O - P

Click a term to expand its definition, or expand all definitions collapse all definitions

• objective measures

  Any measure that is based on fact rather than opinion.
  

• observational study

  A study that records events occurring in a defined population without any intervention by the researcher.
  

• operational definition

  A way of showing something which can’t be seen or measured, like social class, by something that can be measured, like the amount of money you make or how many years you have gone to school. This kind of definition explains an idea by telling how the idea is measured.
  

• ordinal scale

  A ranking of values (amounts, numbers, scores) from greatest to least, lowest to highest, first to last, etc., but by a category instead of a number. For example, social class could be grouped and ordered as lower class, working class, middle class, and upper class. Items (groupings) on this kind of scale are not equally spaced.
  

• outcome measure

  The measure of a change (usually the difference in scores before and after treatment).
  

• outcome variables

  Variables that are used to measure the overall impact of the study.
  

• outliers

  Abnormal values in the data that are unusually large or unusually small compared to the other values.
  

• participant observation

  Investigation in which a researcher participates as a member of the group. The researcher may choose to inform the group of his role or in some cases omit his identity and act as an ordinary member of the group.
  

• participatory action research

  A type of study in which a researcher becomes a member of the group being studied and finds out information by doing what the group is doing.
  

• pilot study

  A trial, both to examine the effectiveness of various aspects of the proposed research, such as procedures for data gathering, and to aid the completion of detailed project plans.
  

• pooling

  Term used to describe the act of combining data from more than one group of subjects, or combining scores from different variables to produce a single score.
  

• psychometrics

  Psychological tests that are standardized (formal or set); for example, an IQ test.
  

• psychosocial rehabilitation

  A kind of therapy that tries to improve a person’s mental health by looking at how the person acts with other people, and how the person can be happier and more skillful in social settings. The therapy often includes group living, group recreation, and other group projects.
  

• pre-coded questions

  Pre-coded questions have a list of answers from which to choose in order to facilitate analysis, or to better control the interview process. In a self-completion questionnaire the respondent chooses the option or options. In an interview, the options are either read out or shown to the respondent who then chooses. In this type of question care must be taken that the options are exclusive and exhaustive. The category 'Other' is often added in case the list is not complete, but it is important to keep in mind that if there are possible answers which are not on the list, bias can ensue.
  

• predictive research

  Predictive research is concerned with identifying indicators of future behaviour or demand in a population, on the basis of the current behaviour and demands of a sample. Predictive techniques use a number of statistical approaches.
  

• predictive validity

  The measure of how well the test being studied predicts some practical result that the “gold standard” will find later.
  

• pre-project research

  Pre-project research is an activity undertaken in the planning stages of research to clarify issues such as the focus of the research, its aims, access to sampling frame, likely response rate, most appropriate methodology, and means of analysis. Overlaps somewhat with a pilot study.
  

• prevalence

  The proportion of a population having a particular condition or characteristic; for instance, the percentage of people in a city with a particular disease, or who smoke.
  

• primary source

  A primary source is that which provides the initial basic data set under discussion, while a secondary source is one which offers further analysis or commentary on the data. For example, the primary source for demographic data in the UK is likely to be the publications of the Office of Population and Census Studies (OPCS), while there are many secondary sources which make use of OPCS output. Generally it is better, if you can, to make reference to primary sources.
  

• principle investigator (PI)

  The main person running a research study.
  

• probability

  A measure of how likely something is. For example, probability could be written as “p < .05,” which means that based on chance alone, this thing should happen fewer than 5 times in 100.
  

• probability sampling

  Also known as random sampling. Choosing people to be studied in such a way that each person (or thing, place, etc.) in the total pool has an equal chance of being chosen.
  

• propensity scores

  Measure of an individual's predicted probability of being a program participant given his or her observed characteristics.