Question

Use the following information to answer questions 5 through 6. Investigators conducted a study among 400 adults to determine the validity of a short form of the self-efficacy scale (SF) compared to the already established long form of the self-efficacy scale (LF). The LF contains 10 questions such as "There isn't much use in asking for a raise, since I probably won't get one anyway" to which persons answer with a number from 1 to 5, with 1 being "never agree" and 5 being "always agree". This score is then summed, divided by 10. A previously established cut-point of a score of 4 or higher indicates low self-efficacy. The SF reduced the number o questions to 5 for use in a national survey, and utilized the same cut-point of a mean response of 4 or higher indicating low self-efficacy. Here are the results for classification of low self-efficacy: Long Form Total Short form Low self-efficacy None Low self-efficacy30 None Total 20 445 465 50 450 400 35 5. Calculate the sensitivity, specificity, positive predictive value, and negative predictive value of the short form measure, and interpret each. 6. Why did the investigators calculate sensitivity and specificity in this example, instead of Kappa?

Answer 1

5.The probability that a diseased individual will be identified as such by the test is called as sensitivity

The probability that an individual without the disease will be identified as such by the test is called as specificity

The positive predictive value is the probability that subjects with a positive screening test truly have the disease.

The negative predictive value is the probability that subjects with a negative screening test truly don't have the disease

*Sensitivity = [True positive (TP) $\large \div$ True positives(TP) + False negatives (FP] X 100

*Specificity = [True Negative (TN) $\large \div$ False positives(FP) + True Negatives (TN)] X 100

*Positive Predictive Value (PPV) = {True positives(TP) $\large \div$ True positives(TP) + False positives(FP)] X 100

*Negative Predictive Value (NPV) = [(True Negatives(TN) $\large \div$ True Negatives (TN) + False Negatives (FN)] X 100

6. Kappa is a popular statistic used to assess interrater reliability. It compares the observed proportion of agreement to the

proportion of agreement that would be expected if the agreement occurred purely by chance. Kappa is the measure of

agreement between evaluations.

Thus the investigator calculate the sensitivity and specificity instead of kappa