Researcher asking questions to a participant.
Inferential statistics are data that are used to make generalizations about a population from a sample. They are based on the use of a random sampling technique designed to ensure that a sample is representative. A simple example of an inferential statistic can probably be found on the front page of almost any newspaper, with any article stating that “X% of the population Y thinks/does/feels/believes Z”. A statement like “33% of 24-30 year olds prefer cake to cake” is based on inferential statistics. It would be impractical to ask all 24-30 year olds about their dessert preferences, so a representative sample of the population was surveyed in order to make an inference about the population as a whole.
Inferential and Descriptive Statistics
Another way to use research data is descriptive statistics. In this case, statements are made that simply describe the data collected. The same data set may be used descriptively or inferentially. For example, in the run-up to an election in the US, 1,000 people in a city might be asked about their voting intentions, with the result that 430 say they would vote for the Democrats, 410 said they would vote for Republicans and 160 were undecided or unwilling to vote. vote. tell. An example of using this data descriptively would be to simply state that 43% of the 1,000 people surveyed in this city intend to vote Democratic. An inferential statement would be “Democrats have a 2% advantage”: an inference about overall voting intentions was drawn from a sample.
methods
Before drawing general conclusions from a sample, it is important to employ the correct methods, otherwise these conclusions may not be valid. Common sources of error are in the way the sample is composed, and various factors can influence the validity of the population sample. Size is critical, as the smaller the size, the greater the risk that the sample will not be representative of the population as a whole. Care must be taken to eliminate sources of bias. In the example above, factors such as age, gender, and income can have a considerable influence on voting intentions, so if the sample was not composed in a way that reflects the general population, the conclusion may not be valid.
Sampling methods must be chosen carefully; For example, if someone took a convenience sample that included every ten names in the phone book or every ten passers-by in a shopping mall, that sample might not be valid. Sample bias is also a consideration. For example, 24- to 30-year-olds attending a cake lovers’ convention might like cake more than cake, which would mean that a dessert preference survey using convention attendees conference as a sample would not be very useful. representative.
applications
The use of inferential statistics is the foundation of research on populations and events because it is often difficult, and often impossible, to survey every member of a population or observe every event. Instead, researchers try to obtain a representative sample and use it as a basis for more general conclusions. For example, it would not have been possible to check the medical records of all smokers to establish a link between smoking and lung cancer, but numerous random samples comparing smokers with non-smokers and ruling out other risk factors have firmly established that link.
Researchers working with inferential statistics seek to keep their methods and practices transparent and as rigorous as possible to ensure the integrity of their results. Statements based on informal searches and quick searches may not be very helpful, but in areas such as medical research and clinical trial standards are much stricter, and inferential statistics have provided a great deal of valuable information. In other areas, they are used every day to make broad generalizations about populations that can shape public policy, product design, marketing, and political campaigns.