Measurement myths and misconceptions.

Goodwin, Laura D.; Goodwin, William L.

doi:10.1037/h0089017

Cited by 61 publications

(34 citation statements)

References 77 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We desired a minimum alpha of .65 for every scale in each data set. Although .70 is widely considered a cutoff point for acceptable internal consistency (George & Mallery, 2003;Nunnally, 1978), this cutoff point has also been criticized as arbitrary (e.g., Goodwin & Goodwin, 1999;Knapp & Brown, 1995). Because several scales were multidimensional, as described later, we were concerned that requiring this standard across multiple data sets might unnecessarily limit the conceptual breadth of the short scales.…”

Section: Methodsmentioning

confidence: 98%

Development and Assessment of Short and Very Short Forms of the Infant Behavior Questionnaire–Revised

Putnam

Helbig

Gartstein

et al. 2013

Journal of Personality Assessment

449

463

View full text Add to dashboard Cite

Using data from parents of 761 infants from 6 independent samples, short (91 items, 14 scales) and very short (37 items, 3 broad scales) forms of the Infant Behavior Questionnaire-Revised (IBQ-R), a well-established caregiver report measure of temperament for infants aged 3 to 12 months, were developed. The forms were subsequently evaluated with data from 1,619 participants from 11 samples. Over 90% of Cronbach's alphas and part-whole correlations calculated for the short and very short form scales were greater than.70. Interparent agreement was nearly identical to that obtained with standard IBQ-R scales, averaging.41 and ranging from.06 to.76. Longitudinal stability over multiple time spans, and estimated retest reliability of the short form scales, were highly similar to those of standard forms, with estimated retest reliability averaging.72 and ranging from.54 to.93. Convergent and predictive validity of select short form scales were comparable to, but slightly lower, than those observed for standard IBQ-R scales. Recommendations for the use of the standard, short, and very short scales are discussed.

show abstract

Section: Methodsmentioning

confidence: 98%

Development and Assessment of Short and Very Short Forms of the Infant Behavior Questionnaire–Revised

Putnam

Helbig

Gartstein

et al. 2013

Journal of Personality Assessment

449

463

View full text Add to dashboard Cite

show abstract

“…Similarly, linear transformations of scores (such as converting raw scores to z scores) will not change the correlation between those data and another variable. A second common misconception is that sample size (N) has a direct relationship to the size of r-a misconception that often results in erroneous interpretations of reliability and validity coefficients (Goodwin & Goodwin, 1999). Although small samples can result in unstable or inaccurate results (Hinkle, Wiersma, & Jurs, 2003), the size of N itself has no direct bearing on the size of the calculated value of r.…”

Section: Discussionmentioning

confidence: 99%

Understanding Correlation: Factors That Affect the Size of r

Goodwin

Leech

2006

The Journal of Experimental Education

Self Cite

386

278

View full text Add to dashboard Cite

ABSTRACT. The authors describe and illustrate 6 factors that affect the size of a Pearson correlation: (a) the amount of variability in the data, (b) differences in the shapes of the 2 distributions, (c) lack of linearity, (d) the presence of 1 or more "outliers," (e) characteristics of the sample, and (f) measurement error. Also discussed are ways to determine whether these factors are likely affecting the correlation, as well as ways to estimate the size of the influence or reduce the influence of each. Key words: correlation, errors, interpretation, Pearson product-moment correlationCORRELATION IS A COMMONLY USED STATISTIC in research and measurement studies, including studies conducted to obtain validity and reliability evidence. Understanding the meaning of a simple correlation is key to understanding more complex statistical techniques for which the simple correlation is the foundation. In basic statistics courses, students typically learn about the conceptual meaning of "relationship" between two variables (including size and direction), how to calculate and interpret a sample correlation, how to construct scattergrams or scatterplots to graphically display the relationship, and how to conduct an inferential test for the significance of the correlation and interpret the results. What is often missing in class discussions and activities, however, is a focus on factors that can affect the size of the statistic based on the characteristics of the correlation or the particular dataset used for the calculation of the correlation. Without a solid understanding of these factors, students and researchers

show abstract

“…Interrater reliability was measured using a correlation coefficient as well as percent agreement (Jackson, 2009). Estimates for weak, moderate, and strong correlation coefficients are as follows: .00 to .29 is considered weak, .30 to .69 is considered moderate, and .70 to 1.0 is considered strong (Jackson, 2009 Reliability estimates are a function of the type of measurement being assessed and no definitive or objective cut off point exists for these estimates, only commonly accepted or used values (e.g., Goodwin & Goodwin, 1999;Knapp & Brown, 1995). The interrater reliability estimates reported in the present study are in alignment with commonly used classroom observation assessments in the field.…”

Section: Css Evidence Of Reliabilitymentioning

confidence: 99%

Development and construct validity of the Classroom Strategies Scale-Observer Form.

Reddy¹,

Fabiano²,

Dudek³

et al. 2013

School Psychology Quarterly

View full text Add to dashboard Cite

Research on progress monitoring has almost exclusively focused on student behavior and not on teacher practices. This article presents the development and validation of a new teacher observational assessment (Classroom Strategies Scale) of classroom instructional and behavioral management practices. The theoretical underpinnings and empirical basis for the instructional and behavioral management scales are presented. The Classroom Strategies Scale (CSS) evidenced overall good reliability estimates including internal consistency, interrater reliability, test-retest reliability, and freedom from item bias on important teacher demographics (age, educational degree, years of teaching experience). Confirmatory factor analyses (CFAs) of CSS data from 317 classrooms were carried out to assess the level of empirical support for (a) a 4 first-order factor theory concerning teachers' instructional practices, and (b) a 4 first-order factor theory concerning teachers' behavior management practice. Several fit indices indicated acceptable fit of the (a) and (b) CFA models to the data, as well as acceptable fit of less parsimonious alternative CFA models that included 1 or 2 second-order factors. Information-theory-based indices generally suggested that the (a) and (b) CFA models fit better than some more parsimonious alternative CFA models that included constraints on relations of first-order factors. Overall, CFA first-order and higher order factor results support the CSS-Observer Total, Composite, and subscales. Suggestions for future measurement development efforts are outlined.

show abstract

Measurement myths and misconceptions.

Cited by 61 publications

References 77 publications

Development and Assessment of Short and Very Short Forms of the Infant Behavior Questionnaire–Revised

Development and Assessment of Short and Very Short Forms of the Infant Behavior Questionnaire–Revised

Understanding Correlation: Factors That Affect the Size of r

Development and construct validity of the Classroom Strategies Scale-Observer Form.

Contact Info

Product

Resources

About