Statistical Tests: Chi-Square Test

dichotomous

divided or dividing into two parts or classifications

Chi-square tests

-appropriate when the outcome is discrete (dichotomous, ordinal, or categorical)

-data has been counted and divided into categories

Pearson chi-square test

used when groups are independent (or unrelated to one another)

p values and confidence intervals

Chi-square tests can be used to help us calculate and construct what?

chi-square test of independence (or association)

uses a chi-square test to assess whether two nominal variables of any number of categories (2 or more) are independent (or not associated with each other)

chi-square test of homogeneity

an appropriate statistical test to assess whether two proportions are equal

-independent groups

-large enough sample size

What are the assumptions we make when we do a chi-square test to ensure the validity of the results of our hypothesis testing procedure?

expected frequencies

What do you have to calculate when doing a chi-square test?

contingency table

simplest form is a 2x2 tablet representing 2 dichotomous variables

Absolute Risk Reduction

-it is the difference between the risk of an event amount the eposed and the risk of the event amound the unexposed

-incidence proportion (exposed) - incidence proportion (unexposed)

risk difference

Absolute risk reduction can also be called what?

relative risk (RR)

incidence proportion (exposed)/ incidence proportion (unexposed)

odds ratio (OR)

odds (exposed)/ odds (unexposed)

Absolute risk reduction (ARR)

incidence proportion (exposed) - incidence proportion (unexposed)

relative risk reduction (RRR)

[Incidence Proportion (Exposed) - Incidence Proportion (Unexposed)] / [Incidence Proportion (Unexposed)]

reject the Ho and state that it is significantly different

If 1 is not included in the interval you are given you do what?

-Chi-square

-Fisher's exact

If we have nominal data with 2 independent samples what should we use?

McNemar's test

If we have nominal data with related or paired samples what should we use?

Chi-sqaure for k independent samples

IF we have nominal data with 3 or more independent samples what should we use?

Cochran Q

If we have nominal data with 3 or more related samples what should we use?

Fisher's exact test

used for sample samples of nominal data with 2 independent samples

Sir Ronald Fisher

developed a test that can be used when the sample size requirements are not met. (Fisher's exact test)

McNemar's test

can be used to appropriately account for dependencies in the set of observations when the outcome variable is nominal and one is interested in comparing two proportions

McNemar's test compares 2 proportions and Cochran's Q test compares 3 or more proportions

What is the difference between Cochran's Q test and McNemar's test?

they both compare 2 dependent values

Why is the paired t test and McNemar's test similar?

A paired t test tests the equality of population means (continuous outcome) between 2 groups, and McNemar's test compares two proportions

What is the difference between a paired t test and McNemar’s test?

The Chisquare test for independence is used when data are collected from independent groups.The McNemar test is only used for paired nominal data

What is the difference between McNemar's test and Pearson's chi-square test of independence?