| Revision as of 00:00, 20 May 2013 editDuoduoduo (talk | contribs)Extended confirmed users, Pending changes reviewers11,085 edits →Methods: skewness and kurtosis← Previous edit |
Latest revision as of 01:17, 13 May 2024 edit undoJlwoodwa (talk | contribs)Extended confirmed users, Page movers, New page reviewers, Pending changes reviewers, Rollbackers77,006 edits +rcats |
| (28 intermediate revisions by 19 users not shown) |
| Line 1: |
Line 1: |
|
|
#REDIRECT ] |
|
'''Univariate analysis''' is the simplest form of ].<ref name=babbie>], , 12th edition, Wadsworth Publishing, 2009, ISBN 0-495-59841-0, p. 426-433</ref> The analysis is carried out with the description of a single ] in terms of the applicable ].<ref name=babbie/> For example, if the variable "age" was the subject of the analysis, the researcher would look at how many subjects fall into given age attribute categories. |
|
|
|
|
|
|
|
{{rcatsh| |
|
Univariate analysis contrasts with ] – the analysis of two variables simultaneously – or ] – the analysis of multiple variables simultaneously.<ref name=babbie/> Univariate analysis is commonly used in the first, ] stages of research, before being supplemented by more advanced, ] bivariate or multivariate analysis.<ref>Harvey Russell Bernard, , Rowman Altamira, 2006, ISBN 0-7591-0869-2, p. 549</ref><ref>A. Cooper, Tony J. Weekes, , Rowman & Littlefield, 1983, ISBN 0-389-20383-1, pp. 50–51</ref> |
|
|
|
{{r sec}} |
|
|
|
|
|
{{r hist}} |
|
==Methods== |
|
|
|
{{r wikidata}} |
|
|
|
|
⚫ |
}} |
|
A basic way of presenting univariate data is to create a ] of the individual cases, which involves presenting the number of cases in the ] that fall into each category of values of the variable.<ref name=babbie/> This can be done in a table format or with a ] or a similar form of graphical representation.<ref name=babbie/> A sample distribution table is presented below, showing the frequency distribution for a variable "age". |
|
|
|
|
|
{| border=1 cellspacing=0 cellpadding=2 |
|
|
!Age range |
|
|
!Number of cases |
|
|
!Percent |
|
|
|- |
|
|
| under 18 |
|
|
|10 |
|
|
|5 |
|
|
|- |
|
|
|18–29 |
|
|
|50 |
|
|
|25 |
|
|
|- |
|
|
|29–45 |
|
|
|40 |
|
|
|20 |
|
|
|- |
|
|
|45–65 |
|
|
|40 |
|
|
|20 |
|
|
|- |
|
|
|over 65 |
|
|
|60 |
|
|
|30 |
|
|
|- |
|
|
| Valid cases: 200 <br> Missing cases: 0 |
|
|
|- |
|
| ⚫ |
|} |
|
|
|
|
|
In addition to frequency distribution, univariate analysis commonly involves reporting measures of ] (location).<ref name=babbie/> This involves describing the way in which ] tend to cluster around some value.<ref>Dodge, Y. (2003) , OUP. ISBN 0-19-920613-9, p. 61</ref> In univariate analysis, the measure of central tendency is an ] of a set of ], the word "average" being variously construed as ], ], ] or another measure of location, depending on the context.<ref name=babbie/> For a ], such as preferred brand of cereal, only the mode can serve this purpose. For a variable measured on an ], such as temperature in ], or on a ], such as temperature on the ] scale, the median or mean can also be used. |
|
|
|
|
|
Another set of measures used in univariate analysis, complementing the study of the central tendency, involves studying the ].<ref name=babbie/> Those measurements look at how the values are distributed around values of central tendency.<ref name=babbie/> The dispersion measures most often involve studying the ], ], and the ].<ref name=babbie/> Further descriptors include the variable's ] and ]. |
|
|
|
|
|
In the case of ], which can be ] along a time scale, univariate analysis can also involve time series analysis such as ], ], ], or ] models. These models describe the relation between the current value of the variable and its various past values. |
|
|
|
|
|
==See also== |
|
|
* ] |
|
|
* ] |
|
|
* ] |
|
|
* ] |
|
|
|
|
|
==References== |
|
|
{{reflist}} |
|
|
|
|
|
] |
|