東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

A comparison study of standard setti...

Freilicher, Tina Marguerite.

FindBook

Google Book

Amazon

博客來

A comparison study of standard setting methods using test score data for a medical competency simulation examination.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	A comparison study of standard setting methods using test score data for a medical competency simulation examination./
作者:	Freilicher, Tina Marguerite.
面頁冊數:	168 p.
附註:	Source: Dissertation Abstracts International, Volume: 66-01, Section: A, page: 0155.
Contained By:	Dissertation Abstracts International66-01A.
標題:	Education, Tests and Measurements. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3159737
ISBN:	9780496928576

A comparison study of standard setting methods using test score data for a medical competency simulation examination.
Freilicher, Tina Marguerite.

A comparison study of standard setting methods using test score data for a medical competency simulation examination. - 168 p.

Source: Dissertation Abstracts International, Volume: 66-01, Section: A, page: 0155.

Thesis (Ph.D.)--Columbia University, 2005.

Signal detection theory has been used in such fields as psychophysics and engineering, in which research focuses on observers' ability to detect signals and make yes/no decisions from two types of observed categories (i.e., signal and noise). Latent class analysis is used when the classes or categories are unobserved. Latent class analysis has been typically used in medical research to determine the presence or absence of disease based on various test results. This study used a latent class extension of signal detection theory. Comparisons were made between the classifications of examinees' pass/fail status based on the use of a traditional standard setting method and classifications based on latent classes. The purpose of the comparisons was to assess the validity of the classifications based on an item-centered approach and an examinee-centered approach. With the item-centered approach, the judges were required to provide probability estimates of examinee performance based solely on the problems comprising the examination. The examinee-centered approach required the judges to rate examinees' test scores that were displayed graphically in two different formats. The results for the latent class signal detection model indicated that participants discriminated better when the test score data were presented graphically as total scores than when presented graphically as breakdown of those scores, regardless of order of presentation. The judges were better able to discriminate the higher and lower latent classes when presented with less information, as the Total Scores graphics presented an aggregate score on the problems comprising the examination, whereas, the Positive & Negative Score graphics presented for each problem a breakdown of the points earned for selecting correct actions and points deducted for selecting incorrect actions. One may surmise that the reason for these findings was that the Positive & Negative Scores may have been more difficult to interpret, as this graphical format displays more information to the judges, thereby the judges had more complex information to consider when making their decisions.

ISBN: 9780496928576Subjects--Topical Terms:

1017589
Education, Tests and Measurements.

A comparison study of standard setting methods using test score data for a medical competency simulation examination.
LDR:03073nam 2200277 a 45 001 969764
005 20110920
008 110921s2005 eng d
020 $a 9780496928576
035 $a (UnM)AAI3159737
035 $a AAI3159737
040 $a UnM $c UnM
100 1 $a Freilicher, Tina Marguerite. $3 1293822
245 1 2 $a A comparison study of standard setting methods using test score data for a medical competency simulation examination.
300 $a 168 p.
500 $a Source: Dissertation Abstracts International, Volume: 66-01, Section: A, page: 0155.
500 $a Sponsor: Lawrence DeCarlo.
502 $a Thesis (Ph.D.)--Columbia University, 2005.
520 $a Signal detection theory has been used in such fields as psychophysics and engineering, in which research focuses on observers' ability to detect signals and make yes/no decisions from two types of observed categories (i.e., signal and noise). Latent class analysis is used when the classes or categories are unobserved. Latent class analysis has been typically used in medical research to determine the presence or absence of disease based on various test results. This study used a latent class extension of signal detection theory. Comparisons were made between the classifications of examinees' pass/fail status based on the use of a traditional standard setting method and classifications based on latent classes. The purpose of the comparisons was to assess the validity of the classifications based on an item-centered approach and an examinee-centered approach. With the item-centered approach, the judges were required to provide probability estimates of examinee performance based solely on the problems comprising the examination. The examinee-centered approach required the judges to rate examinees' test scores that were displayed graphically in two different formats. The results for the latent class signal detection model indicated that participants discriminated better when the test score data were presented graphically as total scores than when presented graphically as breakdown of those scores, regardless of order of presentation. The judges were better able to discriminate the higher and lower latent classes when presented with less information, as the Total Scores graphics presented an aggregate score on the problems comprising the examination, whereas, the Positive & Negative Score graphics presented for each problem a breakdown of the points earned for selecting correct actions and points deducted for selecting incorrect actions. One may surmise that the reason for these findings was that the Positive & Negative Scores may have been more difficult to interpret, as this graphical format displays more information to the judges, thereby the judges had more complex information to consider when making their decisions.
590 $a School code: 0054.
650 4 $a Education, Tests and Measurements. $3 1017589
650 4 $a Psychology, Psychometrics. $3 1017742
690 $a 0288
690 $a 0632
710 2 0 $a Columbia University. $3 571054
773 0 $t Dissertation Abstracts International $g 66-01A.
790 $a 0054
790 1 0 $a DeCarlo, Lawrence, $e advisor
791 $a Ph.D.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3159737