Insight Discovery Survey Report©
The survey report of online survey providers like SurveyMonkey, Zoho Survey, SurveyGizmo, etc. isn`t enough to drill into the data and discover useful, hidden marketing insights.
Insight Discovery Survey Report© bridges the gap between the superficial survey reports of online providers and the expensive reports of professional market research agencies.
MarketingStat analyzes your survey data just as top-tier marketing research agencies do. For just a fraction of the price.
How is that possible?
Thanks to our extensive experience in the field of marketing research and our ability to write efficient software code.
Our analysts have headed up the Marketing Research & Strategic Insights role at renowned multinational companies and consulting agencies. They know how surveys and survey reports work. Their priceless experience made it possible to develop proprietary software that allows MarketingStat to deliver valuable insights to business people, students, and instructors in a fast, professional, and convenient manner.
A survey without a professional report is like a Ferrari without an engine. It is a huge waste.
Assign your important survey report to a professional analyst.
MarketingStat can help – At a price even students can afford!
What’s inside the Insight Discovery Survey Report©
MarketingStat’s Insight Discovery Survey Report© includes 10 sections where you will find all you need to dig into the survey data in a granular manner. Moreover, you will also find all the necessary values to build even complex scenario simulations:
- Sample Size Analysis
- Survey Dataset
- Cross tables in both directions (with row totals and column totals)
- Descriptive Statistics and Box-Plots
- Correlation Analysis
- Euclidean Distance Matrix
- Probability Distribution Fitting
- Cluster Analysis
- Segmentation Tree
- Perceptual Maps (Brand Mapping)
On request we can also:
- Get the survey data in shape and ready for analysis
- Code text, such as open-end questions, comments from socials, and the like
- Recruit respondents to your online survey
Our Insight Discovery Survey Report.
All you need to deliver a better job.
Sample Size Sensitivity Analysis
Sampling is like cooking spaghetti. You try one strand to see if they are all cooked. But you run the risk of saying the pasta is cooked when it is not.
Making a mistake when cooking at home may be disappointing.
But how much risk are you taking when making decisions with an online sample survey?
The Sample Size section of the Insights Discovery Report© tells you exactly this: The amount of risk your sample carries.
Learn how to plan the sample design and how to evaluate the sample size of surveys. You will make better decisions because you will be fully informed on the capability of your surveys to deliver the information you are looking for.
Knowing the amount of risk implied in a sample:
- Helps in fine-tuning future surveys
- Helps in interpreting data correctly
- Is a valid source for academic and professional papers
Cross Tables – Both Column and Row Directions
There is a reason why contingency tables, aka cross tables or crosstabs, are perhaps the most important segmentation tool used by professional survey analysts.
An old saying goes “You cannot swallow an elephant but you can eat it one slice at the time”. Contingency tables are the tool that slices the elephant.
CrossTabs enable you to dig deep into survey data in a systematic way, to turn data into information that can ignite the capacity to generate insights.
In a two-way cross-table two variables, the answers to two questions, are crossed and presented in the form of counts. For instance, we ask 96 men and 129 women whether they smoke or not. The professional cross tabulation of the two variables would look like table 1 below, where we read 46 Male respondents said they smoke and 50 don’t while Females are 55 to 74 smokers to non-smokers.
In turn counts are converted to percentages, to help the analyst figure out the proportions between sub-groups of respondents. Proportions, or percentages, are important because they can identify groups or clusters of respondents with common characteristics, they help in prioritizing, and, very important, percentages allow testing the significance of their differences.
What does testing the significance of the difference of two proportions mean?
Take table 1: of the 96 male respondents 47.9% said they smoke and 52.1% said they don’t. One could be tempted to state non-smokers outnumber smokers by 4.2%, but this wouldn’t be true. In fact, we are reading the results of a survey conducted at the 95% confidence level and an error level equal to 6.53%. Therefore, in order to confirm the proportion of non-smokers is higher than that of smokers it is necessary to test the significance of the difference between the two proportions (4.2%). The question becomes: Is the 4.2% difference between smokers and non-smokers large enough to state that the quantity of the latter is really larger than the former? In our case, with a sub-sample of 96 male respondents, the difference is not large enough to confirm the two proportions differ. In this case we must read the percentages as two equal numbers, say 50% and 50%. There is a difference, however, between the proportions of female smokers and non-smokers (see red arrow).
MarketingStat’s Insight Discovery Report applies the Z-Test at the 95% confidence level to verify the significance of differences.
How much risk are you taking with your online sample?
MarketingStat’s Insight Discovery Survey Report helps you find out!
Order brings clarity and helps in understanding things better.
This section of the Insight Discovery Survey Report bring order to your survey data.
Your survey data is coded appropriately and is stored in an Excel sheet ready for additional analysis.
No time to prepare your survey data for analysis?
No worries. We do it for you.
Both close- and open-end variables (survey answers) are coded, so they can be easily turned into useful contingency tables and more.
Bring order to your surveys.
Squeeze out all the information you worked hard to find.
MarketingStat professional survey reports can help!
Descriptive Statistics and Box-Plots
The Descriptive Analysis section of the Insight Discovery Report© makes available the basic elements of survey data analysis.
For each variable of the survey we deliver a number of descriptive statistics to increase understanding of the survey results. Together with the box-plots they are the first step to making better informed decisions.
The descriptive statistics, together with the report sections Correlations, Euclidean Distances, and PDF (stands for Probability Distribution Functions), supply a detailed view of the main variable parameters that is useful when building even rather complex scenario models.
In turn, scenario models are often simulated with the Monte Carlo technique.
Don’t be left behind.
Learn how today’s marketing champions handle surveys.
Probability Distribution Functions
This section is of great value to advanced users using survey results to populate scenario models simulated with the Monte Carlo technique.
For each variable we create a histogram with the frequencies of the respondent’s answers, to have a visual hint of the shape of the distribution, aka Probability Distribution Function (PDF). This helps in fitting an appropriate PDF to simulate the process.
Moreover, for each variable we test which PDF’s fit is better and list the results as shown in the image below. For instance, the Poisson PDF fits the process depicted in the chart above well (low Fit Index equal to 0.2083).
To reproduce the process in a simulation model all we have to do is to enter a Poisson PDF with coefficient 4.1813. This is great value for managers dealing with simulation models, and the time saving is also huge.
Move to the next level of decision-making.
MarketingStat can help!
Understanding the strength of the relationship between variables may help in avoiding redundant analyses, and sometimes finding very useful constructs, such as those concerning emotions and beliefs.
The Insight Discovery Report includes a matrix of correlation values computed according to the nature of the variable data.
Continuous variables, like age, income, or time to execute, for instance, are treated with the Pearson’s correlation coefficient, whereas we use the Spearman’s correlation coefficient with discrete variables.
It must be remembered that correlation does not mean causation. Just because two variables are correlated does not mean one causes the other. Once you are aware of this, correlation analysis is definitely a technique every decision-maker must learn.
The bottom line:
It’s not about how many tools you have.
It’s about using the right tool at the right time.
Euclidean Distance Matrix
Distance metrics are broadly used segmentation instruments. There are different kinds, all used to determine the distance between pairs of elements of a matrix.
For instance, survey data are typically arranged in a matrix where the columns represent the answers to the survey questions (variables) and each row represents all the answers of a single respondent.
Computing the distance between all pairs of the matrix columns or rows allows grouping the elements in segments so that data within any segment are similar (aka homogeneous groups) while data across segments are different.
MarketingStat’s Insight Discovery Report© supplies the complete distance matrix of all variables of a survey. Moreover, the survey rows (respondents) are grouped using the Cluster Analysis Ward’s method.
You won’t get a better survey report than MarketingStat’s.
Are you looking for homogeneous groups? The Cluster Analysis (CA) of the Insight Discovery Report is the right place to look.
For each report we run two separate CA’s to find:
- Groups among respondents (for instance 320 interviews)
- Clusters among variables (or questions).
Alone these two views shed valuable light on hidden aspects underlying your survey data.
The dendrogram is a valid and intuitive tool to grasp at a glance the data structure. The sooner two variables group together the more homogeneous their group. It’s that simple.
We apply the Ward’s clustering method because it automatically finds the number of clusters in the data, reducing any analyst bias.
Can you imagine how many major groups the histogram suggests the CA found in our data?
And can you find these groups on the dendrogram above?
If it’s homogeneous groups you are looking for,
MarketingStat’s Insight Discovery Report© helps you find ’em!
When the relationship between data is more important than the data itself, an association map is the best way to visualize those relationships.
We apply Correspondence Analysis to draw perceptual maps like this, and we call it Brand Mapping.
These maps are easy to interpret and extremely rich in information. Moreover, their interpretation can be made in light of the analyst’s prior knowledge, which is a great way to stimulate strategic thinking. Modern, best-in-class marketers love this tool.
Read the book:
Mapping Markets for Strategic Purposes. It is the best source to learn about Brand Mapping.
Read also this article on Brand Mapping:
Our maps are different because we also apply Cluster Analysis to find clusters on the map. This extension of the analysis is extremely useful especially when analyzing competitive environments, such as a market.
Ask consumers and put, for instance, brand names and profiling statements on a map. You will see the market, its players, and their strategic positioning all on the same map.
This is perhaps the most important reason why these sorts of strategic maps are so beloved by strategic minded decision-makers.
The power of mapping.
It is visual. It is clear. It is strategic.
The Segmentation Tree of the Insight Discovery Report© helps identify homogeneous groups according to a characteristic, a variable you select.
Say you interviewed vitamin users and now you want to classify them in terms of consumption. Using survey data like demographic and psychographic variables, and a discriminant variable, in our case Consumption of vitamins (yes or no), MarketingStat’s Segmentation Tree produces useful segments.
Segmentation Tree applies William Belson’s original algorithm on matching and prediction, which inspired a number of algorithmic extensions such as AID (Automatic Interaction Detection) and CHAID (Chi Square Automatic Interaction Detection), THAID (Theta AID), and CART (Classification and Regression Trees).
This tool complements the Cluster Analysis section of the report. They are both multivariate techniques, but while Segmentation Tree puts emphasis on the predictor variable, Consumption in our example, Cluster Analysis emphasizes the whole variable set.
It is the perspective from which we look at something that often helps us understand what we are looking at. And this is exactly the reason why the Insight Discovery Report looks at your data from so many different angles.
Change your perspective. Discover more.
MarketingStat can help!