scholarly journals Survey Satisficing Inflates Reliability and Validity Measures

2016 ◽  
Vol 76 (6) ◽  
pp. 912-932 ◽  
Author(s):  
Tyler Hamby ◽  
Wyn Taylor

This study examined the predictors and psychometric outcomes of survey satisficing, wherein respondents provide quick, “good enough” answers (satisficing) rather than carefully considered answers (optimizing). We administered surveys to university students and respondents—half of whom held college degrees—from a for-pay survey website, and we used an experimental method to randomly assign the participants to survey formats, which presumably differed in task difficulty. Based on satisficing theory, we predicted that ability, motivation, and task difficulty would predict satisficing behavior and that satisficing would artificially inflate internal consistency reliability and both convergent and discriminant validity correlations. Indeed, results indicated effects for task difficulty and motivation in predicting survey satisficing, and satisficing in the first part of the study was associated with improved internal consistency reliability and convergent validity but also worse discriminant validity in the second part of the study. Implications for research designs and improvements are discussed.

2019 ◽  
Vol 47 (3) ◽  
pp. 1154-1168 ◽  
Author(s):  
Xiaoqian Chen ◽  
Qi Yu ◽  
Feifei Yu ◽  
Yixiang Huang ◽  
Lingling Zhang

Objective This study was performed to assess the reliability and validity of the Chinese version of the Snizek-revised Hall’s Professionalism Inventory Scale (C-SR-HPIS). Methods Exploratory factor analysis and confirmatory factor analysis were used to evaluate the construct validity of the C-SR-HPIS. The average variance extracted (AVE) and square root of the AVE were calculated and correlation analyses were performed to test the convergent validity and discriminant validity, respectively. Cronbach’s alpha (α) coefficient was used to test the internal consistency reliability. Results Data for 355 clinical nurses in mainland China were collected. Five factors were extracted, accounting for 58.86% of the total explained variance, and 20 items were selected for the C-SR-HPIS. The confirmatory factor analysis suggested good fitness of the modified model. The AVE was acceptable for convergent validity. The square roots of the AVE of the five factors were larger than their correlation coefficients with other factors, showing suitable discriminant validity. Cronbach’s α coefficient of internal consistency reliability of the overall scale was 0.76, indicating good reliability of the scale. Conclusions This study demonstrated good reliability and validity of the C-SR-HPIS and provides a quantitative tool for the assessment of nursing professionalism in China.


2019 ◽  
Vol 56 (2) ◽  
pp. 376-382
Author(s):  
Eklund Mona ◽  
Neil Sandra ◽  
Argentzell Elisabeth

Abstract The aim was to develop a short version of the Swedish Process of Recovery Questionnaire (QPR-Swe) for use with people with severe mental illness and to investigate its internal consistency, construct validity, known-groups validity and any floor or ceiling effects. Two independent samples were used, the first (N = 226) to develop the short version and the second (N = 266) to test its psychometric properties. A seven-item version was developed by selecting items based on item-total correlations. The QPR-Swe-7 showed good internal consistency reliability (α = 0.82). It showed moderate correlations with indicators of convergent validity (self-rated health, self-mastery and quality of life) and weak with those selected to test discriminant validity (psychiatric symptoms and level of functioning). QPR-Swe-7 differentiated between people receiving two different levels of housing support. No floor or ceiling effects were found. The QPR-Swe-7 had appropriate psychometric properties for use with people with a variety of mental disorders when a brief scale is warranted.


2018 ◽  
Vol 36 (34_suppl) ◽  
pp. 151-151
Author(s):  
Laura M Perry ◽  
Adina S Kazan ◽  
James Louis Rogers ◽  
Michael Hoerger

151 Background: Research has not thoroughly examined patient-level factors such as perceptions that could contribute to underutilization of palliative care, which may be due in part to a lack of existing measures for this purpose. Therefore, this investigation aimed to develop and validate a 9-item measure called the Palliative Care Preferences Scale (PCPS-9), which was comprised of three subscales: emotional, cognitive, and behavioral. Methods: Data were collected in three separate online studies of individuals with cancer (study 1: N = 633; study 2: N = 462) or one of the following non-cancer serious illnesses: COPD, heart failure, or kidney failure (study 3: N = 248). Analyses assessed various psychometric properties of the scale in cancer and non-cancer patients, including internal consistency reliability, confirmatory factor analyses (CFAs), multigroup CFAs, and convergent validity associations with related constructs. Results: Across all three studies, results supported the internal consistency reliability for the total scale (αs from 0.76 to 0.83) and subscales: emotional (αs from 0.83 to 0.84), cognitive (αs from 0.60 to 0.77), behavioral (αs from 0.87 to 0.91). CFAs supported the three-factor model of the PCPS-9 (CFI ≥ 0.97, NNFI ≥ 0.96, RMSEA ≤ 0.07, SRMR ≤ 0.04), and a multigroup CFA supported the generalizability of its factor structure across cancer and non-cancer serious illness subgroups (ΔCFIs ≤ 0.006, ΔRMSEA ≤ 0.003). Finally, convergent validity analyses in studies 2 and 3 found that the PCPS-9 was significantly associated with related constructs, including a separate measure of palliative care preferences ( ps < 0.001) and a measure of palliative care knowledge ( ps < 0.001). Conclusions: Findings support the overall reliability and validity of the PCPS-9 in cancer and non-cancer serious illness samples and have implications for increasing palliative care utilization via clinical care and future research efforts.


2021 ◽  
Vol 45 (2) ◽  
pp. 342-351
Author(s):  
Kelli J. England ◽  
Paul T. Harrell ◽  
Kaitlyn A. Mondejar ◽  
Amy C. Paulson ◽  
Ann L. Edwards ◽  
...  

Objectives: Adolescent use of electronic cigarettes has risen dramatically, prompting concerns about the health effects. There is need for brief measures to assess adolescents' perceived threat and efficacy related to e-cigarette use and cessation. A 12-item Likert-type scale was modeled after the Risk Behavior Diagnosis Scale and designed to assess threat (ie, severity and susceptibility of threat) and efficacy (ie, self-efficacy and response efficacy) as they relate to e-cigarette use. Methods: The scale was administered online to a developmental sample of 674 adolescents to examine internal consistency and factor structure. Participants (52.1% female, M age = 14.6) were representative of the surrounding community (60% non-Hispanic white; 27% non-Hispanic black; 8% Hispanic). Results: Factor analysis and Velicer's minimum average partial test revealed 2 factors (as expected), which explained 68% of the variance. Analyses revealed strong internal consistency, with Cronbach's alpha of .93 overall and alphas of .92 and .87 for threat and efficacy subscales, respectively. The measure also exhibited good convergent and discriminant validity with other constructs. Conclusions: The measure demonstrates strong preliminary reliability and validity for a developmental sample of adolescents.


1994 ◽  
Vol 18 (3) ◽  
pp. 389-402 ◽  
Author(s):  
Ruth E. Fassinger

This article outlines the development and testing of the Attitudes Toward Feminism and the Women's Movement (FWM) Scale, a brief measure of affective attitudes toward the feminist movement. Thurstone's (1959) method of equal-appearing intervals was used initially to create the final 10-item summated rating (Likert) scale. Establishment of internal consistency reliability and construct (convergent and discriminant) validity was determined on a sample of 117 female and male college students. Results suggested a highly internally consistent and valid attitudinal measure. Additional evidence for the validity of the FWM is discussed in terms of research in which it has been successfully used.


Healthcare ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1587
Author(s):  
Aya Kondou ◽  
Mari Haku ◽  
Toshiyuki Yasui

The mental health of fathers influences the development of children and the functioning of families significantly. However, there is no useful scale for the mental health screening of childrearing fathers. This study developed a Mental Health Scale for Childrearing Fathers (MSCF) and determined its reliability and validity. Childrearing fathers are working fathers who co-parent with their spouses. This survey was conducted in two stages: a pilot study and a main survey. Data were obtained from 98 fathers raising preschoolers in the pilot study and 306 fathers in the main survey. The collected data were used to confirm the construct validity, criterion-related validity, convergent validity, and internal consistency reliability. The final MSCF consisted of 25 items comprising four factors: peaceful familial connection, healthy mind and body, satisfying paternal alliances, and leading a meaningful life as a parent. The internal consistency reliability estimated using Cronbach’s alpha coefficient for the total scale was 0.918. The validity of the MSCF was logically secured using a confirmatory factor analysis. The MSCF can be an effective tool for mental health screening among fathers in relation to the burden of childrearing during regular infant health checks.


2017 ◽  
Vol 69 (1) ◽  
pp. 64-75 ◽  
Author(s):  
Ruchi Jain Garg ◽  
Vinod Kumar ◽  
Vandana

Purpose The purpose of this paper is to develop and validate a scale involving the factors affecting usage of e-resources. Design/methodology/approach The present study identifies five factors affecting the usage of e-resources: training modes, awareness, influencers, utilitarian benefits, and experiential and hedonic benefits. To generate measurement items, two focus group discussions were carried out which resulted in 20 items. To empirically ensure reliability and validity of scale, data were collected from 347 postgraduate students actively using e-resources. To test reliability of scale, internal consistency reliability and construct reliability were examined. The construct validity of scale (which includes convergent validity and discriminant validity) was verified through confirmatory factor analysis using structure equation modeling. Findings Findings of the study present a statistically reliable and valid scale consisting of five factors and 18 items. Originality/value The present study is one of the distinctive studies on introducing a scale employing factors affecting usage of e-resources.


Author(s):  
Inmaculada-Concepción Jemes-Campaña ◽  
Rita-Pilar Romero-Galisteo ◽  
María-Teresa Labajos-Manzanares ◽  
Pablo Gálvez-Ruiz ◽  
Noelia Moreno-Morales

Evaluating the service quality in early intervention (EI) from the perspective of professionals with knowledge in this area is essential for the improvement of EI centres. In this study, we aimed to test the reliability and validity of the adapted Inventory of Quality in Early Intervention Centres-P (IQEIC-P) in a sample of professionals who worked in EI centres. Three hundred and twenty-four professionals of 85 EI Spanish centres were recruited for this research. Various psychometric analyses were used to evaluate the factorial structure, the internal consistency, factorial validity and construct validity. A 5-dimension structure was obtained in the exploratory factor analysis (EFA). The results showed an adequate internal consistency (Cronbach’s alpha values between 0.71 and 0.83, and composite reliability (CR) values higher than 0.70), as well as satisfactory convergent and discriminant validity (average variance extracted (AVE) values above 0.50). In the confirmatory factor analysis, good model fit indicators were observed. The IQEIC-P showed adequate psychometric properties, demonstrating to be a valid instrument for the evaluation of service quality in EI centres from the perspective of professionals. The benefits will influence the professionals themselves, and they will have a positive and direct impact on the families that are attended to in these centres.


2018 ◽  
Vol 43 (4) ◽  
pp. 213-221
Author(s):  
Elena Castarlenas ◽  
Ester Solé ◽  
Santiago Galán ◽  
Mélanie Racine ◽  
Mark P. Jensen ◽  
...  

The purpose of this study was to evaluate the construct validity and reliability of the Catalan version of the Pain Self-Efficacy Questionnaire (PSEQ) in a sample of young people with chronic pain. Two hundred twenty-seven young people with chronic pain (age range = 12–24 years, mean age = 17.87 years, SD = 3.08 years) participated in this study. The findings support a one-factor structure of the PSEQ, and the scale demonstrated excellent internal consistency reliability in our sample. In addition, convergent validity was supported by a loading of average variance extracted (AVE) greater than .50, and discriminant validity was supported by the finding that self-efficacy and pain-related anxiety AVEs were greater than the shared variance between both constructs. Further support for the measure’s construct validity was shown by (1) significant and positive associations between PSEQ scores and adaptive coping strategies and (2) negative and significant associations between PSEQ scores and maladaptive coping strategies and catastrophizing thoughts. The results of this study indicate that the Catalan version of the PSEQ is reliable and valid when used to assess pain self-efficacy beliefs in young people with chronic pain.


2015 ◽  
Vol 18 ◽  
Author(s):  
Wen Liu ◽  
Liang Chen ◽  
Ying Yang ◽  
Shuai Zhang

AbstractThis paper presents a Chinese adaption of the Formal Characteristics of the Behavior-Temperament Inventory (FCB-TI), a self-report instrument that evaluates six temperamental scales, based on Strelau’s concept of temperament. A first sample of 626 undergraduates completed the Chinese version of the Regulative Theory of Temperament Questionnaire (RTTQ), which is an initial pool of 381 items. Internal consistency suggests adequate reliability (.66 to .82), and an exploratory factor analysis revealed a six-factor solution consistent with the original instrument. A follow-up confirmatory factor analysis revealed good support for the temperament structure with a second sample of students (N = 2.980). Internal consistency and factorial structure were re-examined (Cronbach’s alpha ranged .64 to .85), and test-retest correlations over a two-week period ranged from .82 to .96 with a third sample of adults (N = 2.265). Convergent and discriminant validity was explored in relation to the Eysenck Personality Questionnaire-Revision Short Scale for Chinese (EPQ-RSC) model dimensions. Results indicate that the Chinese version of the FCB-TI has similar psychometric properties and generally satisfactory reliability and validity.


Sign in / Sign up

Export Citation Format

Share Document