2.50
Hdl Handle:
http://hdl.handle.net/10755/158120
Type:
Presentation
Title:
Validation of Likert Scaling Preferences in an Ethnic Sample
Abstract:
Validation of Likert Scaling Preferences in an Ethnic Sample
Conference Sponsor:Western Institute of Nursing
Conference Year:2004
Author:Tse, Alice, PhD, APRN
P.I. Institution Name:University of HI at Manoa , Kapiolani Med. Ctr
Contact Address:Room 719, 1319 Punahou Stl, , Honolulu, HI , 96826, USA
Co-Authors:Donna-Marie Palakiko, MS, RN
Purpose/Aims: The traditional western-style 5-point Likert-type response option was compared against other alternative response formats for cultural preference and to determine if other response options demonstrate a better fit with the respondents’ perspectives. Empirical substantiation of preferences for response formats are needed for the design of response formats with Native Hawaiians. Four questions were investigated by means of a pilot study: (1) What response format is the easiest to fill out? (2) What is the preferred response format? (3) What are reasons given for the response preferences? (4) Are respondents willing to use the 5-point Likert format? Response formats included 2-point, 3-point and 5-point options. Rationale/Conceptual Basis/Background: This pilot study is a methodological investigation to assess the preferences for responding to Likert-type scales by Native Hawaiian respondents. Several investigators have suggested that use of the traditional 5-point Likert scale is challenging and not preferred, although empirical evidence does not exist to support this contention. Some ethnic researchers have shied away from the traditional 5-point response options in favor of a 3-point response scale. It is suggested that Hawaiian words demonstrate a stronger cultural fit. Methods: The design is descriptive with four response choices (2-point, 3-point, 5-point and graphical response formats) and 7 age groups [ages 6-12 (n=24), 13-21 (n=22), 22-40 (n=17), 41-65 (n=19), and 66-90 (n=18) years]. Stratified quota sampling was used to obtain participants per age strata; participants were recruited from both rural and urban communities. The inclusion criteria consist of anyone who self-declares as Native Hawaiian; health status did not matter because we wanted to sample the general population. Results: Differences are noted in preference for response format among the age groups (X2=41.4, df=18, p<.001). Individuals < age 14 years preferred the 3-point format with native Hawaiian words/graphics images; over 50% in this group did not prefer using a 5-point format. Themes noted were display of cultural identify and ease of answering. Individuals aged 15-40 years preferred the 2- and 3-point scales, disliked using the 5-point format, citing that the former was easier to comprehend. Individuals > age 40 years preferred the 5-point format; over 50% objected to the 3-point scales with native Hawaiian words and graphics images. They indicated that having more options was preferred so they would not have to select the extreme responses. Overall the 2-point format was rated as easiest to complete by 39% of respondents across all ages; themes noted are: simple, quick, fast, definitive, and familiarity with the wording. On the 5-point format, “agree-disagree” some reported reluctance to endorse items using the “agree-disagree” anchors because it is not good to show disagreement, although “good-bad” response anchors were more acceptable. However, when asked specifically, 90% of respondents across all age groups indicated that they would be willing to use the 5-point format. This is an important finding because researchers need to be sensitive of participants’ reluctance to respond to items that we are asking. Yet from a measurement perspective, 5-point response options are preferred to yield interval level dependent measures which allow for use of parametric procedures. Implications: Sensitivity in explaining the need to use a specific scaling format to participants will foster cooperation with study responses. Differences in the environments among data collection sites, age and education may account for respondent’s preferences. It is recommended in future studies to ask respondents directly how familiar they are with the scaling formats, comfort with these formats, familiarity and interpretation of the words used as anchors. Ultimately, methodological investigations are needed to determine whether other formats should be considered when working with ethnic groups.
Repository Posting Date:
26-Oct-2011
Date of Publication:
17-Oct-2011
Sponsors:
Western Institute of Nursing

Full metadata record

DC FieldValue Language
dc.typePresentationen_GB
dc.titleValidation of Likert Scaling Preferences in an Ethnic Sampleen_GB
dc.identifier.urihttp://hdl.handle.net/10755/158120-
dc.description.abstract<table><tr><td colspan="2" class="item-title">Validation of Likert Scaling Preferences in an Ethnic Sample</td></tr><tr class="item-sponsor"><td class="label">Conference Sponsor:</td><td class="value">Western Institute of Nursing</td></tr><tr class="item-year"><td class="label">Conference Year:</td><td class="value">2004</td></tr><tr class="item-author"><td class="label">Author:</td><td class="value">Tse, Alice, PhD, APRN</td></tr><tr class="item-institute"><td class="label">P.I. Institution Name:</td><td class="value">University of HI at Manoa , Kapiolani Med. Ctr</td></tr><tr class="item-address"><td class="label">Contact Address:</td><td class="value">Room 719, 1319 Punahou Stl, , Honolulu, HI , 96826, USA</td></tr><tr class="item-co-authors"><td class="label">Co-Authors:</td><td class="value">Donna-Marie Palakiko, MS, RN</td></tr><tr><td colspan="2" class="item-abstract">Purpose/Aims: The traditional western-style 5-point Likert-type response option was compared against other alternative response formats for cultural preference and to determine if other response options demonstrate a better fit with the respondents&rsquo; perspectives. Empirical substantiation of preferences for response formats are needed for the design of response formats with Native Hawaiians. Four questions were investigated by means of a pilot study: (1) What response format is the easiest to fill out? (2) What is the preferred response format? (3) What are reasons given for the response preferences? (4) Are respondents willing to use the 5-point Likert format? Response formats included 2-point, 3-point and 5-point options. Rationale/Conceptual Basis/Background: This pilot study is a methodological investigation to assess the preferences for responding to Likert-type scales by Native Hawaiian respondents. Several investigators have suggested that use of the traditional 5-point Likert scale is challenging and not preferred, although empirical evidence does not exist to support this contention. Some ethnic researchers have shied away from the traditional 5-point response options in favor of a 3-point response scale. It is suggested that Hawaiian words demonstrate a stronger cultural fit. Methods: The design is descriptive with four response choices (2-point, 3-point, 5-point and graphical response formats) and 7 age groups [ages 6-12 (n=24), 13-21 (n=22), 22-40 (n=17), 41-65 (n=19), and 66-90 (n=18) years]. Stratified quota sampling was used to obtain participants per age strata; participants were recruited from both rural and urban communities. The inclusion criteria consist of anyone who self-declares as Native Hawaiian; health status did not matter because we wanted to sample the general population. Results: Differences are noted in preference for response format among the age groups (X2=41.4, df=18, p&lt;.001). Individuals &lt; age 14 years preferred the 3-point format with native Hawaiian words/graphics images; over 50% in this group did not prefer using a 5-point format. Themes noted were display of cultural identify and ease of answering. Individuals aged 15-40 years preferred the 2- and 3-point scales, disliked using the 5-point format, citing that the former was easier to comprehend. Individuals &gt; age 40 years preferred the 5-point format; over 50% objected to the 3-point scales with native Hawaiian words and graphics images. They indicated that having more options was preferred so they would not have to select the extreme responses. Overall the 2-point format was rated as easiest to complete by 39% of respondents across all ages; themes noted are: simple, quick, fast, definitive, and familiarity with the wording. On the 5-point format, &ldquo;agree-disagree&rdquo; some reported reluctance to endorse items using the &ldquo;agree-disagree&rdquo; anchors because it is not good to show disagreement, although &ldquo;good-bad&rdquo; response anchors were more acceptable. However, when asked specifically, 90% of respondents across all age groups indicated that they would be willing to use the 5-point format. This is an important finding because researchers need to be sensitive of participants&rsquo; reluctance to respond to items that we are asking. Yet from a measurement perspective, 5-point response options are preferred to yield interval level dependent measures which allow for use of parametric procedures. Implications: Sensitivity in explaining the need to use a specific scaling format to participants will foster cooperation with study responses. Differences in the environments among data collection sites, age and education may account for respondent&rsquo;s preferences. It is recommended in future studies to ask respondents directly how familiar they are with the scaling formats, comfort with these formats, familiarity and interpretation of the words used as anchors. Ultimately, methodological investigations are needed to determine whether other formats should be considered when working with ethnic groups. </td></tr></table>en_GB
dc.date.available2011-10-26T20:31:45Z-
dc.date.issued2011-10-17en_GB
dc.date.accessioned2011-10-26T20:31:45Z-
dc.description.sponsorshipWestern Institute of Nursingen_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.