# About Individual Tests

**T -test: (student t-test)**

**As for all parametric tests, it is used for quantitative data which is normally distributed in the population.**

(i.e. continuous data such as weight/height etc).

T -test can be unpaired or paired:

Paired t-test is a special type of t-test used when the data is "paired" e.g. - blood glucose before and after taking a drug OR Pulse rate before and after exercise (in the same group).**Z-Test:****â€‹**Involves the same steps as t-test.- Used when the sample is large (n> 100).
- T-test though is more important as there is no Âsituation where as Z test can be used and a t-test cannot be but the vice versa can occur.

- â€‹
**Anova:**

Whereas a T test is appropriate for making just one comparison (between two sample means, or between a sample mean and a hypothesized population mean), when more than one comparison is being made (i.e. when means of> 2 groups are being compared), ANOVA (analysis of variance) is the appropriate technique.

ANOV A can be:- â€‹One way ANOVA - when the groups differ in terms of only one factor at a time.

e.g.: 3 different drugs given to 3 groups of people to compare their effects. - Two way ANOVA - If the groups 2 differ in factors at a time.

e.g. - If in the above example if each group consists of male and female patients, the researcher may also want to make comparisons between the sexes, making a total of 6 groups.

- â€‹One way ANOVA - when the groups differ in terms of only one factor at a time.
- â€‹
**Chi-square test:**

Used for qualitative data, which is in the form of proportions (percentages). e.g. â€“ comparing incidence of a disease in 2 groups of children with one group vaccinated and the other not, OR comÂparing incidence of Hb < 10 (anemia) in 2 groups of pregnant women, one taking iron supplements and the other not.

(adsbygoogle = window.adsbygoogle || []).push({});

**
**<!--
e9 = new Object();
e9.size = "160x600";
//-->

<!--
e9 = new Object();
e9.size = "160x600";
//-->