Evaluation (Validation and Verification) - Medical Device Design: Innovation from Concept to Market - page 248

Table 9.16: t-test for Data Sets That Are Significantly Different

(a) Data Sets

Set 1 Set 2

9.00 41

9.01 13

9.02 19

8.99 14

8.98 20

9.00 25

9.00 0

9.00 0

8.99 1

9.99 38

9.00 41

9.01 13

9.02 19

8.99 14

8.98 20

9.00 25

9.00 0

9.00 0

8.99 1

9.99 38

(b) t-test result
Two-Sample t-test Assuming Unequal Variances
Set 1

Set 2

Mean 9.10 17.24

Variance 0.09 206.58

Observations 20.00 20.00

Hypothesized mean difference 0.00

df 19.00

t stat − 2.53

p (T <= t) one-tailed 0.01

t critical one-tailed 1.73

p (T <= t) two-tailed 0.02

t critical two-tailed 2.09

known issues in devices similar to yours and then to show that you have either designed
them out or accommodated them. Note this part feeds directly to the overall risk analysis.

l

Clinical/scientific literature : predominantly to ensure that your device is utilizing best practices
and even better if the literature shows that your device (independent of you) is the best.

9.7.1 Conducting the Review
Referring to MEDDEV 2.7.1 rev 3 and modifying terminology to suit the FDA results in a
literature flow chart.