STATISTICS

STATISTICS

The mathematics of the collection, organization, and interpretation of numerical data, especially the analysis of population characteristics by inference from sampling.

FIELD OF STATISTICS:

DESCRIPTIVE

Descriptive statistics are typically distinguished from inferential statistics. With descriptive statistics you are simply describing what is or what the data shows.

INFERENTIAL

With inferential statistics, you are trying to reach conclusions that extend beyond the immediate data alone.

POPULATION AND SAMPLE

*A population is a collection of data whose properties are analyzed. The population is the complete collection to be studied, it contains all subjects of interest.

*A sample is a part of the population of interest, a sub-collection selected from a population.

Sampling Technique

This category is for techniques for statistical sampling from real-world populations, used in observational studies and surveys.

Sampling methods

Before an organisation conducts primary research it has to be clear which respondents it wishes to interview. A company cannot possibly interview the whole population to get their opinions and views. This simply would be to costly and unfeasible. A sample of the population is taken to help them conduct this research. To select this sample there are again different methods of choosing your respondents, a mathematical approach called 'probability sampling' and a non- mathematical approach, simply called 'non-probability sampling'. Lets look at these in a little more detail.
Probability Sampling Methods – A mathematical chance of selecting the respondent.
Simple Random Samples
With this method of sampling the potential people you want to interview are listed e.g. a group of 100 are listed and a group of 20 may be selected from this list at random. The selection may be done by computer.
Systematic samples
Out of the 100 people we talked about above, systematic sampling suggests that if we select the 5th person from the above list, then we would select every 5th, 10th, 15th, 20th etc. The pattern is the every consecutive 5th. If the 6th person was selected then it would be every consecutive 6th.
Multi-Stage Samples
With this sampling process the respondents are chosen through a process of defined stages. For example residents within Islington (London) may have been chosen for a survey through the following process:
Throughout the UK the south east may have been selected at random, ( stage 1), within the UK London is selected again at random (stage 2), Islington is selected as the borough (stage 3), then polling districts from Islington (stage 4) and then individuals from the electoral register (stage 5).
As demonstrated five stages were gone through before the final selection of respondents were selected from the electoral register.
Non Probability Samples
Convenience Sampling
Where the researcher questions anyone who is available. This method is quick and cheap. However we do not know how representative the sample is and how reliable the result.
Quota Sampling
Using this method the sample audience is made up of potential purchasers of your product. For example if you feel that your typical customers will be male between 18-23, female between 26-30, then some of the respondents you interview should be made up of this group, i.e. a quota is given.
Dimensional Sampling
An extension to quota sampling. The researcher takes into account several characteristics e.g. gender, age income, residence education and ensures there is at least one person in the study that represents that population. E.g. out of 10 people you may want to make sure that 2 people are within a certain gender, two a certain age group who have an income rate between £25000 and £30000, this will again ensure the accuracy of the sample frame again.
To summaries there are two types of sampling frames - probability and non-probability, and within this six types of sampling methods as discussed above.

In ascending order of precision, the four different levels of measurement are nominal, ordinal, interval, and ratio.

The first level of measurement is nominal measurement. In this level of measurement, the numbers are used to classify the data. Also, in this level of measurement, words and letters can be used. Suppose there are data about people belonging to two different genders. In this case, the person belonging to the female gender could be classified as F, and the person belonging to the male gender could be classified as M. This type of assigning classification is nothing but the nominal level of measurement.
The second level of measurement is the ordinal level of measurement. This level of measurement depicts some ordered relationship between the number of items. Suppose a student scores the maximum marks in the class. In this case, he would be assigned the first rank. Then, the person scoring the second highest marks would be assigned the second rank, and so on. This level of measurement signifies some specific reason behind the assignment. The ordinal level of measurement indicates an approximate ordering of the measurements. The researcher should note that in this type of measurement, the difference or the ratio between any two types of rankings is not the same along the scale.
The third level of measurement is the interval level of measurement. The interval level of measurement not only classifies and orders the measurements, but it also specifies that the distances between each interval on the scale are equivalent along the scale from low interval to high interval. For example, an interval level of measurement could be the measurement of anxiety in a student between the score of 10 and 11, if this interval is the same as that of a student who is in between the score of 40 and 41.  A popular example of this level of measurement is temperature in centigrade, where, for example, the distance between 94⁰C and 96⁰C is the same as the distance between 100⁰C and 102⁰C.
The fourth level of measurement is the ratio level of measurement. In this level of measurement, the measurements can have a value of zero as well, which makes this type of measurement unlike the other types of measurement, although the properties are similar to that of the interval level of measurement. In the ratio level of measurement, the divisions between the points on the scale have an equivalent distance between them, and the rankings assigned to the items are according to their size.

http://www.statisticssolutions.com/methods-chapter/descriptive-statistics-and-interpreting-statistics/levels-of-measurement/

http://www.learnmarketing.net/sampling.htm

http://infinity.cos.edu/faculty/woodbury/stats/tutorial/Data_Pop_Samp.htm

http://www.socialresearchmethods.net/kb/statdesc.php