• User Interface – better viewing of reports display
• Advance Segmentation – used for analyzing unlimited subsets of your website’s traffic which is easier to use with the drag and drop segment builder
• Account Management – an easier way to manage all your accounts through simpler navigation and dashboard preferences upon login
• Adsense Integration – Adsense performance can be broken down more by page and referring site which allows publishers to optimize AdSense units as well as improve user experience
• Custom Reporting – organize metrics how you want to view it
• Data Visualization – with the development of motion charts, you can do multidimensional analysis like trend of metrics over time
• API – “enables you to create software programs and applications using all read-only report level data from Analytics”

Here are some basic steps in doing Survey Research.

1. Determine what you want to examine. Why are you performing a survey in the first place? What would people think regarding some product you are going to launch? Are your customers satisfied with the services you are offering? Have, first, a specific issue you would want to solve.
2. Define the population to be studied. Okay, so you’ve got your problem identified. Now you need to establish who you want to address. Are you sure you are asking the right crowd? If they could not relate to any of the topics you are throwing, you’re shooting the wrong board. To illustrate: you do not inquire first time visitors of your site if they enjoy discounts offered only to members.
3. Time to write the survey. Write and revise and revise until you perfect it.
4. Select a sample. In step 2, you have just identified who you want to study. You’d exhaust time and a lot of effort before you finish if, say, you have a hundred thousand subjects to survey. You cannot simply decide “Oh I only want to survey a hundred of them.” You need to compute for the sufficient sample size so reliability will not be a problem in your outcomes.
5. Oversee the survey. There is nothing wrong in checking the results once in a while. At least you will have a sight on how your survey is doing, if your response rate is low, etc.
6. Last is the fun and messy part – analyzing and interpreting the results. Nothing could be more rewarding than completing the puzzle – having explanations and conclusions to your thesis.

An interesting find in doing surveys – there is always additional information which you can derive from your data. For instance, you can find correlations among variables when doing cross tabs, or you would be surprised to see a totally different point of view in open-ended questions, etc.

The Invitation

• One way to start the survey could be by stating “you have been randomly selected…” Be careful in using words like this. Saying “I choose/pick, etc. …” for a start already gives the impression of your would-be-results to be biased.
• ALWAYS state the purpose of your survey. Would you, yourself, dare answer some paper without knowing what it is for? A short introduction at the top of the page would do. It serves like the direction before answering your final exam.
• If your survey requires answerers to indicate their name then you should follow the ethics for survey research which specifies that respondent profiles must be kept confidential. Publishing of names of respondents is ground for breach of contract.
• Be respectful. If some do not wish to participate in answering or completing the questionnaire then you should regard their decision. Resending surveys to those who’ve unsubscribed to your list, and/or insisting them to finish the survey, is plainly annoying.

The Questions

• Make the survey visually appealing. Use readable font.
• Never ask leading questions. Subtly prompting respondents to answer in a particular way results in false or slanted information. Avoid assumptions in the inquiry itself – answers should be on the choices not the questions.
• Use simple language. Highfaluting words are for novels and narratives. Surveys use words which are easy to understand.
• Write short questions – clear and direct to the point. Make sure your thoughts are pieced together. Consider one concept per question to prevent confusing your respondents.
• Group similar questions so that the survey is easy to follow.
• In using words like “will,” “may,” “might” or “could” which may be time-related, remember to specify your time frame.

The Choices

• Wordings of choices should be consistent. Scalar options are more likely paired. A five-scaled choices example would be (a)Very Satisfactory, (b)Satisfactory (c)Neutral, (d)Unsatisfactory and (e)Very Unsatisfactory.
• For non-scalar choices, provide a “Other (Please Specify)” because more likely, not all your respondents would pick what is laid in front of them. If choices to “What is your favorite fruit” are only apple, grape, and banana but your buyer’s real favorite is mango, and then which option box should he check?

Don’t forget to thank the respondent after finishing the questionnaire. Take note that a few small mistakes in these could affect the attitudes and decisions of people being studied. Research more on how to write surveys. Double check or consult someone about your paper before actually sending it out. There are lots of resources you can find in doing so. Don’t limit yourself!

Statistical significance, since it is based on a computation with some elaborate probability and confidence level, gives a more scientific basis to claim if two or more means (or measures of central tendency; proportions/rates; data distributions; and independence of data among k groups) are considerably different. Knowing the significant difference between two mean or more means gives us sufficient evidence to decide that one value is much higher or lower than the other and if they are, it would imply another meaning to just declaring “We hit the target sales by 30!” or something like that.

Before delving into your actual testing, you need to understand the requisites in doing significance testing.

• Null Hypothesis – Every test of significance starts with this. It is a speculation usually believed to be true but has not yet been proven. By the way, in a statistical point of view, the null hypothesis is commonly stated as an equality so for an instance, my null hypothesis could be that “Changing the color of the call to action button, from the default blue, to green does not increase customers click through it”
• Alternative Hypothesis – This is the statement you want to result to. An alternative to the statement above may be “Click through on green call to action button is higher than the blue one.”
• α, the Level of Significance – The criterion used for rejecting the null hypothesis
• Test Statistic – A random variable which value serves to determine the conclusion
• Critical Value – A tabular value that the test statistic needs to exceed in order to reject the null hypothesis. This goes hand in hand with α.

Now that these terms have been introduced, following the steps in statistical testing would be easier. Comparing the status of the site’s key metrics through their significant difference over the past few months will give more meaning to data. This will also give Web Analysts more confidence when reporting the real impact of the increase and decrease of the site’s key metrics.