The post Override Analysis Value appeared first on SnapSurveys.

Enter an expression describing the table cell data to insert the current table cell data into the report field, when you run the report.

The expression is defined as the table name, and an expression identifying the cell to be inserted. You can use the appropriate operators within the expression, e.g., A21 R1C1 – A22 R1C1 where both table cells contain quantities.

The cell referred to can be

• A row label description: tablename RNlabel.
• A column label description:  tablename CNlabel.
• A data cell described by its row and column number: tablename RNCN.
• A statistic value described by its row and statistic number, where the statistic number is the position in the list of statistics, S1 being the top, given by tablename RNSN.

You can also use the expression tablename empty to test if a specific table contains any data.

You can choose to modify the case and set the number of decimal places to display.

The post New Cell Value Field dialog appeared first on SnapSurveys.

If your table contains questions with multiple codes, you can decide whether the question text appears above the code labels or beside it.

1. Open the table to be changed
2. Click F2 or right-click and select Options from the context menu to open the Options dialog.

3. Change the options to include or exclude the labels as required.
4. Click OK to save the settings and see how they appear in a table.

The post Choosing what is displayed in a table appeared first on SnapSurveys.

You can specify how many lines you can use to write the text, and how big the cells are.

1. Open the table to be changed
2. Click F2 or right-click and select Styles from the context menu to open the Define Table Style dialog.
3. Select the areas of the table that you wish to alter in the left-hand pane.
4. Click in the appropriate place in the Alignment pane to change the position of the text in the cells.
5. Set the values in the Margins to set the distance of the text from the edges of the cells.
6. Click Apply to check the table looks the way you would like, and OK if satisfied.

Setting the size of cells

You can change the size of table cells by dragging the row and column borders. These changes will not be stored in the style file if you save it.

1. Move the mouse over the gap between columns until the cursor changes to a double-headed arrow.
2. Drag the column or row border to the position that you want.

Note that if the rows or columns have been set to Keep all the same size in the Cell Sizing dialog; when you drag one border, all the rows or columns resize together. If you want to drag them individually, you need to open the Cell Sizing dialog and clear Keep all the same size.

These changes are not automatically saved when the table is saved.

It is possible to set the size of the table cells to a fixed width/height so that it is stored in the style file.

1. Open the table to be changed.
2. Click F2 or right-click and select Sizing from the context menu to open the Cell Sizing dialog.

3. Choose from Best Fit, Fixed or Variable cell size for the Column Width and Row Height.
   • Best Fit lets Snap calculate the cell size according to their contents
   • Fixed lets you to set the size in the Size field displayed when this option is selected
   • Variable lets you drag the cell to set the size.
4. When you choose Best Fit you can check the Keep all the same size box to force all rows to have the same width or height.
5. Choose from Best Fit or Fixed for the Column Label Height or Row Label Width, as required.
6. Click OK to apply your settings. These settings will be saved if you save the style.

The post Changing the position of text and the size of table cells appeared first on SnapSurveys.

Defining how the lines will look

1. Open the table to be changed
2. Click , click F2 or right-click to select Edit Styles from the context menu open the Define Table Style dialog.
3. Select Blank in the Regions area to define how the inserted blank lines will look. You can then change the background color, font, gridlines etc as you would for any other row.
4. Select Highlight in the Regions area to define how the highlighted rows or columns will look. Note that any styling you apply to the Highlight region will overwrite any existing styling if a row or column is highlighted.

Defining which rows/columns will be blank or highlighted

1. Open the table to be changed.
2. Click F2 or right-click and select Separators from the context menu to open the Separators dialog.

3. Select Rows in the Area dropdown list to set the row highlighting. Select None in the Highlighting dropdown list to clear any row highlighting.
4. Choose By group to repeat the highlight pattern for each set of rows associated with a single variable; choose By item to use the highlight pattern across the whole table.
5. Set the number of the first row you wish to highlight in the Start at field, set the number of rows you want highlighted in the For field, and how far along you want the next block of highlighting to start in the Repeat every field. For example:

6. Select Columns in the Area dropdown list to set the column highlighting. Select None in the Highlighting dropdown list to clear any column highlighting.
7. Set the column highlighting in the same way that you have set the row highlighting.
8. Click OK to apply the highlighting to the table.

The post Changing the highlighting and spacing of rows and columns appeared first on SnapSurveys.

1. Open the table to be changed
2. Click , click F2 or right-click to select Edit Styles from the context menu open the Define Table Style dialog.
3. The Region field contains a list of all the areas of the table. Select one or more regions from the list.
4. Change the color of the lines by clicking the Gridline button in the Colour section.
5. To add or remove the lines of the selected regions click the lines in the Gridlines box.

• To remove all lines, select all the regions of the table and remove all the lines displayed in the Gridlines area by clicking on each line.
• To only show lines between the data rows.
  • First remove all lines as described above
  • Select Body in the Regions pane
  • Click the centre and bottom horizontal lines in the Gridlines area.

6. Click Apply or OK to save the changes.

The post Changing the lines between table rows and columns appeared first on SnapSurveys.

You can edit the way the table looks using the Table styles, Separators, Sizing and Options dialogs available from the context menu.

Loading table styles

You can load an existing style by

• selecting the style from the Style field of the Analysis Definition dialog
• right-clicking or pressing F2 in a table window and selecting Load Style from the context menu.

The table style files have the extension .tsf . Styles provided with Snap XMP Desktop are stored in the Styles sub-directory of the main Snap XMP Desktop folder.

Saving table styles

If you have altered the layout of a table and want to store this new design for future use, press F2 or click with the right-hand button of the mouse and select the Save Style option. This displays the file name of the style used to create the original table in the Save Style As dialog box.

Change the name in the File Name field, leaving the .tsf extension. Click OK to save the style.

The post Using table styles appeared first on SnapSurveys.

There are two ways to open the menu from the Table window

• right-click the table
• press the F2 function key

There are 11 different areas or regions in any table and any combination of these areas can be altered independently using the Edit Styles menu item. This allows you to change the way the contents of the rows and columns look. You can change the color of the text and background, the font used, and where the text appears. It is advisable to make consistent alterations to a table, such as all totals to be bold, all labels to be italics, etc. so that the table is easy to read.

• The Separators menu item allows you to specify highlighting of table rows and columns (for example, highlighting alternate columns so they are easier to read). You can also insert blank rows and columns to break up the table.
• The Sizing menu item allows you to force the table cells to be a specified size.
• The Options menu item allows you to decide whether the question label headings and totals rows and columns appear.

Defining the table style

Open the Define Table Styles dialog from an Analysis Display window displaying a table by

• Click   on the Analysis Display toolbar
• click F2 or right-click the mouse and select Edit Styles from the list displayed.

You can use this dialog to:

• Changing the lines between table rows and columns
• Changing the highlighting and separation of rows
• Changing the position of text in table cells

The post Table appearance appeared first on SnapSurveys.

This means: Is the difference in percentage scores in the table purely a result of the sample used, or does it indicate a real difference in percentages in the target population?

For each row in a table it compares the Break Percent for each column with all other columns. If more than one variable is included in the Break specification, the comparison will be among columns for the same variable only. That is, if “Age” and “Gender” are specified as separate break variables, the individual columns within the age variable will only be compared with other columns for “Age” and not with the columns for “Gender”.

Each cell of the table will contain the Break percent and a series of letters and hyphens. This is the output of the z-test and indicates which differences are significant and which are not significant, at the specified confidence levels.

The three possible characters and their meanings are:

• A hyphen, meaning the difference is not statistically significant
• A lower case letter indicating that the difference is statistically significant at the lower level specified
• An upper case letter indicating that the difference is significant at the higher level specified.

The letters and hyphens refer, in order, to the other columns within the variable (A refers to the first column, B to the second column and so on).

Example: Adding the z-test to a table in the Crocodile survey

1. Click on the Snap toolbar to build a table
2. Enter Q4 (Items ordered) in the Analysis field.
3. Enter Q11 (Age) in the Break field.
4. Check the Break Percents and z-test boxes on the right hand side. All other options should be clear.

5. Click the Base/Labels tab. Confirm that any missing values are excluded.

6. Click the Cells tab.

7. In the Body z-test section:
   • Set the Upper Level to 95% and the Lower Level to 90%
   • Select 2-Tail.
   • Select All in the Show box.
   • Check Hyphen and Index if these options are not already selected.
   • Clear the Apply Yates Correction box.

8. Click OK to create the table.

If you look at the cell for the row labelled “Coffee/Tea” and the column labelled “C. 25-34” the Z-Test output shows “Ab‑‑-”. This indicates that the differences between this column (C) and column A is significant at the upper level (upper case letters), the difference between this column and column B is significant at the lower level (lower case letters) but the differences between this column and the columns D,E and F are not significant (hyphens). Note that there must be at least one hyphen in the output as a column cannot be significantly different from itself.

The post Statistical significance in tables (z-test) appeared first on SnapSurveys.

1. Click to display the Analysis Definition dialog box.
2. Type into the Analysis (and Break) field the names of the variables on which you want to measure confidence. For example, type Q6a in the Analysis field and Q11:Q12 in the Break field.
3. Click on the Summary Statistics tab.
4. Select Mean in the Available list and click > to move it to the Used column.
5. Enter the name of the previously created Weight, Score5 in the Score field.

6. Click OK to display the table. Note that the score label has been added to the window title.

To display the confidence level for these statistics, go to the Summary Statistics tab of the Analysis Definition dialog and move Confidence (mean) into the Used pane. By default the confidence level is set to 95%.

The post Creating a table using a scoring system appeared first on SnapSurveys.

Confidence intervals on percentage values

The most common use of confidence intervals is when creating groups from a ratings scale. The table below shows a ratings scale for speed of service, broken down by age and gender.

It includes a satisfied scale, which is the percentage of respondents who selected either “Very Good” or “Good”. For the Base column in the table below, you can be 95% confident that the percentage of respondents in the target population satisfied with “Speed of Service” is in the range (53 – 5)% and (53 + 5)%; that is, between 48% and 58%. The size of margins varies according to the sample size and will generally be reduced with larger samples.

You have control over the following aspects:

• whether to show the Confidence Interval statistics (as above)
• the Level of Confidence
• which categories of the row variable represent the required group

How the confidence interval is calculated

Using an example of a question which:

• has 5 codes (“Very Good”, “Good”, “OK”, “Poor”, “Very Poor”)
• with a base of 389 respondents
• 53% of the respondents said that the service was “Very Good” or “Good” and the remaining 47% chose the other 3 categories

You can then calculate the confidence interval as follows:

The 95% confidence level has a constant of 1.96.

In the example, this gives:

i.e., a Confidence Interval of ± 5%

You can be 95% confident that 53% (± 5%) of the population are “Very Satisfied” or “Fairly Satisfied” with the service provided.

If tables are weighted then the calculation of the Confidence Interval will be based on the weighted results not the original cases.

Confidence intervals on means with scoring systems

The mean value is the value for the sample using a numerical scoring system for responses. The confidence interval is the likely range of mean values for the target population.

Using an example of a question which has 5 codes (“Very Good”, “Good”, “OK”, “Poor”, “Very Poor”), with a base of 204 respondents which uses a scoring system of: +2 for Very Good to – 2 for Very Poor the mean value and standard deviation will be calculated using these scores. You can then calculate the confidence interval as follows:

The post Confidence intervals in tables appeared first on SnapSurveys.

The example shows top and bottom boxes applied to a single rating question (with a Single Response) in a cross-tabulation.

1. Click to display the Analysis Definition dialog box.
2. Type into the Analysis (and Break) field the names of the variables on which you want to measure satisfaction. For example, type Q6a in the Analysis field and Q11:Q12 in the Break field.
3. Click on the Summary Statistics tab.
4. Select Confidence Top Box in the Available list and click > to move it to the Used column.

5. Check the details of the box. The example show the Confidence Top Box uses the first 2 out of 5 responses. This groups together the “Very Good” and “Good” codes.
6. The figure will be displayed as %Satisfied. You can select different text to display from the dropdown list.
7. For now, clear the Show confidence interval results…
8. Repeat for the Confidence Bottom box, using the last two codes out of five.
9. Click Apply to display the table.

To display the confidence level for these statistics, check the Confidence interval results box. By default the confidence level is set to 95%. This means that 95 times out of a hundred the true percentage for the target population is within the specified range based on the result for the sample. This also assumes the sample you have is a truly random sample from the target population.

In the table below, you would be 95% confident that the percentage of people in the target population satisfied with “Speed of Service” is in the range 53% +/ – 5%; that is, between 48% and 58%.

The post Creating a satisfaction scale (or other ratings scale) appeared first on SnapSurveys.

These allow you to:

• identify a typical value (the mean, median or mode)
• display how much the figures are likely to vary depending on the sample (standard deviation, standard error, variance, confidence)
• incorporate significance tests in your table (z-test, significance(t-test), t-test, U-test)

You can also use these statistics to group the responses to a single-response question (normally a ratings question), so you can immediately compare the high ratings to the low ratings. The high-ratings are known as the Top Box, and the low ratings are known as the Bottom Box. If you display these, you can also display how confident you are that the true population figure is within a specified range based on the sample results.

1. Click the Summary statistics tab of the Analysis Definition dialog.

2. Select the statistics you wish to add to your table in the Available pane. (Many of these will require you to apply a scoring system to the table.)
3. Use the > button to move them into the Show pane to add them to your table.

The post Displaying statistics in a cross-tabulation or frequency table appeared first on SnapSurveys.

1. Click to display the Analysis Definition dialog box.
2. Type the required variables names for the statistics in the Analysis field, separated by commas. For example Q11, Q12.
3. Select Statistics table from the dropdown list in the Break field (or type STATS in lower or upper case).
4. Click OK to build a table of descriptive statistics.

This type of table will not work with Multiple Response, Literal Response, Time or Date variables.

Selecting which statistics are displayed

1. Click the Descriptive Statistics tab of the Analysis Definition dialog.

2. Select items in the Available pane and use the > button to move them to the Used pane to add them to your table.
3. Move them back to the Available pane to remove them from your table.
4. You can change the order of the items in your table by selecting them and using the Move Up and Move Down buttons.

The post Creating a descriptive statistics table appeared first on SnapSurveys.

1. Click to display the Analysis Definition dialog box.
2. Type Q2 TO Q12 (the complete range of questions) into the Analysis field.
3. Select Holecount table from the dropdown list in the Break field (or type HOLECOUNT or COUNT in the field, in upper or lower case).
4. It is useful to display missing responses in the table. Click the Base/Labels tab to say what you do with responses of Errors, Not Asked and No Reply.
5. Select Show for Errors, Not Asked and No Reply in both the Analysis and Break columns.

6. Click OK to build the Holecount Table.

A number of the variables have zero values in all fields except Code 1. This is generally because the variables are open questions with a response of type literal, quantity, date or time and only 1 code is ever created. The Holecount Table will be built with as many codes as the question with the largest number of codes. Variables of the type Note are also included but will only show counts in the No Reply or Not Asked columns.

The post Creating a holecount table appeared first on SnapSurveys.

1. Click to display the Analysis Definition dialog box.
2. Type into the Analysis field Q6a TO Q6e.
3. Select Grid table from the dropdown list in the Break field (or type GRID in upper or lower case). If you leave the Break field blank, Snap assumes that you want a grid table because of the value you put in the Analysis field, but this can be confusing.

4. Click on Analysis Percents so that the percentages of the total of each row are included.
5. Click OK to build a grid table.

6. If you wish to alter the specification of the table, click .
7. If you specify the variables in the Break field and GRID in the Analysis field, the axes of the table will be reversed. Alternatively, select the option Transpose.
8. Click to save the table. The name will be generated by Snap. If you then wish to work on the table again, it is stored in the Analyses Window .

The post Creating a grid table appeared first on SnapSurveys.

This example uses the Crocodile Rock Cafe survey supplied with Snap XMP Desktop.

1. Click to display the Analysis Definition dialog box and type into the Analysis field Q6a. Type Q9 into the Break field.
2. Check Break Percents, which shows each answer as a percentage of the column totals for the break variable (Q9).
3. Press OK and a Cross-tabulation will be built, showing the values of Q6a as the row labels on the left-hand side of the table and the values of Q9 as the column labels across the top of the table.

4. To add more variables to the table, click to display the Analysis Definition dialog box, and use the word WITH to link the variables together. For example, Q9 WITH Q10. As an alternative to WITH use the : character.
5. Click to save the table. The name will be generated by Snap. If you then wish to work on the table again, it is stored in the Analyses Window .

The post Creating a cross-tabulation appeared first on SnapSurveys.

Creating a frequency table from a single variable

The example below uses ‘Q4: Which of the following items did you order?’ in the Crocodile Rock Cafe survey supplied with Snap XMP Desktop.

1. Click to display the Analysis Definition dialog box. Type Q4 in the Analysis field.
2. Click OK to create a frequency table that shows counts only.

3. Check Base Percents to express all answers as a percentage of the total number of respondents.
4. Select Analysis Base in the Order By drop-down list, so that the most frequently answered reply will be at the top of the table.
5. Click the Cells tab and check Suppress zeroes to hide any answers where the response count has been zero. (This option is normally used when a long list of codes exists for a question).

6. Click OK. This builds the frequency table.

7. Notice that the calculated percentages add up to a number greater than 100 because this question has a Multiple Response, so there are more responses than there are respondents.
8. To calculate the percentages to add up to 100, click and select the Base/Labels tab.
9. Change the Base field from Respondents to Responses. Rebuild the table to alter the method of calculation.

10. Click to save the table. The name will be generated by Snap. If you then wish to work on the table again, it is stored in the Analyses Window .

Creating a frequency table showing two variables

If you use more than one variable in a frequency table, then you can:

• display the details for the variables side by side (using the keyword WITH)
• look at each permutation of the two variables using the key word PER

The example uses the frequency of visit question (Q2) and the gender question (Q12) in the same table.

Displaying the variables next to one another

1. Click to display the Analysis Definition dialog.
2. Type Q2:Q12 into the Analysis field. Note that : is the short form of the key word WITH, which means that Q2 is analysed with Q12 next to it.
3. Check Base Percents to express all answers as a percentage of the Base figure.

4. Check Transpose to align the table horizontally rather than vertically.
5. Click OK to build the table.

Looking at each permutation of the variables

1. Click on to alter the specification of the table.
2. Change the text in the analysis field to Q2 PER Q12.
3. Click OK to build the amended table.

Note that the table shows all the male variations of the frequency of visit, followed by all the female variation of the frequency of visit.

4. Click to save the table. The name is generated automatically. The table can be edited using the Analyses Window .

The post Creating a frequency table appeared first on SnapSurveys.

When you have created a table, you can also add extra variables to the table by dragging them in from the Variables window. This is equivalent to adding an extra variable to the Analysis field using the WITH keyword.

Select the variable in the variable window drag it to the Analysis window.

As you drag the cursor over the table it changes from to one of these alternatives:

	insert above this row variable
	insert below this row variable
	replace all row or column variables with the new one
	insert to the left of this column variable
	insert to the right of this column variable

The post Adding variables to tables using drag and drop appeared first on SnapSurveys.

A table of results for one or more variables entered in the Analysis field. A frequency table displays the number of cases for the variable(s). Use WITH or a semi-colon to link them together. The maximum number of rows or columns is 2000 values. No value should appear in the Break field. (You can also build a frequency table from an expression in the Break field with nothing in the Analysis field.)

Cross-tabulation

This is a table where two or more variables are mapped against each other. One set appears in the Analysis and the other in the Break field. Use WITH (:) or PER to link multiple variables. A cross-tabulation displays the data for cases that appear in both categories.

Grid table

Used for tabulating grid questions. Enter the word TO or ~ between the first and last grid question numbers in the analysis field or list questions separated by commas. You can also enter the word GRID in the Break field or select Grid table from the dropdown list.

Holecount table

Holecount tables display the counts in the variables, as the code labels do not appear: just Code 1, Code 2, etc. They are a useful method of checking the accuracy of data entry and a simple way of highlighting areas with possible errors prior to full analysis of the survey. Select Holecount table from the dropdown list in the break or analysis field.

Descriptive statistics table

Statistics tables display a selection of statistics about the variable. Enter the word STATS or select Statistics table from the dropdown list in either the Analysis or Break field. Statistics can be calculated on any variable or list of variables, although most benefit is achieved when analysing variables with a response of Quantity.

The post Types of table appeared first on SnapSurveys.