Making Meaning out of MANOVA: The Need for Multivariate Post Hoc Testing in Gifted Education Research

Multivariate analysis of variance (MANOVA) is a statistical method used to examine group differences on multiple outcomes. This article reports results of a review of MANOVA in gifted education journals between 2011 and 2017 ( N = 56). Findings suggest a number of conceptual and procedural misunderstandings about the nature of MANOVA and its application, including pervasive use of univariate post hoc tests to interpret MANOVA results. Accordingly, this article aims to make MANOVA more accessible to gifted education scholars by clarifying its purpose and introducing descriptive discriminant analysis as a more appropriate post hoc technique. A heuristic data set is used to demonstrate the procedures for running a descriptive discriminant analysis, both in place of a one-way MANOVA and as a post hoc analysis to a factorial design. SPSS and R syntax are provided.

Download Full-text

Outcome Variables that Contribute to Group Differences Between Caucasians, African Americans, and Asian Americans who are Deaf

Journal of Applied Rehabilitation Counseling ◽

10.1891/0047-2220.33.2.8 ◽

2002 ◽

Vol 33 (2) ◽

pp. 8-12 ◽

Cited By ~ 6

Author(s):

Corey L. Moore

Keyword(s):

Multivariate Analysis ◽

Discriminant Analysis ◽

African Americans ◽

Analysis Of Variance ◽

Asian Americans ◽

Fiscal Year ◽

Group Differences ◽

Multivariate Analysis Of Variance ◽

Research And Practice ◽

Post Hoc

The purpose of this research was to identify those dimensions of outcome variables (i.e., number of VR services provided, cost of case services, income, and number of hours worked at closure) that make the greatest contribution to group differences between Caucasians, African Americans, and Asian Americans who are deaf. Multivariate analysis of variance (MANOVA) and post hoc descriptive discriminant analysis (DDA) were utilized to evaluate 1,108 case records obtained from the RSA-911 database for fiscal year 1997. DDA results indicated that African-Americans were provided with significantly more VR services and achieved significantly lower levels of income when compared to Caucasians and Asian Americans. Results are presented for the discriminating variables and the implications of findings for research and practice are discussed.

Download Full-text

Response-Specific Scalp Distributions in Deception Detection and ERP Correlates of Psychopathic Personality Traits

Journal of Psychophysiology ◽

10.1027/0269-8803.18.1.13 ◽

2004 ◽

Vol 18 (1) ◽

pp. 13-26 ◽

Cited By ~ 13

Author(s):

Antoinette R. Miller ◽

J. Peter Rosenfeld

Keyword(s):

Deception Detection ◽

Event Related Potential ◽

Psychopathic Personality ◽

P300 Amplitude ◽

Group Differences ◽

Post Hoc Analysis ◽

P300 Component ◽

Psychopathic Personality Inventory ◽

Post Hoc ◽

First Time

Abstract University students were screened using items from the Psychopathic Personality Inventory and divided into high (n = 13) and low (n = 11) Psychopathic Personality Trait (PPT) groups. The P300 component of the event-related potential (ERP) was recorded as each group completed a two-block autobiographical oddball task, responding honestly during the first (Phone) block, in which oddball items were participants' home phone numbers, and then feigning amnesia in response to approximately 50% of items in the second (Birthday) block in which oddball items were participants' birthdates. Bootstrapping of peak-to-peak amplitudes correctly identified 100% of low PPT and 92% of high PPT participants as having intact recognition. Both groups demonstrated malingering-related P300 amplitude reduction. For the first time, P300 amplitude and topography differences were observed between honest and deceptive responses to Birthday items. No main between-group P300 effects resulted. Post-hoc analysis revealed between-group differences in a frontally located post-P300 component. Honest responses were associated with late frontal amplitudes larger than deceptive responses at frontal sites in the low PPT group only.

Download Full-text

Cochran’s Q with Pairwise McNemar for Dichotomous Multiple Responses Data: a Practical Approach

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i3.18.16662 ◽

2018 ◽

Vol 7 (3.18) ◽

pp. 4

Author(s):

Donald Stephen ◽

Shahren Ahmad Zaidi Adruce

Keyword(s):

Simulated Data ◽

Bonferroni Correction ◽

Deductive Verification ◽

Multiple Responses ◽

Data Set ◽

Post Hoc Analysis ◽

Mcnemar Test ◽

Exact Difference ◽

Single Response ◽

Post Hoc

When utilizing single-response questions for a survey, researchers often overlook the possibility that an item can have a smorgasbord of viable answers. It results in the loss of information as it forces the respondents to select a best-of-fit option. A multiple-responses question allows the respondent to select any number of answers from a set of preformatted options. The ability to capture a flexible number of responses allows collectively exhaustive concepts to manifest for deductive verification. This paper explores the practical use of Cochran’s Q test and pairwise McNemar test to examine the proportion of responses derived from the results of Multiple Responses Analysis (MRA). This includes Cochran’s Q operation on MRA data table using a simulated data set. Cochran’s Q test detects if there is a difference in the proportion of multiple concepts. In the case of a significant result, it would require a post hoc analysis to pinpoint the exact difference in pairwise proportions. This pairwise difference can be detected by utilizing pairwise McNemar test with Bonferroni Correction. This paper serves as a reference for researchers and practitioners who need to examine the proportion of collectively exhaustive concepts collected from a multiple responses item.

Download Full-text

Attitudes of Physical Educators Toward Teaching Handicapped Pupils

Adapted Physical Activity Quarterly ◽

10.1123/apaq.1.4.267 ◽

1984 ◽

Vol 1 (4) ◽

pp. 267-274 ◽

Cited By ~ 34

Author(s):

Terry L. Rizzo

Keyword(s):

Factorial Design ◽

Teacher Attitudes ◽

Grade Level ◽

Survey Instrument ◽

Physical Educators ◽

Post Hoc Analysis ◽

Regular Class ◽

Attitudes Toward Teaching ◽

Post Hoc

This study assessed the attitudes of physical educators (n = 194) toward teaching handicapped pupils in the regular class. The survey instrument used was the Physical Educators Attitude Toward Teaching the Handicapped (PEATH), which assesses teacher attitudes according to the type of handicapping condition (learning and physical) and grade level (K-3, 4-6, 7-8). A 2 × 3 randomized block factorial design and the Tukey (HSD) post hoc analysis were applied to the data. Results indicated that physical educators held more favorable attitudes toward teaching pupils with learning handicaps than those with physical handicaps. Furthermore, as grade level advanced from primary (K-3) to intermediate (4-6) and upper (7-8) grades, teacher attitudes became progressively less favorable.

Download Full-text

Comparative Study of Static, Dynamic, and Proprioceptive Neuromuscular Facilitation Stretching Techniques on Flexibility

Perceptual and Motor Skills ◽

10.2466/pms.1984.58.2.615 ◽

1984 ◽

Vol 58 (2) ◽

pp. 615-618 ◽

Cited By ~ 31

Author(s):

Ranna C. Lucas ◽

Robert Koslow

Keyword(s):

Comparative Study ◽

Factorial Design ◽

College Women ◽

Group Factor ◽

Treatment Groups ◽

Post Hoc Analysis ◽

Proprioceptive Neuromuscular Facilitation ◽

Flexibility Training ◽

Gastrocnemius Muscles ◽

Post Hoc

63 college women served as subjects in this 7-wk. study examining the effects of static, dynamic, and proprioceptive neuromuscular facilitating stretching techniques on the flexibility of the hamstring-gastrocnemius muscles. Subjects were assigned to one of the 3 treatment groups and received treatment 3 days a week. A pretest, a midtest (after 11 treatment days), and a posttest (after 21 treatment days) were administered. Analysis of group and test effects was accomplished by using a 3 × 3 factorial design with the group factor nested and the test factor crossed. Post hoc analysis indicated that all scores significantly improved from pretest to posttest. The findings indicated all 3 methods of flexibility training produced significant improvements when pretest and posttest mean scores were compared.

Download Full-text