Define and distinguish among nominal, ordinal, interval, and ratio scales used in the quantitative measurement of research project outcomes. Discuss the errors which can be made by failing to understand the proper use of measurement scales based on level and type of comparison. For topic support please include at least 2 in-text citations, current and relevant references.

Nominal- they are used to label variables without any quantitative value that is giving a variable a higher value does not mean that variable is better the one given a lower value.for instance when coding gender you may give males a value 1 and females a value 2 or the vice versa

Ordinal-The order of values is important and meaningful with ordinal scales, but the variations between the individual values are not really understood. [Dalati, 2018]. for example For example, the difference between "OK and "Unhappy" is the same as the difference between Very Happy" and "Happy," and that's how much better it does is the difference between "OK and "Unhappy?" "

Interval-Interval scales are numeric scales that know the order of the values and the exact differences. Celsius temperature is the classic example of an interval scale since the variation between each value is the same. The difference of 60-50 degrees,[Dalati 2018] for example, is measurable, as is the difference of 80-70 degrees. Here's the problem with interval scales: they don't have a 'absolute zero,' like no temperature, at least not a celsius. For the interval scales, zero does not mean that there is no value, but actually another value, such as 0 degrees celsius, is used on the scale. Negative numbers have importance as well. Ratios cannot be measured without a true zero. We can add and subtract with interval data, but cannot divide or multiply.

Ratio-In terms of data measurement scales, ratios scales are the perfect nirvana since they show us how precise the value is between the units. AND they have an absolute null, which allows for a wide variety of both descriptive and inferential figures.[Gaca, 2016] If I repeat, all the above concerning interval data is true for proportional scales, plus ratio scales have a simple meaning of 0. The height, weight and length are good examples of ratio variables. In relation to statistical analysis, ratio scales offer an abundance of opportunities. Simply add, remove, multiply and divide these variables (ratios). Central pattern can be determined by mode, middle or medium; scatter metrics, such as standard deviation and variance coefficients, can also be calculated from ratio scales.

 Discuss the errors which can be made by failing to understand the proper use of measurement scales based on level and type of comparison.

• may lead to wrong estimates- assume you classify a nominal variable as an ordinal variable the estimates of say mean will vary
• brings about wrong decision making- when doing regression analysis if you quantify a variable in the wrong category you will get a model that is biased which will lead to wrong conclusions which will lead to wrong decisions
• wrong units of calculation- assume you have gender which is a unitless variable and you ranks it as an interval variable this will lead to wrong units at the end point