In: Statistics and Probability
(a) differentiate between parametric and non parametric statistics and give one example for each test. (b)outline and discuss the steps which guide a researcher in designing a questionnaire. (c) briefly discuss the merit and demerit of a questionnaire as a research tool.
Parametric Statistics
Parametric statistics are any statistical tests based on underlying
assumptions about data’s distribution. In other words, parametric
statistics are based on the parameters of the normal curve. Because
parametric statistics are based on the normal curve, data must meet
certain assumptions, or parametric statistics cannot be calculated.
Prior to running any parametric statistics, you should always be
sure to test the assumptions for the tests that you are planning to
run.
Nonparametric Statistics
As implied by the name, nonparametric statistics are not based on
the parameters of the normal curve. Therefore, if your data violate
the assumptions of a usual parametric and nonparametric statistics
might better define the data, try running the nonparametric
equivalent of the parametric test. You should also consider using
nonparametric equivalent tests when you have limited sample sizes
(e.g., n < 30). Though nonparametric statistical tests have more
flexibility than do parametric statistical tests, nonparametric
tests are not as robust; therefore, most statisticians recommend
that when appropriate, parametric statistics are preferred.
The steps which guide a researcher in designing a questionnaire are:
the steps which guide a researcher in designing a questionnaire.
Advantages:
1. Questionnaires are inexpensive
First of all, questionnaires are one of the most affordable ways to
gather quantitative data.Especially self-administered
questionnaires, where you don’t have to hire surveyors to perform
face-to-face interviews, are a cost-efficient way to quickly
collect massive amounts of information from a large number of
people in a relatively short period of time.
A questionnaire can be placed on your website or emailed to your customers. These methods have little to no cost, though strong targeting is necessary if you want to have the highest possible response rate receive the most accurate results.
Still, no matter what type of questionnaires you pick, it will be more affordable than outsourcing to a market research company.
2. Questionnaires are practical
Apart from being inexpensive, questionnaires are also a practical
way to gather data. They can be targeted to groups of your choosing
and managed in various ways. You can pick and choose the questions
asked as well as the format (open-ended or multiple choice). They
offer a way to gather vast amounts of data on any subject. They can
be used in a wide variety of ways.
For example, KBC Group learned just how practical surveys are. They were able to spread their quizzes, polls, and questionnaires during a three-day event. This made collecting real-time feedback almost effortlessly.
3. Questionnaires offer a quick way to get results
questionnaire speedy results
It’s quick and easy to collect results with online and mobile
tools. This means that you can gain insights in as little as 24
hours (or less!), depending on the scale and reach of your
questionnaire.
You don’t need to wait for another company to deliver the answers you need.
Dajo Associates needed quality feedback fast. The South African consulting firm needed a way to make informed decisions quickly. An online questionnaire allowed them to collect the data they needed in the shortest time frame possible.
4. Scalability
Questionnaires and surveys allow you to gather information from a
large audience.
Online, you can literally distribute your questions to anyone, anywhere in the world (provided they have an internet connection). All you have to do is send them a link to your survey page. And you don’t even need to do this manually. This could be done through an automated email in your customer onboarding or lead nurturing campaigns.
This means that for a relatively low cost, you can target a city or a country.
You can use multiple data collection points, for example via multiple tablets in kiosk mode.
Geography no longer stands in the way of market research either, thanks to the internet. But be aware of cultural differences between people and countries when conducting worldwide research. Thanks to Survey Anyplace’s multiple languages feature, you can easily create a single questionnaire available in multiple languages.
5. Comparability
When data has been quantified, it can be used to compare and
contrast other research and may be used to measure change. This
makes monthly or yearly questionnaire more and more valuable over
time.
Improving comparability implies that errors due to translation have to be minimized. In terms of questionnaire translation for multi-national, multi-cultural and multi-regional surveys the aim is to achieve a level of comparability across all local versions.
6. Easy Analysis and visualization
Most survey and questionnaire providers are quantitative in nature
and allow easy analysis of results. With built-in tools, it’s easy
to analyze your results without a background in statistics or
scientific research.
Tools like Survey Anyplace offer easy to interpret reports and visualizations, meaning that you’ll quickly be turning your data into results. These results can be put in a wide variety of charts and tables to present them to your boss, colleagues, clients or customers.
Disadvantages:
1. Dishonest answers
vantagens e desvantagens dos questionários 6While there are many
positives to questionnaires, dishonesty can be an issue.
Respondents may not be 100% truthful with their answers.
This can happen for a variety of reasons, including social desirability bias and attempting to protect privacy. Stop dishonesty in its tracks by assuring respondents that their privacy is valued and that the process prevents personal identification.
2. Unanswered questions
When using questionnaires, there is a chance that some questions
will be ignored or left unanswered.
If questions are not required, there is always that risk they won’t be answered. Online questionnaires offer a simple solution to this issue: make answering the question required.
Otherwise, make your survey short and your questions uncomplicated and you will avoid question skipping and get better completion rates.
3. Differences in understanding and interpretation
The trouble with not presenting questions to users face-to-face is
that each may have different interpretations of your questions.
Without someone to explain the questionnaire fully and ensure each individual has the same understanding, results can be subjective.
Respondents may have trouble grasping the meaning of some questions that may seem clear to the creator.
This miscommunication can lead to skewed results. The best way to combat this situation is to create simple questions that are easy to answer.
4. Hard to convey feelings and emotions
vantagens e desvantagens dos questionários 7A survey or
questionnaire cannot fully capture emotional responses or feelings
of respondents. Without administering the questionnaire
face-to-face, there is no way to observe facial expression,
reactions or body language.
Without these subtleties, useful data can go unnoticed.
Don’t get stuck trying to interpret emotion in data, instead go for a Likert scale, the response scale that often uses a rating scale from “slightly agree” to “strongly disagree.” This allows for strength and assertion in responses rather than multiple choice.
5. Some questions are difficult to analyze
Questionnaires produce a lot of data. Multiple choice questions can
be tabulated and graphed, but open-ended questions are
different.
Open-ended questions allow for individualized answers which cannot be quantified and must be reviewed by a human.
Too many open-ended questions can produce a flood of data, that can take forever to analyze. Fix this pitfall but choosing your question types carefully. If you have ten questions, you probably don’t want more than one to be open-ended since these have no way to be quantified.
That’s why it’s important to select the right type of question as a questionnaire is only as effective as its questions.
The survey questions need to be evaluated quickly and they need to produce data that can be acted upon.
If you make questions too difficult or confusing to answer, you may end up with meaningless data.
Choosing the wrong type of question can also lead to incomplete results or data that is hard to interpret.
The main question types are open-ended, closed-ended and semi-closed ended questions. Within these types, there is an abundance of ways to present your query from ratings to yes/no question.
6. Respondents may have a hidden agenda
questionnaire-agendaAs with any sort of research, respondent bias
can be an issue.
Participants in your survey may have an interest in your product, idea or service. Others may be influenced to participate based on the subject of your questionnaire. These proclivities can lead to inaccuracies in your data, generated from an imbalance of respondents who see your topic in an overly positive or negative light.
Filter out a hidden agenda with a pre-screening. Come up with a few indirect questions that will remove those results wreckers.