-405.

Linacre, J. M. (2000, Autumn). Guttman coefficients and Rasch data. Rasch Measurement Transactions, 14(2), 746-7 [http://www.rasch.org/rmt/rmt142e.htm].

Perkins, K., Wright, B. D., & Dorsey, J. K. (2005). Using Rasch measurement with medical data. In N. Bezruczko (Ed.), Rasch measurement in health sciences (pp. 221-34). Maple Grove, MN: JAM Press.

Rasch, G. (1960). Probabilistic models for some intelligence and attainment tests (Reprint, with Foreword and Afterword by B. D. Wright, Chicago: University of Chicago Press, 1980). Copenhagen, Denmark: Danmarks Paedogogiske Institut.

Schimansky-Geier, L., Freund, J. A., Neiman, A. B., & Shulgin, B. (1998). Noise induced order: Stochastic resonance. International Journal of Bifurcation and Chaos, 8(5), 869-79.

Smith, R. M. (2000). Fit analysis in latent trait measurement models. Journal of Applied Measurement, 1(2), 199-218.

Wilson, M. (2005). Constructing measures: An item response modeling approach. Mahwah, New Jersey: Lawrence Erlbaum Associates.

Wright, B. D. (1977). Solving measurement problems with the Rasch model. Journal of Educational Measurement, 14(2), 97-116 [http://www.rasch.org/memo42.htm].

Wright, B. D. (1995, Summer). Which standard error? Rasch Measurement Transactions, 9(2), 436-437 [http://www.rasch.org/rmt/rmt92n.htm].

Wright, B. D. (1996, Winter). Reliability and separation. Rasch Measurement Transactions, 9(4), 472 [http://www.rasch.org/rmt/rmt94n.htm].

Wright, B. D. (2000). Rasch regression: My recipe. Rasch Measurement Transactions, 14(3), 758-9 [http://www.rasch.org/rmt/rmt143u.htm].

Wright, B. D., & Masters, G. N. (1982). Rating scale analysis: Rasch measurement. Chicago, Illinois: MESA Press.

Wright, B. D., & Stone, M. H. (1979). Best test design: Rasch measurement. Chicago, Illinois: MESA Press.

Creative Commons License
LivingCapitalMetrics Blog by William P. Fisher, Jr., Ph.D. is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.
Based on a work at livingcapitalmetrics.wordpress.com.
Permissions beyond the scope of this license may be available at http://www.livingcapitalmetrics.com.

Advertisements

Reliability Revisited: Distinguishing Consistency from Error

August 28, 2009

When something is meaningful to us, and we understand it, then we can successfully restate it in our own words and predictably reproduce approximately the same representation across situations  as was obtained in the original formulation. When data fit a Rasch model, the implications are (1) that different subsets of items (that is, different ways of composing a series of observations summarized in a sufficient statistic) will all converge on the same pattern of person measures, and (2) that different samples of respondents or examinees will all converge on the same pattern of item calibrations. The meaningfulness of propositions based in these patterns will then not depend on which collection of items (instrument) or sample of persons is obtained, and all instruments might be equated relative to a single universal, uniform metric so that the same symbols reliably represent the same amount of the same thing.

Statistics and research methods textbooks in psychology and the social sciences commonly make statements like the following about reliability: “Reliability is consistency in measurement. The reliability of individual scale items increases with the number of points in the item. The reliability of the complete scale increases with the number of items.” (These sentences are found at the top of p. 371 in Experimental Methods in Psychology, by Gustav Levine and Stanley Parkinson (Lawrence Erlbaum Associates, 1994).) The unproven, perhaps unintended, and likely unfounded implication of these statements is that consistency increases as items are added.

Despite the popularity of doing so, Green, Lissitz, and Mulaik (1977) argue that reliability coefficients are misused when they are interpreted as indicating the extent to which data are internally consistent. “Green et al. (1977) observed that though high ‘internal consistency’ as indexed by a high alpha results when a general factor runs through the items, this does not rule out obtaining high alpha when there is no general factor running through the test items…. They concluded that the chief defect of alpha as an index of dimensionality is its tendency to increase as the number of items increase” (Hattie, 1985, p. 144).

In addressing the internal consistency of data, the implicit but incompletely realized purpose of estimating scale reliability is to evaluate the extent to which sum scores function as sufficient statistics. How limited is reliability as a tool for this purpose? To answer this question, five dichotomous data sets of 23 items and 22 persons were simulated. The first one was constructed so as to be highly likely to fit a Rasch model, with a deliberately orchestrated probabilistic Guttman pattern. The second one was made nearly completely random. The third, fourth, and fifth data sets were modifications of the first one in which increasing numbers of increasingly inconsistent responses were introduced. (The inconsistencies were not introduced in any systematic way apart from inserting contrary responses in the ordered matrix.) The data sets are shown in the Appendix. Tables 1 and 2 summarize the results.

Table 1 shows that the reliability coefficients do in fact decrease, along with the global model fit log-likelihood chi-squares, as the amount of randomness and inconsistency is increased. Contrary to what is implied in Levine and Parkinson’s statements, however, reliability can vary within a given number of items, as it might across different data sets produced from the same test, survey, or assessment, depending on how much structural invariance is present within them.

Two other points about the tables are worthy of note. First, the Rasch-based person separation reliability coefficients drop at a faster rate than Cronbach’s alpha does. This is probably an effect of the individualized error estimates in the Rasch context, which makes its reliability coefficients more conservative than correlation-based, group-level error estimates. (It is worth noting, as well, that the Winsteps and SPSS estimates of Cronbach’s alpha match. They are reported to one fewer decimal places by Winsteps, but the third decimal place is shown for the SPSS values for contrast.)

Second, the fit statistics are most affected by the initial and most glaring introduction of inconsistencies, in data set three. As the randomness in the data increases, the reliabilities continue to drop, but the fit statistics improve, culminating in the case of data set two, where complete randomness results in near-perfect model fit. This is, of course, the situation in which both the instrument and the sample are as well targeted as they can be, since all respondents have about the same measure and all the items about the same calibration; see Wood (1978) for a commentary on this situation, where coin tosses fit a Rasch model.

Table 2 shows the results of the Winsteps Principal Components Analysis of the standardized residuals for all five data sets. Again, the results conform with and support the pattern shown in the reliability coefficients. It is, however, interesting to note that, for data sets 4 and 5, with their Cronbach’s alphas of about .89 and .80, respectively, which are typically deemed quite good, the PCA shows more variance left unexplained than is explained by the Rasch dimension. The PCA is suggesting that two or more constructs might be represented in the data, but this would never be known from Cronbach’s alpha alone.

Alpha alone would indicate the presence of a unidimensional construct for data sets 3, 4 and 5, despite large standard deviations in the fit statistics and even though more than half the variance cannot be explained by the primary dimension. Worse, for the fifth data set, more variance is captured in the first three contrasts than is explained by the Rasch dimension. But with Cronbach’s alpha at .80, most researchers would consider this scale quite satisfactorily unidimensional and internally consistent.

These results suggest that, first, in seeking high reliability, what is sought more fundamentally is fit to a Rasch model (Andrich & Douglas, 1977; Andrich, 1982; Wright, 1977). That is, in addressing the internal consistency of data, the popular conception of reliability is taking on the concerns of construct validity. A conceptually clearer sense of reliability focuses on the extent to which an instrument works as expected every time it is used, in the sense of the way a car can be reliable. For instance, with an alpha of .70, a screening tool would be able to reliably distinguish measures into two statistically distinct groups (Fisher, 1992; Wright, 1996), problematic and typical. Within the limits of this purpose, the tool would meet the need for the repeated production of information capable of meeting the needs of the situation. Applications in research, accountability, licensure/certification, or diagnosis, however, might demand alphas of .95 and the kind of precision that allows for statistically distinct divisions into six or more groups. In these kinds of applications, where experimental designs or practical demands require more statistical power, measurement precision articulates finer degrees of differences. Finely calibrated instruments provide sensitivity over the entire length of the measurement continuum, which is needed for repeated reproductions of the small amounts of change that might accrue from hard to detect treatment effects.

Separating the construct, internal consistency, and unidimensionality issues  from the repeatability and reproducibility of a given degree of measurement precision provides a much-needed conceptual and methodological clarification of reliability. This clarification is routinely made in Rasch measurement applications (Andrich, 1982; Andrich & Douglas, 1977; Fisher, 1992; Linacre, 1993, 1996, 1997). It is reasonable to want to account for inconsistencies in the data in the error estimates and in the reliability coefficients, and so errors and reliabilities are routinely reported in terms of both the modeled expectations and in a fit-inflated form (Wright, 1995). The fundamental value of proceeding from a basis in individual error and fit statistics (Wright, 1996), is that local imprecisions and failures of invariance can be isolated for further study and selective attention.

The results of the simulated data analyses suggest, second, that, used in isolation, reliability coefficients can be misleading. As Green, et al. say, reliability estimates tend to systematically increase as the number of items increases (Fisher, 2008). The simulated data show that reliability coefficients also systematically decrease as inconsistency increases.

The primary problem with relying on reliability coefficients alone as indications of data consistency hinges on their inability to reveal the location of departures from modeled expectations. Most uses of reliability coefficients take place in contexts in which the model remains unstated and expectations are not formulated or compared with observations. The best that can be done in the absence of a model statement and test of data fit to it is to compare the reliability obtained against that expected on the basis of the number of items and response categories, relative to the observed standard deviation in the scores, expressed in logits (Linacre, 1993). One might then raise questions as to targeting, data consistency, etc. in order to explain larger than expected differences.

A more methodical way, however, would be to employ multiple avenues of approach to the evaluation of the data, including the use of model fit statistics and Principal Components Analysis in the evaluation of differential item and person functioning. Being able to see which individual observations depart the furthest from modeled expectation can provide illuminating qualitative information on the meaningfulness of the data, the measures, and the calibrations, or the lack thereof.  This information is crucial to correcting data entry errors, identifying sources of differential item or person functioning, separating constructs and populations, and improving the instrument. The power of the reliability-coefficient-only approach to data quality evaluation is multiplied many times over when the researcher sets up a nested series of iterative dialectics in which repeated data analyses explore various hypotheses as to what the construct is, and in which these analyses feed into revisions to the instrument, its administration, and/or the population sampled.

For instance, following the point made by Smith (1996), it may be expected that the PCA results will illuminate the presence of multiple constructs in the data with greater clarity than the fit statistics, when there are nearly equal numbers of items representing each different measured dimension. But the PCA does not work as well as the fit statistics when there are only a few items and/or people exhibiting inconsistencies.

This work should result in a full circle return to the drawing board (Wright, 1994; Wright & Stone, 2003), such that a theory of the measured construct ultimately provides rigorously precise predictive control over item calibrations, in the manner of the Lexile Framework (Stenner, et al., 2006) or developmental theories of hierarchical complexity (Dawson, 2004). Given that the five data sets employed here were simulations with no associated item content, the invariant stability and meaningfulness of the construct cannot be illustrated or annotated. But such illustration also is implicit in the quest for reliable instrumentation: the evidentiary basis for a delineation of meaningful expressions of amounts of the thing measured. The hope to be gleaned from the successes in theoretical prediction achieved to date is that we might arrive at practical applications of psychosocial measures that are as meaningful, useful, and economically productive as the theoretical applications of electromagnetism, thermodynamics, etc. that we take for granted in the technologies of everyday life.

Table 1

Reliability and Consistency Statistics

22 Persons, 23 Items, 506 Data Points

Data set Intended reliability Winsteps Real/Model Person Separation Reliability Winsteps/SPSS Cronbach’s alpha Winsteps Person Infit/Outfit Average Mn Sq Winsteps Person Infit/Outfit SD Winsteps Real/Model Item Separation Reliability Winsteps Item Infit/Outfit Average Mn Sq Winsteps Item Infit/Outfit SD Log-Likelihood Chi-Sq/d.f./p
First Best .96/.97 .96/.957 1.04/.35 .49/.25 .95/.96 1.08/0.35 .36/.19 185/462/1.00
Second Worst .00/.00 .00/-1.668 1.00/1.00 .05/.06 .00/.00 1.00/1.00 .05/.06 679/462/.0000
Third Good .90/.91 .93/.927 .92/2.21 .30/2.83 .85/.88 .90/2.13 .64/3.43 337/462/.9996
Fourth Fair .86/.87 .89/.891 .96/1.91 .25/2.18 .79/.83 .94/1.68 .53/2.27 444/462/.7226
Fifth Poor .76/.77 .80/.797 .98/1.15 .24/.67 .59/.65 .99/1.15 .41/.84 550/462/.0029
Table 2

Principal Components Analysis

Data set Intended reliability % Raw Variance Explained by Measures/Persons/Items % Raw Variance Captured in First Three Contrasts Total number of loadings > |.40| in first contrast
First Best 76/41/35 12 8
Second Worst 4.3/1.7/2.6 56 15
Third Good 59/34/25 20 14
Fourth Fair 47/27/20 26 13
Fifth Poor 29/17/11 41 15

References

Andrich, D. (1982, June). An index of person separation in Latent Trait Theory, the traditional KR-20 index, and the Guttman scale response pattern. Education Research and Perspectives, 9(1), http://www.rasch.org/erp7.htm.

Andrich, D. & G. A. Douglas. (1977). Reliability: Distinctions between item consistency and subject separation with the simple logistic model. Paper presented at the Annual Meeting of the American Educational Research Association, New York.

Dawson, T. L. (2004, April). Assessing intellectual development: Three approaches, one sequence. Journal of Adult Development, 11(2), 71-85.

Fisher, W. P., Jr. (1992). Reliability statistics. Rasch Measurement Transactions, 6(3), 238  [http://www.rasch.org/rmt/rmt63i.htm].

Fisher, W. P., Jr. (2008, Summer). The cash value of reliability. Rasch Measurement Transactions, 22(1), 1160-3.

Green, S. B., Lissitz, R. W., & Mulaik, S. A. (1977, Winter). Limitations of coefficient alpha as an index of test unidimensionality. Educational and Psychological Measurement, 37(4), 827-833.

Hattie, J. (1985, June). Methodology review: Assessing unidimensionality of tests and items. Applied Psychological Measurement, 9(2), 139-64.

Levine, G., & Parkinson, S. (1994). Experimental methods in psychology. Mahwah, NJ: Lawrence Erlbaum Associates, Inc.

Linacre, J. M. (1993). Rasch-based generalizability theory. Rasch Measurement Transactions, 7(1), 283-284; [http://www.rasch.org/rmt/rmt71h.htm].

Linacre, J. M. (1996). True-score reliability or Rasch statistical validity? Rasch Measurement Transactions, 9(4), 455 [http://www.rasch.org/rmt/rmt94a.htm].

Linacre, J. M. (1997). KR-20 or Rasch reliability: Which tells the “Truth?”. Rasch Measurement Transactions, 11(3), 580-1 [http://www.rasch.org/rmt/rmt113l.htm].

Smith, R. M. (1996). A comparison of methods for determining dimensionality in Rasch measurement. Structural Equation Modeling, 3(1), 25-40.

Stenner, A. J., Burdick, H., Sanford, E. E., & Burdick, D. S. (2006). How accurate are Lexile text measures? Journal of Applied Measurement, 7(3), 307-22.

Wood, R. (1978). Fitting the Rasch model: A heady tale. British Journal of Mathematical and Statistical Psychology, 31, 27-32.

Wright, B. D. (1977). Solving measurement problems with the Rasch model. Journal of Educational Measurement, 14(2), 97-116 [http://www.rasch.org/memo42.htm].

Wright, B. D. (1980). Foreword, Afterword. In Probabilistic models for some intelligence and attainment tests, by Georg Rasch (pp. ix-xix, 185-199. http://www.rasch.org/memo63.htm) [Reprint; original work published in 1960 by the Danish Institute for Educational Research]. Chicago, Illinois: University of Chicago Press.

Wright, B. D. (1994, Summer). Theory construction from empirical observations. Rasch Measurement Transactions, 8(2), 362 [http://www.rasch.org/rmt/rmt82h.htm].

Wright, B. D. (1995, Summer). Which standard error? Rasch Measurement Transactions, 9(2), 436-437 [http://www.rasch.org/rmt/rmt92n.htm].

Wright, B. D. (1996, Winter). Reliability and separation. Rasch Measurement Transactions, 9(4), 472 [http://www.rasch.org/rmt/rmt94n.htm].

Wright, B. D., & Stone, M. H. (2003). Five steps to science: Observing, scoring, measuring, analyzing, and applying. Rasch Measurement Transactions, 17(1), 912-913 [http://www.rasch.org/rmt/rmt171j.htm].

Appendix

Data Set 1

01100000000000000000000

10100000000000000000000

11000000000000000000000

11100000000000000000000

11101000000000000000000

11011000000000000000000

11100100000000000000000

11110100000000000000000

11111010100000000000000

11111101000000000000000

11111111010101000000000

11111111101010100000000

11111111111010101000000

11111111101101010010000

11111111111010101100000

11111111111111010101000

11111111111111101010100

11111111111111110101011

11111111111111111010110

11111111111111111111001

11111111111111111111101

11111111111111111111100

Data Set 2

01101010101010101001001

10100101010101010010010

11010010101010100100101

10101001010101001001000

01101010101010110010011

11011010010101100100101

01100101001001001001010

10110101000110010010100

01011010100100100101001

11101101001001001010010

11011010010101010100100

10110101101010101001001

01101011010000101010010

11010110101001010010100

10101101010000101101010

11011010101010010101010

10110101010101001010101

11101010101010110101011

11010101010101011010110

10101010101010110111001

01010101010101101111101

10101010101011011111100

Data Set 3

01100000000000100000010

10100000000000000010001

11000000000000100000010

11100000000000100000000

11101000000000100010000

11011000000000000000000

11100100000000100000000

11110100000000000000000

11111010100000100000000

11111101000000000000000

11111111010101000000000

11111111101010100000000

11111111111010001000000

11011111111111010010000

11011111111111101100000

11111111111111010101000

11011111111111101010100

11111111111111010101011

11011111111111111010110

11111111111111111111001

11011111111111111111101

10111111111111111111110

Data Set 4

01100000000000100010010

10100000000000000010001

11000000000000100000010

11100000000000100000001

11101000000000100010000

11011000000000000010000

11100100000000100010000

11110100000000000000000

11111010100000100010000

11111101000000000000000

11111011010101000010000

11011110111010100000000

11111111011010001000000

11011111101011110010000

11011111101101101100000

11111111110101010101000

11011111111011101010100

11111111111101110101011

01011111111111011010110

10111111111111111111001

11011111111111011111101

10111111111111011111110

Data Set 5

11100000010000100010011

10100000000000000011001

11000000010000100001010

11100000010000100000011

11101000000000100010010

11011000000000000010011

11100100000000100010000

11110100000000000000011

11111010100000100010000

00000000000011111111111

11111011010101000010000

11011110111010100000000

11111111011010001000000

11011111101011110010000

11011111101101101100000

11111111110101010101000

11011111101011101010100

11111111111101110101011

01011111111111011010110

10111111101111111111001

11011111101111011111101

00111111101111011111110

Creative Commons License
LivingCapitalMetrics Blog by William P. Fisher, Jr., Ph.D. is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.
Based on a work at livingcapitalmetrics.wordpress.com.
Permissions beyond the scope of this license may be available at http://www.livingcapitalmetrics.com.

Statistics and Measurement: Clarifying the Differences

August 26, 2009

Measurement is qualitatively and paradigmatically quite different from statistics, even though statistics obviously play important roles in measurement, and vice versa. The perception of measurement as conceptually difficult stems in part from its rearrangement of most of the concepts that we take for granted in the statistical paradigm as landmarks of quantitative thinking. When we recognize and accept the qualitative differences between statistics and measurement, they both become easier to understand.

Statistical analyses are commonly referred to as quantitative, even though the numbers analyzed most usually have not been derived from the mapping of an invariant substantive unit onto a number line. Measurement takes such mapping as its primary concern, focusing on the quantitative meaningfulness of numbers (Falmagne & Narens, 1983; Luce, 1978; ,  Marcus-Roberts & Roberts, 1987; Mundy, 1986; Narens, 2002; Roberts, 1999). Statistical models focus on group processes and relations among variables, while measurement models focus on individual processes and relations within variables (Duncan, 1992; Duncan & Stenbeck, 1988; Rogosa, 1987). Statistics makes assumptions about factors beyond its control, while measurement sets requirements for objective inference (Andrich, 1989). Statistics primarily involves data analysis, while measurement primarily calibrates instruments in common metrics for interpretation at the point of use (Cohen, 1994; Fisher, 2000; Guttman, 1985; Goodman, 1999a-c; Rasch, 1960).

Statistics focuses on making the most of the data in hand, while measurement focuses on using the data in hand to inform (a) instrument calibration and improvement, and (b) the prediction and efficient gathering of meaningful new data on individuals in practical applications. Where statistical “measures” are defined inherently by a particular analytic method, measures read from calibrated instruments—and the raw observations informing these measures—need not be computerized for further analysis.

Because statistical “measures” are usually derived from ordinal raw scores, changes to the instrument change their meaning, resulting in a strong inclination to avoid improving the instrument. Measures, in contrast, take missing data into account, so their meaning remains invariant over instrument configurations, resulting in a firm basis for the emergence of a measurement quality improvement culture. So statistical “measurement” begins and ends with data analysis, where measurement from calibrated instruments is in a constant cycle of application, new item calibrations, and critical recalibrations that require only intermittent resampling.

The vast majority of statistical methods and models make strong assumptions about the nature of the unit of measurement, but provide either very limited ways of checking those assumptions, or no checks at all. Statistical models are descriptive in nature, meaning that models are fit to data, that the validity of the data is beyond the immediate scope of interest, and that the model accounting for the most variation is regarded as best. Finally, and perhaps most importantly, statistical models are inherently oriented toward the relations among variables at the level of samples and populations.

Measurement models, however, impose strong requirements on data quality in order to achieve the unit of measurement that is easiest to think with, one that stays constant and remains invariant across the local particulars of instrument and sample. Measurement methods and models, then, provide extensive and varied ways of checking the quality of the unit, and so must be prescriptive rather than descriptive. That is, measurement models define the data quality that must be obtained for objective inference. In the measurement paradigm, data are fit to models, data quality is of paramount interest, and data quality evaluation must be informed as much by qualitative criteria as by quantitative.

To repeat the most fundamental point, measurement models are oriented toward individual-level response processes, not group-level aggregate processes. Herbert Blumer pointed out as early as 1930 that quantitative method is not equivalent to statistical method, and that the natural sciences had conspicuous degrees of success long before the emergence of statistical techniques (Hammersly, 1989, pp. 113-4). Both the initial scientific revolution in the 16th-17th centuries and the second scientific revolution of the 19th century found a basis in measurement for publicly objective and reproducible results, but statistics played little or no role in the major discoveries of the times.

The scientific value of statistics resides largely in the reproducibility of cross-variable data relations, and statisticians widely agree that statistical analyses should depend only on sufficient statistics (Arnold, 1982, p. 79). Measurement theoreticians and practitioners also agree, but the sufficiency of the mean and standard deviation relative to a normal distribution is one thing, and the sufficiency of individual responses relative to an invariant construct is quite another (Andersen, 1977; Arnold, 1985; Dynkin, 1951; Fischer, 1981; Hall, Wijsman, & Ghosh, 1965; van der Linden, 1992).

It is of historical interest, though, to point out that Rasch, foremost proponent of the latter, attributes credit for the general value of the concept of sufficiency to Ronald Fisher, foremost proponent of the former. Rasch’s strong statements concerning the fundamental inferential value of sufficiency (Andrich, 1997; Rasch, 1977; Wright, 1980) would seem to contradict his repeated joke about burning all the statistics texts making use of the normal distribution (Andersen, 1995, p. 385) were it not for the paradigmatic distinction between statistical models of group-level relations among variables, and measurement models of individual processes. Indeed, this distinction is made on the first page of Rasch’s (1980) book.

Now we are in a position to appreciate a comment by Ernst Rutherford, the winner of the 1908 Nobel Prize in Chemistry, who held that, if you need statistics to understand the results of your experiment, then you should have designed a better experiment (Wise, 1995, p. 11). A similar point was made by Feinstein (1995) concerning meta-analysis. The rarely appreciated point is that the generalizable replication and application of results depends heavily on the existence of a portable and universally uniform observational framework. The inferences, judgments, and adjustments that can be made at the point of use by clinicians, teachers, managers, etc. provided with additive measures expressed in a substantively meaningful common metric far outstrip those that can be made using ordinal measures expressed in instrument- and sample-dependent scores. See Andrich (1989, 2002, 2004), Cohen (1994), Davidoff (1999), Duncan (1992), Embretson (1996), Goodman (1999a, 1999b, 1999c), Guttman (1981, 1985), Meehl (1967), Michell (1986), Rogosa (1987), Romanowski and Douglas (2002), and others for more on this distinction between statistics and measurement.

These contrasts show that the confounding of statistics and measurement is a problem of vast significance that persists in spite of repeated efforts to clarify the distinction. For a wide variety of reasons ranging from cultural presuppositions about the nature of number to the popular notion that quantification is as easy as assigning numbers to observations, measurement is not generally well understood by the public (or even by statisticians!). And so statistics textbooks rarely, if ever, include even passing mention of instrument calibration methods, metric equating processes, the evaluation of data quality relative to the requirements of objective inference, traceability to metrological reference standards, or the integration of qualitative and quantitative methods in the interpretation of measures.

Similarly, in business, marketing, health care, and quality improvement circles, we find near-universal repetition of the mantra, “You manage what you measure,” with very little or no attention paid to the quality of the numbers treated as measures. And so, we find ourselves stuck with so-called measurement systems where,

• instead of linear measures defined by a unit that remains constant across samples and instruments we saddle ourselves with nonlinear scores and percentages defined by units that vary in unknown ways across samples and instruments;
• instead of availing ourselves of the capacity to take missing data into account, we hobble ourselves with the need for complete data;
• instead of dramatically reducing data volume with no loss of information, we insist on constantly re-enacting the meaningless ritual of poring over undigestible masses of numbers;
• instead of adjusting measures for the severity or leniency of judges assigning ratings, we allow measures to depend unfairly on which rater happens to make the observations;
• instead of using methods that give the same result across different distributions, we restrict ourselves to ones that give different results when assumptions of normality are not met and/or standard deviations differ;
• instead of calibrating instruments in an experimental test of the hypothesis that the intended construct is in fact structured in such a way as to make its mapping onto a number line meaningful, we assign numbers and make quantitative inferences with no idea as to whether they relate at all to anything real;
• instead of checking to see whether rating scales work as intended, with higher ratings consistently representing more of the variable, we make assumptions that may be contradicted by the order and spacing of the way rating scales actually work in practice;
• instead of defining a comprehensive framework for interpreting measures relative to a construct, we accept the narrow limits of frameworks defined by the local sample and items;
• instead of capitalizing on the practicality and convenience of theories capable of accurately predicting item calibrations and measures apart from data, we counterproductively define measurement empirically in terms of data analysis;
• instead of putting calibrated tools into the hands of front-line managers, service representatives, teachers and clinicians, we require them to submit to cumbersome data entry, analysis, and reporting processes that defeat the purpose of measurement by ensuring the information provided is obsolete by the time it gets back to the person who could act on it; and
• instead of setting up efficient systems for communicating meaningful measures in common languages with shared points of reference, we settle for inefficient systems for communicating meaningless scores in local incommensurable languages.

Because measurement is simultaneously ubiquitous and rarely well understood, we find ourselves in a world that gives near-constant lip service to the importance of measurement while it does almost nothing to provide measures that behave the way we assume they do. This state of affairs seems to have emerged in large part due to our failure to distinguish between the group-level orientation of statistics and the individual-level orientation of measurement. We seem to have been seduced by a variation on what Whitehead (1925, pp. 52-8) called the fallacy of misplaced concreteness. That is, we have assumed that the power of lawful regularities in thought and behavior would be best revealed and acted on via statistical analyses of data that themselves embody the aggregate mass of the patterns involved.

It now appears, however, in light of studies in the history of science (Latour, 1987, 2005; Wise, 1995), that an alternative and likely more successful approach will be to capitalize on the “wisdom of crowds” (Surowiecki, 2004) phenomenon of collective, distributed cognition (Akkerman, et al., 2007; Douglas, 1986; Hutchins, 1995; Magnus, 2007). This will be done by embodying lawful regularities in instruments calibrated in ideal, abstract, and portable metrics put to work by front-line actors on mass scales (Fisher, 2000, 2005, 2009a, 2009b). In this way, we will inform individual decision processes and structure communicative transactions with efficiencies, meaningfulness, substantive effectiveness, and power that go far beyond anything that could be accomplished by trying to make inferences about individuals from group-level statistics.

We ought not accept the factuality of data as the sole criterion of objectivity, with all theory and instruments constrained by and focused on the passing ephemera of individual sets of local particularities. Properly defined and operationalized via a balanced interrelation of theory, data, and instrument, advanced measurement is not a mere mathematical exercise but offers a wealth of advantages and conveniences that cannot otherwise be obtained. We ignore its potentials at our peril.

References
Akkerman, S., Van den Bossche, P., Admiraal, W., Gijselaers, W., Segers, M., Simons, R.-J., et al. (2007, February). Reconsidering group cognition: From conceptual confusion to a boundary area between cognitive and socio-cultural perspectives? Educational Research Review, 2, 39-63.

Andersen, E. B. (1977). Sufficient statistics and latent trait models. Psychometrika, 42(1), 69-81.

Andersen, E. B. (1995). What George Rasch would have thought about this book. In G. H. Fischer & I. W. Molenaar (Eds.), Rasch models: Foundations, recent developments, and applications (pp. 383-390). New York: Springer-Verlag.

Andrich, D. (1989). Distinctions between assumptions and requirements in measurement in the social sciences. In J. A. Keats, R. Taft, R. A. Heath & S. H. Lovibond (Eds.), Mathematical and Theoretical Systems: Proceedings of the 24th International Congress of Psychology of the International Union of Psychological Science, Vol. 4 (pp. 7-16). North-Holland: Elsevier Science Publishers.

Andrich, D. (1997). Georg Rasch in his own words [excerpt from a 1979 interview]. Rasch Measurement Transactions, 11(1), 542-3. [http://www.rasch.org/rmt/rmt111.htm#Georg].

Andrich, D. (2002). Understanding resistance to the data-model relationship in Rasch’s paradigm: A reflection for the next generation. Journal of Applied Measurement, 3(3), 325-59.

Andrich, D. (2004, January). Controversy and the Rasch model: A characteristic of incompatible paradigms? Medical Care, 42(1), I-7–I-16.

Arnold, S. F. (1982-1988). Sufficient statistics. In S. Kotz, N. L. Johnson & C. B. Read (Eds.), Encyclopedia of Statistical Sciences (pp. 72-80). New York: John Wiley & Sons.

Arnold, S. F. (1985, September). Sufficiency and invariance. Statistics & Probability Letters, 3, 275-279.

Cohen, J. (1994). The earth is round (p < 0.05). American Psychologist, 49, 997-1003.

Davidoff, F. (1999, 15 June). Standing statistics right side up (Editorial). Annals of Internal Medicine, 130(12), 1019-1021.

Douglas, M. (1986). How institutions think. Syracuse, New York: Syracuse University Press.

Dynkin, E. B. (1951). Necessary and sufficient statistics for a family of probability distributions. Selected Translations in Mathematical Statistics and Probability, 1, 23-41.

Duncan, O. D. (1992, September). What if? Contemporary Sociology, 21(5), 667-668.

Duncan, O. D., & Stenbeck, M. (1988). Panels and cohorts: Design and model in the study of voting turnout. In C. C. Clogg (Ed.), Sociological Methodology 1988 (pp. 1-35). Washington, DC: American Sociological Association.

Embretson, S. E. (1996, September). Item Response Theory models and spurious interaction effects in factorial ANOVA designs. Applied Psychological Measurement, 20(3), 201-212.

Falmagne, J.-C., & Narens, L. (1983). Scales and meaningfulness of quantitative laws. Synthese, 55, 287-325.

Feinstein, A. R. (1995, January). Meta-analysis: Statistical alchemy for the 21st century. Journal of Clinical Epidemiology, 48(1), 71-79.

Fischer, G. H. (1981, March). On the existence and uniqueness of maximum-likelihood estimates in the Rasch model. Psychometrika, 46(1), 59-77.

Fisher, W. P., Jr. (2000). Objectivity in psychosocial measurement: What, why, how. Journal of Outcome Measurement, 4(2), 527-563.

Fisher, W. P., Jr. (2005). Daredevil barnstorming to the tipping point: New aspirations for the human sciences. Journal of Applied Measurement, 6(3), 173-9.

Fisher, W. P., Jr. (2009a). Bringing human, social, and natural capital to life: Practical consequences and opportunities. In M. Wilson, K. Draney, N. Brown & B. Duckor (Eds.), Advances in Rasch Measurement, Vol. Two (p. in press). Maple Grove, MN: JAM Press.

Fisher, W. P., Jr. (2009b, July). Invariance and traceability for measures of human, social, and natural capital: Theory and application. Measurement (Elsevier), in press.

Goodman, S. N. (1999a, 6 April). Probability at the bedside: The knowing of chances or the chances of knowing? (Editorial). Annals of Internal Medicine, 130(7), 604-6.

Goodman, S. N. (1999b, 15 June). Toward evidence-based medical statistics. 1: The p-value fallacy. Annals of Internal Medicine, 130(12), 995-1004.

Goodman, S. N. (1999c, 15 June). Toward evidence-based medical statistics. 2: The Bayes factor. Annals of Internal Medicine, 130(12), 1005-1013.

Guttman, L. (1981). What is not what in theory construction. In I. Borg (Ed.), Multidimensional data representations: When & why. Ann Arbor, MI: Mathesis Press.

Guttman, L. (1985). The illogic of statistical inference for cumulative science. Applied Stochastic Models and Data Analysis, 1, 3-10.

Hall, W. J., Wijsman, R. A., & Ghosh, J. K. (1965). The relationship between sufficiency and invariance with applications in sequential analysis. Annals of Mathematical Statistics, 36, 575-614.

Hammersley, M. (1989). The dilemma of qualitative method: Herbert Blumer and the Chicago Tradition. New York: Routledge.

Hutchins, E. (1995). Cognition in the wild. Cambridge, Massachusetts: MIT Press.

Latour, B. (1987). Science in action: How to follow scientists and engineers through society. New York: Cambridge University Press.

Latour, B. (1995). Cogito ergo sumus! Or psychology swept inside out by the fresh air of the upper deck: Review of Hutchins’ Cognition in the Wild, MIT Press, 1995. Mind, Culture, and Activity: An International Journal, 3(192), 54-63.

Latour, B. (2005). Reassembling the social: An introduction to Actor-Network-Theory. (Clarendon Lectures in Management Studies). Oxford, England: Oxford University Press.

Luce, R. D. (1978, March). Dimensionally invariant numerical laws correspond to meaningful qualitative relations. Philosophy of Science, 45, 1-16.

Magnus, P. D. (2007). Distributed cognition and the task of science. Social Studies of Science, 37(2), 297-310.

Marcus-Roberts, H., & Roberts, F. S. (1987). Meaningless statistics. Journal of Educational Statistics, 12(4), 383-394.

Meehl, P. E. (1967). Theory-testing in psychology and physics: A methodological paradox. Philosophy of Science, 34(2), 103-115.

Michell, J. (1986). Measurement scales and statistics: A clash of paradigms. Psychological Bulletin, 100, 398-407.

Mundy, B. (1986, June). On the general theory of meaningful representation. Synthese, 67(3), 391-437.

Narens, L. (2002, December). A meaningful justification for the representational theory of measurement. Journal of Mathematical Psychology, 46(6), 746-68.

Rasch, G. (1960). Probabilistic models for some intelligence and attainment tests (Reprint, with Foreword and Afterword by B. D. Wright, Chicago: University of Chicago Press, 1980). Copenhagen, Denmark: Danmarks Paedogogiske Institut.

Rasch, G. (1977). On specific objectivity: An attempt at formalizing the request for generality and validity of scientific statements. Danish Yearbook of Philosophy, 14, 58-94.

Roberts, F. S. (1999). Meaningless statements. In R. Graham, J. Kratochvil, J. Nesetril & F. Roberts (Eds.), Contemporary trends in discrete mathematics, DIMACS Series, Volume 49 (pp. 257-274). Providence, RI: American Mathematical Society.

Rogosa, D. (1987). Casual [sic] models do not support scientific conclusions: A comment in support of Freedman. Journal of Educational Statistics, 12(2), 185-95.

Romanoski, J. T., & Douglas, G. (2002). Rasch-transformed raw scores and two-way ANOVA: A simulation analysis. Journal of Applied Measurement, 3(4), 421-430.

Stevens, S. S. (1951). Mathematics, measurement, and psychophysics. In S. S. Stevens (Ed.), Handbook of experimental psychology (pp. 1-49). New York: John Wiley & Sons.

Surowiecki, J. (2004). The wisdom of crowds: Why the many are smarter than the few and how collective wisdom shapes business, economies, societies and nations. New York: Doubleday.

van der Linden, W. J. (1992). Sufficient and necessary statistics. Rasch Measurement Transactions, 6(3), 231 [http://www.rasch.org/rmt/rmt63d.htm].

Whitehead, A. N. (1925). Science and the modern world. New York: Macmillan.

Wise, M. N. (Ed.). (1995). The values of precision. Princeton, New Jersey: Princeton University Press.

Wright, B. D. (1980). Foreword, Afterword. In Probabilistic models for some intelligence and attainment tests, by Georg Rasch (pp. ix-xix, 185-199. http://www.rasch.org/memo63.htm) [Reprint; original work published in 1960 by the Danish Institute for Educational Research]. Chicago, Illinois: University of Chicago Press.

Creative Commons License
LivingCapitalMetrics Blog by William P. Fisher, Jr., Ph.D. is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.
Based on a work at livingcapitalmetrics.wordpress.com.
Permissions beyond the scope of this license may be available at http://www.livingcapitalmetrics.com.