# inferential tests

- Created by: Thegirlwhoknewtoomuch - Team GR
- Created on: 18-10-13 11:31

First 473 words of the document:

Research methods

Inferential tests

Choosing a statistical test

If the study was investigating a correlation then the spearman's rank test

should be used. If the study was investigating a significance difference

between two groups then the level of data used in the investigation must be

considered.

If the data used in the investigation was nominal then Chi squared must be

used. Nominal data is data grouped into categories. The scores of each

category are described as frequencies.

The other type of data that could be used is ordinal which is data in the

form of ratings and rankings and anything that can be put in a position. As

spearman's rank requires the data to be ranked that too is also ordinal data.

Any investigation using ordinal data will either use a Wilcoxon T test or a

Mann Whitney U test as they both are used for ordinal data. To decide

which test to use for ordinal data the experimental design used in the

investigation must be considered. If a repeated measures design is used

then the Wilcoxon T test is used and if an independent groups design is used

then the Mann Whitney U test is used.

Spearman's rank

The correlation co-efficient which is called Rho; this is between +1 and -1. To see

if it is significant, a significance table is used along with two other pieces of

information which are the number of participants (N) and the type of hypothesis

(one or two tailed). To be significant, Rho needs to be the same or greater than

the critical value. In order to find the critical value the Rho, number of

participants and the type of hypothesis is needed. The + or symbol in the value

of Rho (e.g. +0.58 or -0.58) is ignored when finding if Rho is significant.

Chi squared test

Used when the data is nominal and when we are looking for a difference between

two groups. The calculated value of chi squared needs to be compared to the

critical value. If chi is greater than the critical value or the same as the critical

value then we reject the null hypothesis and say there is a significant difference.

Findings from an investigation involving chi squared as a statistical test are

presented in a contingency table. To calculate the degree of freedom the number

of rows minus one is multiplied by the number of columns minus one. This is then

used to find out the critical value by referring

to a critical value table and then if the critical

value is the same as or greater than the chi

## Comments

No comments have yet been made