Introducing Inferential Statistics

• Published in: Statistics in Corpus Linguistics Research Vol. 1; pp. 97 - 115
• Main Author: Wallis, Sean
• Format: Book Chapter
• Language: English
• Published: Routledge 2021
• Edition: 1
• Subjects: Confidence Intervals; Wilson Score Interval; Wald Interval; Vice Versa; Yates's Continuity Correction; Calculate Confidence Intervals; Corpus Linguistics Research; Coin Tosses; Upper Bound; Wilson Interval; Population Probability; Unbiased Coin; Cochran's Rule; Binomial Function; Car Crash; Central Limit Theorem; Binomial Distribution; OLS Regression; Gaussian Formula; Typical Error Level; Credible Intervals; UK Household; Wilson Score; Traditional Statistics Teaching; Tail Area
• ISBN: 9781138589377; 9781138589384; 1138589381; 1138589373
• DOI: 10.4324/9780429491696-9

Cognitive psychologists refer to children learning 'naive physics', where they learn rules of the physical world through experience. What the people might call 'naïve statistics' is much more difficult to acquire. It is also more likely to mislead. Simple observed probability is just the beginning. In discussing inferential statistics, in this chapter, the author needs to keep in mind three distinct types of probability: the observed probability (or proportion), the 'true' population probability and the probability that an observation is unreliable. Statements about a sample are sometimes called descriptive statistics (the word statistic here being used in its most general sense, i.e., a number). The basic idea of inferential statistics is to draw an inference from our sample to this population. Inferential statistics is a methodology of extrapolation from data. It rests on a mathematical model that allows us to predict values in the population based on observations in a sample drawn from that population.