Does statistical language constitute a "significant" roadblock to readers' interpretations of research results?

Robinson, Daniel H.; Levin, Joel R.; O'Ryan, Leslie; Halbur-Ramseyer, Duane

doi:10.1037/0022-0663.93.3.646

Cited by 4 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers can help to alleviate this problem by avoiding use of confusing terminology. For example, rather than describing results as "boys scored significantly higher than girls, p Ͻ .05," authors could simply say, "on average, boys scored higher than girls, p Ͻ .05" (Robinson, Levin, Halbur, & O'Ryan, 2001).…”

Section: What If P = 06?mentioning

confidence: 99%

Shaping Up the Practice of Null Hypothesis Significance Testing

Wainer

Robinson

2003

Educational Researcher

Self Cite

View full text Add to dashboard Cite

Recent criticisms of null hypothesis significance testing (NHST) have appeared in education and psychology research journals (e.g., Cohen, 1990 , 1994 ; Kupfersmid, 1988 ; Rosenthal, 1991 ; Rosnow & Rosenthal, 1989; Shaver, 1985 ; Sohn, 2000 ; Thompson, 1994 , 1997 ; see also Research in the Schools [1998]). In this article we discuss these criticisms for both current use of NHST and plausible future use. We suggest that the historical use of such procedures was reasonable and that current users might spend time profitably reading some of Fisher’s applied work. However, we also believe that modifications to NHST and to the interpretations of its outcomes might better suit the needs of modern science. Our primary conclusion is that NHST is most often useful as an adjunct to other results (e.g., effect sizes) rather than as a stand-alone result. We cite some examples, however, where NHST can be profitably used alone. Last, we find considerable experimental support for a less rigid attitude toward the interpretation of the probability yielded from such procedures.

show abstract

Section: What If P = 06?mentioning

confidence: 99%

Shaping Up the Practice of Null Hypothesis Significance Testing

Wainer

Robinson

2003

Educational Researcher

Self Cite

View full text Add to dashboard Cite

show abstract

“…There would be a serious problem had the percentages been very different (and hence statistically significant) because then one would have to further investigate the cause of the inconsistency and whether it was due to student or lecturer error or oversight. Even though the outcome for the ANOVA analysis was statistically insignificant, the results are by no means unimportant [24].…”

Section: Discussionmentioning

confidence: 93%

Student Perceptions of Problem-Based Learning: A Case Study of Undergraduate Applied Agrometeorology

Wet

Walker

2013

ISRN Education

View full text Add to dashboard Cite

Many students do not seem to transfer their learning during formal education into applications in the real world. The objective of this ongoing study was to investigate the opinion of third-year students concerning their program through problem-based learning and to improve the module where necessary. Students attending theory classes had to apply their newly gained knowledge coupled with real-life weather data to solve a problem during practicums. Students attending practicums were given the same questionnaire thrice; thus, the answers were based on different sets of exercises. Responses by attendees for the three questionnaires were 73%, 100%, and 61%, respectively. Students preferred problem-based practicums (78%, 54%, and 72%, resp.) to other non-problem-based practicums. Most students thought that their knowledge had improved and it had prepared them better for the workplace (85%, 77%, and 92%, resp.). Generally students preferred working in groups (74%, 62%, and 56%, resp.), in contrast to those preferring to work individually. Students benefited from problem-based learning in that they thought they had improved their knowledge, skills, and critical thinking abilities and felt that they had learnt things that they could carry into their future lives out in the world at large and the workplace.

show abstract

“…In the present study, we examined the impact of two other editorial policies. Robinson et al (2001) recommended that rather than referring to statistically significant results as significant, statistically significant, or statistical, authors would perhaps do best to avoid the language issue and simply use phrases like "there was a main effect for group" when there is evidence of the sign of that effect, and stake no claim when the sign of that effect is indefinite or not yet determined (Tukey, 1960). When researchers consider effect size information, perhaps it would be best to simply provide sufficient statistics (so that an effect size can be calculated) and let an expert decide whether the results are important or impressive in a practical context.…”

Section: Discussionmentioning

confidence: 97%

“…We have previously examined what language should be used to describe statistically significant results (Robinson, Levin, Halbur, & O'Ryan, 2001) and whether an alpha of .05 should be used (Robinson, Funk, Halbur, & O'Ryan, in press). In the present study, we examined the impact of two other editorial policies.…”

Section: Discussionmentioning

confidence: 99%