Introduction

Loading...

Del curso dictado por Johns Hopkins University

Hypothesis Testing in Public Health

7 calificaciones

Johns Hopkins University

Hypothesis Testing in Public Health

7 calificaciones

Curso 2 de 4 en SpecializationBiostatistics in Public Health

Biostatistics is an essential skill for every public health researcher because it provides a set of precise methods for extracting meaningful conclusions from data. In this second course of the Biostatistics in Public Health Specialization, you'll learn to evaluate sample variability and apply statistical hypothesis testing methods. Along the way, you'll perform calculations and interpret real-world data from the published scientific literature. Topics include sample statistics, the central limit theorem, confidence intervals, hypothesis testing, and p values.

De la lección

Confidence Intervals for Population Comparison Measures

Within module three, confidence intervals are discussed at length and ratios are discussed again. Aside from the lectures, you will also be completing a practice quiz and graded quiz.

Introduction2:06

Confidence Intervals for Population Comparison Measures15:08

Confidence Intervals for Comparing Means of Continuous Outcomes Between Two Populations28:24

Confidence Intervals for Binary Comparisons: Part 1, Difference in Proportions12:07

Confidence Intervals for Binary Comparisons: Part 2, Ratio of Proportions and Odds Ratios24:13

Confidence Intervals for Incidence Rate Ratios10:19

A Brief Note About Ratios (Again)11:14

Additional Examples17:49

Conoce a los instructores

John McGready, PhD, MS
Associate Scientist, Biostatistics
Bloomberg School of Public Health

Hey guys, John here again,

and in lecture set eight here we're going to

consider taking into account sampling variability through

confidence intervals where we're looking at measures that compare

two populations using data from two samples.

We'll find out the general drill for creating confidence intervals for things like

mean differences or differences in

proportions is the same as what we saw for single measures.

We take our estimated difference and then

subtract two estimated standard errors and we'll show how to do that.

Then for ratios and we've alluded to this before,

we're going to need to take things to the log scale

before doing their confidence interval computations.

So, it'll be a two-step process where we

first do the computations for the confidence interval in

the log ratio scale and then anti-log or

exponentiate our results back to the ratio scale.

So, in this process we'll see that generally again,

the procedure is similar across all these computations.

We take our estimate of interests and add and subtract two standard errors,

but we'll also focus on interpreting the range of

possible values for association measure whether it be a mean difference,

difference in proportions, relative risk etc.

Interpreting that in the scientific context

and paying attention to something called a null

value whose presence would indicate no association at the population level.

We're going to be very interested as to whether

that number appears in our confidence interval or not.

So for example, if we were computing a difference between two populations for example,

mean difference, there are really no difference at

the population level then the true mean difference would be zero.

So, we're going to be concerned about whether zero appears

as a possible value in our confidence interval or not,

and if not we're going to define

the concept called statistically significant and talk about that as well.

So, this will be a really interesting lecture set,

so we'll start seeing how the results and inclusions were made for

some of the seminal studies we've looked at and other studies as well.

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.

© 2019 Coursera Inc. Todos los derechos reservados.

Descargar en la App Store

Consíguelo en Google Play