Statistical Techniques and sampling designs (step 4 deductive research process)

5 important questions on Statistical Techniques and sampling designs (step 4 deductive research process)

What's the difference between descriptive statistics and inferential statistics?

Raw data means nothing without the proper tools to analyze and interpret them --> therefore we use statistical techniques:

1. Descriptive statistics: Methods of summarizing the data in an informative way.
- Measures of central tendency (mean, median, mode)
- Measures of dispersion (range, standard deviation, variance, interquartile range: you look at the 50 middle data)
2. Inferential statistics: Methods to draw conclusions (or to make inferences).
- Mean difference test
- Chi - square test
- Analysis of variance (ANOVA)
- Regression analysis
- Logit analysis

What are the four types of scales and what are the differences?

1. Nominal: no logical order. Don't have a value: to classify observations (elections).
2. Ordinal: Ranked or ordered. We don't know how much between orders (more spicier: based on personal flavour).
3. Interval: Meaningful differences between values, but no natural zero point (IQ).
4. Ratio: meaningful differences and ratios between values due to a natural zero point (for example zero means "no distance" navigation).

What's the goal of a sampling design?

A sampling design is used, because when statistics can do more harm than good if the population is not correctly targeted.
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

Why use samples in the first place?

  • Impossible to study the entire population;
  • Prohibitive to study the entire population in terms of cost & speed.

When you have to determine the sampling design, as a researcher you have to choose between 2 types of sampling techniques. What are these sampling techniques?

Probability sampling: each element of the population has a known chance of being selected as a subject.
Pro's: results are generalizable to population
Con's: More time and resource intensive + you need a good sampling frame, most of the time not direct available.

Nonprobability sampling
: the elements of the population do not have a known chance of being selected as a subject.
Pro's: less time and resource intensive
Con's: results are not generalizable to population.

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo