Topic 1. Linear regression. OLS Flashcards
What is a population?
Population is a set of similar items or events. It is a group of actually existing objects or a hypothetical group of objects conceived as a generalization from experience.
What is a sample?
Sample is a data set selected from a statistical population.
What are the elements of a sample
observations (or sampling units, sampling points)
What is the common aim of statistical analysis?
to produce information about the population of our interest
What is the simple random sampling?
In the simple random sampling n objects are selected at random from a population and each object is equally likely to be included in the sample.
What does “simple linear regression” mean?
The word “simple” means that y depends on only one variable x.
What does the slope parameter in a regression line represent?
Slope of the line measures its steepness. It describes how y changes in response to a one unit change in x.
What is the linear correlation coefficient?
The linear correlation coefficient (r) measures the strength and direction of the linear relationship between two variables.
What is the standard deviation?
SD quantifies the amount of variation of values in a data set.
SD is simply the average distance to the mean.
What does low standard deviation indicate?
Low SD indicates that the data points tend to be close to the mean
What does high standard deviation indicate?
High SD indicates that the data points are spread out over a wider range of values.
What is a statistical error?
Statistical error is the amount by which an observation differs from its expected value, based on the whole population, from which the observation was selected randomly.
Is the statistical error observable parameter?
No. The statistical error is unobservable, because the population mean is unobservable.
How the statistical error is measured?
Statistical error is the difference between the value of a variable in the sample and the unobservable population mean.
What is a residual?
Residual is an observable estimate of the unobservable statistical error.