scholarly journals POST EXAM ANALYSIS SELECTION OF HIGH AND LOW EXAM RESULT GROUPS BY NORMAL DISTRIBUTION CURVE

Author(s):  
Faiz Marikar

The key factor of an assessment is to minimize the errors by having a good reliability and validity of the assessment yardstick. To achieve high score in the test examinee must be aware about assessment cycle and use it in appropriate way in post exam analysis. Outcome of the results can be utilized as a constructive feedback in any given program. This cross-sectional study was conducted at department of Biochemistry, University of Rajarata. Multiple choice questions, structured essay type questions, objective structured practical examination, and continuous assessment was used in this study. Total number of students are 180 and was assessed for difficulty index, discrimination index, reliability, and standard error of measurement. In this study sample for analysis was used basically the examiner divides students into two groups (‘high’ and ‘low’) according to the score sheet of each student. Most of them are doing in a wrong way basically they divide high and low clusters as 25% each and considered upper quartile and lower quartile. In this study we compared it with the standard normal distribution curve where high and low groups are considered as 16% where is the standard. There is no significant difference among both clusters, and we recommend using the standard 16% as the high and low groups in post examination analysis. Keywords: difficulty index, post examination analysis, reliability of the examination, standard error of measurement

1966 ◽  
Vol 19 (2) ◽  
pp. 611-617 ◽  
Author(s):  
Donald W. Zimmerman ◽  
Richard H. Williams

It is shown that for the case of non-independence of true scores and error scores interpretation of the standard error of measurement is modified in two ways. First, the standard deviation of the distribution of error scores is given by a modified equation. Second, the confidence interval for true score varies with the individual's observed score. It is shown that the equation, so=√[(N−O/a]+[so2(roō−roo)/roō]̄, where N is the number of items, O is the individual's observed score, a is the number of choices per item, so2 is observed variance, roo is test reliability as empirically determined, and roō is reliability for the case where only non-independent error is present, provides a more accurate interpretation of the test score of an individual.


1993 ◽  
Vol 2 (2) ◽  
pp. 97-103 ◽  
Author(s):  
Kelly R. Holcomb ◽  
Cheryl A. Skaggs ◽  
Teddy W. Worrell ◽  
Mark DeCarlo ◽  
K. Donald Shelbourne

A paucity of information exists concerning reliability of the KT-1000 knee arthrometer (MEDmetric Corp., San Diego, CA) when used by different clinicians to assess the same anterior cruciate ligament-deficient patient. The purpose of this study was to determine the reliability and standard error of measurement of four clinicians who routinely report KT-1000 arthrometer values to referring orthopedic surgeons. Two physical therapists and two athletic trainers performed anterior laxity tests using the KT-1000 on 19 subjects. Intraclass correlation coefficients (ICC) and standard error of measurement (SEM) were used to determine reliability. Intratester ICC ranged from .98 to 1.0 and intratesterSEMranged from 0.0 to .28 mm. Intertester ICC andSEMfor all four testers were .53 and 1.2 mm, respectively. A 95% confidence interval (M ± 1.96 ×SEM) of the intertester variability ranged from −0.18 to 4.52 mm. Therefore, large intertester variation existed in KT-1000 values. Each facility should standardize testing procedures and establish intratester and intertester reliability for all clinicians reporting KT-1000 values.


Author(s):  
Víctor Rodríguez-Rielves ◽  
Alejandro Martínez-Cava ◽  
Ángel Buendía-Romero ◽  
José Ramón Lillo-Beviá ◽  
Javier Courel-Ibáñez ◽  
...  

Purpose: To examine the reproducibility (intradevice and interdevice agreement) of the Rotor 2INpower device under a wide range of cycling conditions. Methods: Twelve highly trained male cyclists and triathletes completed 5 cycling tests, including graded exercise tests at different cadences (70–100 rpm), workloads (100–650 W), pedaling positions (seated and standing), and vibration conditions (20–40 Hz) and an 8-second maximal sprint (>1000 W). An intradevice analysis included a comparison between the power output registered by 3 units of Rotor 2INpower, whereas the power output provided by each one of these units and the gold-standard SRM crankset were compared for the interdevice analysis. Among others, statistical calculations included the standard error of measurement, expressed in absolute (in watts) and relative terms as the coefficient of variation (CV). Results: Except for the graded exercise test seated at 100 rpm/100 W (CV = 10.2%), the intradevice analysis showed an acceptable magnitude of error (CV ≤ 6.9%, standard error of measurement ≤ 12.3 W) between the 3 Rotor 2INpower. Similarly, these 3 units showed an acceptable agreement with the gold standard in all graded exercise test situations (CV ≤ 4.0%, standard error of measurement ≤ 13.1 W). On the other hand, both the intradevice and interdevice agreements proved to be slightly reduced under high cadences (intradevice: CV ≤ 10.2%; interdevice: CV ≤ 4.0%) and vibration (intradevice: CV ≤ 4.0%; interdevice: CV ≤ 3.6%), as well as during standing pedaling (intradevice: CV ≤ 4.1%; interdevice: CV ≤ 2.5%). Although within the limits of an acceptable agreement, measurement errors increased during the sprint tests (CV ≤ 7.4%). Conclusions: Based on these results, the Rotor 2INpower could be considered a reproducible tool to monitor power output in most cycling situations.


Author(s):  
Andrea Berger

Inhibition of Return (IOR) is a mechanism whereby the attentional system favors novel locations by inhibiting already scanned ones. In spatial attention tasks, it commonly occurs when the interval between cue onset and target onset is longer than 300 ms. The positive difference between reactions in the valid condition and those in the invalid one shows that responses to target stimuli are slower following a valid cue than responses to target stimuli following an invalid cue. IOR is a very robust phenomenon at the group mean level; however, this study demonstrates that its standard error of measurement is extremely high, which seriously challenges any attempt to interpret an individual score as representing the characteristics of a subject's attention system. Furthermore, this reliability problem might diminish the likelihood of finding differences between groups and conditions. The study shows that these problems may be partially corrected by employing the back-to-center paradigm.


Hand Therapy ◽  
2020 ◽  
Vol 25 (2) ◽  
pp. 56-62 ◽  
Author(s):  
Erfan Shafiee ◽  
Maryam Farzad ◽  
Joy Macdermid ◽  
Amirreza Smaeel Beygi ◽  
Atefeh Vafaei ◽  
...  

Introduction The Patient-Rated Tennis Elbow Evaluation (PRTEE) questionnaire is a tool designed for self-assessment of forearm pain and disability in patients with tennis elbow. The aims of this study were to translate and cross-culturally adapt the PRTEE questionnaire into Persian and evaluate its reliability and construct validity. Methods The PRTEE questionnaire was translated into and cross-culturally adapted to Persian in 90 consecutive patients with tennis elbow, according to well-established guidelines. Reliability was tested by means of test–retest and internal consistency. The measurement error was measured by calculating the standard error of measurement. Based on the standard error of measurement, the minimum detectable change was calculated. To evaluate construct and convergent validity, correlation with the PRTEE with the Disabilities of the Arm, Shoulder and Hand questionnaire and Visual analogue scale was used. Results In the process of cross-cultural adaptation, two items (6 and 8) were modified. In item 6, the term “door knob” was changed to “turn a key”, and in the item 8, “cup of coffee” was changed to “cup of milk”. Item-total correlations were greater than 0.55 (ranged from 0.55 to 0.76), internal consistency was high (Cronbach’s alpha, 0.94) and a high intraclass correlation coefficient (0.98) indicated excellent reliability of the P-PRTEE. The standard error of measurement and minimum detectable change were 5.40 and 14.24, respectively. The Persian version of the PRTEE questionnaire (P-PRTEE) shows strong construct and convergent validity ( r values = 0.85, p < 0.05). Conclusions The P-PRTEE is valid and reliable in assessing disability and pain in Persian patients with tennis elbow. The excellent psychometric properties of the P-PRTEE endorse the use of this questionnaire in clinical settings.


Sign in / Sign up

Export Citation Format

Share Document