Question

What are the methods that work better for ordinal data in comparison to continuous data and explain the reasons?

Answer 1

answer:

explanation of reasons

• Straight out and Continuous Variables. Straight out factors are otherwise called discrete or subjective factors.
• Absolute factors can be additionally arranged as either ostensible, ordinal or dichotomous. ... For this situation there will be numerous more levels of the ostensible variable
• Ordinal information is a clear cut, measurable information compose where the factors have regular, requested classes and the separations between the classifications isn't known.
• These information exist on an ordinal scale, one of four levels of estimation depicted by S. S
• Consistent information will be data that can be estimated on a continuum or scale.
• Consistent information can have any numeric esteem and can be definitively subdivided into better and better augmentations, contingent on the accuracy of the estimation framework.
• Ordinal information is a straight out, measurable information compose where the factors have characteristic, requested classes and the separations between the classifications isn't known.
• These information exist on an ordinal scale, one of four levels of estimation portrayed by S. S. Stevens in 1946.
• Discrete information can go up against just number qualities though persistent information can go up against any esteem.
• For example the quantity of tumor patients treated by a healing center every year is discrete yet your weight is ceaseless.
• A few information are consistent however estimated in a discrete
• Level of estimation or size of measure is a characterization that portrays the idea of data inside the qualities doled out to factors.
• Analyst Stanley Smith Stevens built up the best-known arrangement with four levels, or scales, of estimation: ostensible, ordinal, interim, and proportion.
• Estimations of ordinal factors have a significant request to them. ... We can utilize frequencies, rates, and certain non-parametric measurements with ordinal information.
• In any case, implies, standard deviations, and parametric factual tests are for the most part not suitable to use with ordinal information.
• so finally these  are the work better for ordinal data in comparison to continuous data.