Reliability

00:01 Now let's talk about validity and reliability.

00:03 These are important concepts in scientific proof.

00:07 Reliability is reproducibility, can the results that you have collected in your study, for example, can be reproduced, if you do the example again, the study again? That's actually the hallmark of science, reproducibility.

00:21 That's why we publish our methodologies in papers so that other people can read our methods, reproduce our studies, and hopefully get the same results.

00:29 Validity on the other hand is, does my results, do my results represent the real world? Are they valid when I extrapolate to the rest of the world? So validity and reliability, as I've mentioned are philosophical corner stones to science.

00:46 There we considered it to be the basis of scientific proof.

00:50 There are threats to reliability. For example, consider a poor sampling strategy.

00:56 Let's say I'm trying to measure the average age of my population.

01:00 I'm going to sample several groups of people from my population and measure their average ages and use that information to extrapolate about the rest of the population.

01:10 So I take a selection from the old folk's home and I get an average age of over 60.

01:15 Then take a selection from high school, I got an average age around 15.

01:19 Every time I make a sample from a different part of my community, I'm getting a different estimate.

01:25 That's unreliable, that's because my sampling strategy was poor, it was not representative.

01:30 So a poor sampling strategy results in unreliable estimate.

01:34 Sometimes it's instability in the thing that I'm measuring.

01:38 Consider if I'm using a blood pressure cuff to measure blood pressure in an individual, that's my study, I'm measuring blood pressure.

01:45 But I'm measuring them at different times of the day.

01:48 As you may know, blood pressure changes throughout the day depending upon how awake you are, how horizontal you are, maybe what you've eating.

01:56 So unless I'm being consistent in how I'm measuring something, I might get different answers all the time, that's unreliability.

02:03 Sometimes there's divergences in observers.

02:07 So consider this. Maybe, I want to measure the mood of a group.

02:13 Several classes that I'm teaching maybe I care about how happy they are.

02:16 And I'm going to have various judges or raters tell me on average that class seems 6.5 happy.

02:23 That class seems 7.3 happy.

02:25 The problem with that is different people have different ideas of what happiness is, so the different raters will have different opinions and give me different responses.

02:33 That also is lack of reliability.