Types of sampling

Loading...

Del curso dictado por University of Cape Town

Understanding Clinical Research: Behind the Statistics

729 calificaciones

University of Cape Town

Understanding Clinical Research: Behind the Statistics

729 calificaciones

If you’ve ever skipped over`the results section of a medical paper because terms like “confidence interval” or “p-value” go over your head, then you’re in the right place. You may be a clinical practitioner reading research articles to keep up-to-date with developments in your field or a medical student wondering how to approach your own research. Greater confidence in understanding statistical analysis and the results can benefit both working professionals and those undertaking research themselves. If you are simply interested in properly understanding the published literature or if you are embarking on conducting your own research, this course is your first step. It offers an easy entry into interpreting common statistical concepts without getting into nitty-gritty mathematical formulae. To be able to interpret and understand these concepts is the best way to start your journey into the world of clinical literature. That’s where this course comes in - so let’s get started! The course is free to enroll and take. You will be offered the option of purchasing a certificate of completion which you become eligible for, if you successfully complete the course requirements. This can be an excellent way of staying motivated! Financial Aid is also available.

De la lección

Describing your data

With the next topics, we finally get started with the statistics. Have you ever looked at the methods and results section of any healthcare research publication and noted the variety of statistical tests used? You would have come across terms like t-test, Mann-Whitney-U test, Wilcoxon test, Fisher’s exact test and the ubiquitous chi-squared test. Why so many tests you might wonder? It’s all about types of data. In this week, I am going to tackle the differences in data which determine what type of statistical test we can use in making sense of our data.

Making inferences: Sampling5:13

Types of sampling3:17

Conoce a los instructores

Juan H Klopper
Dr
Department of Surgery

Now there are four types of sampling that I want to discuss.

The first one is going to be simple random selection.

So let's start off by talking about simple random sampling.

That is where every member of a population has an equal likelihood of being chosen.

So, I do have to have a master list and add a number to each individual.

And then have some form of random number generator that can be done on paper,

if possible.

These days, of course, we just use computers to generate random numbers.

And those random numbers, each of them from that master list has an equal

likelihood of being chosen and would choose from a population.

Then there's systematic sampling.

Now there we're going to be very rigorous about it and

choose our individuals specifically, but also from that master list.

So how's this going to work?

That is where we're just going to as a system just choose every individual

equally spaced, every 10th individual, every 20th individual on the list.

In the end, we've got to a little equation.

We call it every kth, a lowercase k, every kth individual.

And the sample size we're going to call lowercase i.

And the population, uppercase N.

So to choose the kth member we'll just be N divided by i.

So if we look at a little example if we have a population of 10,000 and

we want 1,000 from those.

So 10,000 divided by 1,000 it's 10, so

we're going to choose from that list exactly every 10th individual.

Just to remember though that this can also introduce bias.

Imagine you work in a clinic, and you're going to include in your

data collection every 10th patient who comes into the clinic.

But that might mean that it's a patient who comes in quite late in the day,

if it's every 10th one, and you only see a small amount of patients everyday.

And there might be a reason why those patients come in late.

They might be sicker or elderly in some way, and it's difficult for

them to come to a hospital, or to the clinic early in the morning.

So you can introduce bias by this sort of sampling.

Then there's the cluster random sampling.

This is usually where we don't have a master list.

We don't have a master list of the population, but

at least they clustered somehow.

So as an example I mention you wanted to do some research on healthcare workers at

clinics in a city.

You don't have a master list of those health care workers, but

you do have a master list of those clinics.

Now, those clinics can be chosen at random, and

then every worker at that clinic would form part of a sample.

Now lastly, there's the stratified random sampling.

That's where there's a mutually exclusive trait in the population.

Which immediately separates them and

we can take participants from each of those groups.

The usual example there is just gender,

if you were to divide the population between male and female for instance.

You could then start taking samples from each of those mutually exclusive groups.

And that's usually done where we want to keep the group sizes equal in number.

Explora nuestro catálogo

Inscríbete de manera gratuita y obtén recomendaciones personalizadas, actualizaciones y ofertas.

Coursera brinda acceso universal a la mejor educación del mundo, al asociarse con las mejores universidades y organizaciones, para ofrecer cursos en línea.

© 2018 Coursera Inc. Todos los derechos reservados.

Descargar en la App Store

Consíguelo en Google Play