Which Test To Use?

You conducted your survey and collected your data. You plotted your charts and suspect a certain conclusion. Which test should you use to validate your hypothesis?

Having learnt different statistical tools and showing their implementation in Excel LAMBDA, we want a reference to guide us.

Qualitative and Quantitative Data

The first is to distinguish the type of data. Data can be qualitative or quantitative.

Qualitative data can be nominal or ordinal.

Nominal data are named categorised data, for example gender:{male, female} and direction:{north, south, east, west}.

Ordinal data are categories with implied order, for example size:{small, medium, large}, school grades:{A, B, C, D, E} and service rating:{very poor, poor, average, good, great}. The order however are not equally spaced, i.e. you cannot equate the difference between poor and average, with the difference between average and good.

Quantitative data can be interval or ratio. Unlike qualitative data, quantitative data are equally spaced.

Interval data are data which can be placed on a scale, for example temperature in Celsius and IQ. The difference between any two integer points are equally spaced. But interval data have no true zero.

Ratio data have the same properties as interval data, but has a true zero with no negative values, for example temperature in Kelvin, speed, height, and weight.

Here's a table summary.

	Qualitative Data		Quantitative Data
	Nominal	Ordinal	Interval	Ratio
Ranked		✅	✅	✅
Equal spacing			✅	✅
True zero				✅

Deciding which Test

With qualitative data we can use proportion tests. With quantitative data, we would need to determine whether the data is normally distributed. If normally distributed we can use sample mean tests. Else we use non-parametric tests.

• Qualitative Data
• 1 Sample
• One Proportion Test
• 2 Sample
• Two Proportion Test
• Quantitative Data
• Determine Normality
• Anderson-Darling Test
• Shapiro-Wilk Test
• Normal Data
• 1 Sample
• One Sample Mean Test | Array
• 2 Samples
• Two Sample Mean Test | Array
• > 2 Samples
• ANOVA
• Non-Normal Data
• 2 Samples
• Mann-Whitney Test
• > 2 Samples
• Kruskal-Wallis Test

There are many other types of statistical tests, and you are most welcome to try implementing them in Excel LAMBDA. I listed only those I have come across before.

Now you have these LAMBDA functions presented in this blog, you are armed with this to tackle your experiments in DC-DEN!