Quantitative Research: Interval Scales and Questionnaires
Understanding Interval Scales
The interval scale is a type of metric scale that focuses on quantitative values. An interval scale can always be divided into equal portions. This means the difference between any two values is equivalent to the difference between any two adjacent values of an interval scale.
The most common example is a Celsius temperature scale in which the difference between the values is the same. The difference in temperature between 10 and 20 degrees is the same distance as between 40 and 50 degrees.
Questionnaires in Quantitative Research
Questionnaires are used in quantitative research. In order to acquire all the data properly, one must avoid several things:
- Avoid long or general questions: These make the questions less precise.
- Avoid technical terms: These may make the respondent reluctant to answer some of the questions if they are difficult to understand.
- Avoid poor phrasing: Poor phrasing of a question will cause respondents to skip it and not answer it, or they will answer the question incorrectly.
- Avoid ambiguous terms: For example, “often, regularly, frequently”.
- Avoid asking two questions in one.
- Use precise number scales: Avoid confusing wording like “a week, more or less, it is about…”.
- Maximize responses: People have short attention spans.
- Avoid open-ended questions.
- Avoid negatives and double negatives: For example, “they are disagreeing with not doing something”.
- Rank scale questions in order.
- Provide enough options for the respondent to choose from.
- Do not force people to answer all the questions.
When to Use Regression
We use regression when we need to measure the association between two variables when both have interval or ratio scales.
Independent T-Test Example
This independent T-test compares the means of two colors: Color 0 = Red was chosen more by the respondents, and color Green was less likely chosen. Red is closer to 7 with a 6.4, and Green further away with a 4.2. There is a higher variance in the Green color 3.89 than in the Red one, meaning the numbers were further apart from the average value. An equal number of people took the test. The table below does not provide more information to be compared between the two, so what I can say is that the willingness to buy can be determined by the mean on the first row. The higher mean of the Red color shows that there were more people choosing that option rather than choosing the Green color.
Understanding Multiple R and R-Squared
Multiple R is the correlation coefficient, and it tells us how strong the linear relationship is. The value 0.3 is closer to zero, meaning there is very little relationship between the two variables (attitude and willingness to pay). The R-squared tells us how many points fall on the regression line. The value 0.096 clearly shows us that there are very few points that fit this line, meaning there is not a linear correlation. The adjusted R-squared is used when there is more than one value, so we can disregard this data.
The standard error of regression is the precision that the regression coefficient is measured. The standard error is large with a value of 16.59. This value tells us how strong the regression model is. Big values indicate that the observations are further away from the fitted line. Unlike the R-squared, we can use the standard error of regression to assess the precision of the predictions.
Qualitative Research: Consumer Insights on Organic Chips
Understanding the underlying reasons to buy these and their opinions will help the company develop a hypothesis for any kind of further investigations. The in-depth interview explores individual experiences and the consumers’ perceptions in rich detail. Open-ended questions will help the respondent answer broadly and the company get a good sense of what consumers personally think. I would personally structure the qualitative study (interview) in the following way:
Introduction
The purpose of this interview is to know what are the reasons that would encourage consumers to try these new organic chips. I would encourage you to speak out confidently and to be as sincere as possible, highlighting positive and negative aspects of the company, as well as your thoughts and opinions about Lay’s incorporating organic chips into the market.
Questions
- What do you think about/what are your feelings when someone says they bought a bag of Lays?
- How did you get to know the brand?
- What do you associate organic chips with?
- Can you describe an organic brand?
- Can you describe the brand Lays?
- Would you prefer buying organic chips rather than regular chips?
- What role do chips play in your household?
- How often do you buy chips?
- Do you find the word “organic” to have beneficial connotations?
- What are the attitudes of adults towards organic foods in general?
- What strategies are being used to incentivize the consumption of organic foods?
- Do you associate organic foods to be more expensive?
- Do you think organic foods are healthier?
- Do you feel Lay’s should incorporate a healthier look to processed chips?
I personally think that with the questions stated above, we should be able to gather a wide variety of answers. The opinions of the consumers could help Lay’s incorporate their organic chips wisely. This kind of exploratory research could be done in a focused group or a small sample size in order to maximize results of a given region.