Thurstone Scale, Likert Scale and Semantic Differential Scale
A Thurstone scale has a number of “agree” or “disagree” statements. It is a unidimensional scale to measure attitudes towards people. Developing the scale is time consuming and relatively complex compared to other scales (like the Likert scale).
Although there are technically three scales, when people refer to the “Thurstone Scale” they’re usually talking about the method of equal-appearing intervals. It’s called “Equal appearing intervals” because when you choose the items for your test (see Step 6 below), you’re picking items equally spaced apart.
The other two variations are:
- The method of successive intervals: this method is more challenging to implement than equal-appearing intervals.
- The method of paired comparisons: requires twice the judgments than the equal-appearing intervals method and can quickly become very consuming.
The three methods differ in their construction, but still result in the same Agree/Disagree quiz given to respondents.
Method of Equal-Appearing Intervals
Step 1: Develop a large number of agree/disagree statements for a topic. For example, if you wanted to find out people’s attitudes towards immigrants, your statements might include:
- Immigrants drain social services.
- Immigrants take jobs away from regular people.
- Immigrants perform low-wage, unpopular tasks.
Step 2: Have a panel of judges rate the items on a scale of 1 to 11 for how favorable each item is towards the topic (in this case, immigration). The lowest score(1) should indicate an extremely unfavorable attitude and the highest score(11) should indicate an extremely favorable attitude. Note that you do not want the judges to agree or disagree with the statements — you want them to rate the statements on how effective they would be at uncovering attitudes.
Step 3: Find the median score and interquartile range (IQR) for each item. If you have 50 items, you should have 50 median scores and 50 IQRs.
Step 4: Sort the table in ascending order(smallest to largest) by median. In other words, the 1s should be at the top of the table and the 11s should be at the bottom.
Step 5: For each set of medians (i.e. 1s. 2s, 3s) sort the IQRs by descending order (largest to smallest).
The figure below shows a partial table with the data sorted according to ascending medians with their respective, descending IQRs.
Step 6: Select your final scale items using the table you created in Step 4 and 5. For example, you might choose one item from each median value.
You want the statements with the most agreement between judges. For each median value, this is the item with the lowest interquartile range. This is a “Rule of Thumb”: you don’t have to choose this item. If you decide it’s poorly worded or ambiguous, choose the item above it (with the next lowest IQR).
Various kinds of rating scales have been developed to measure attitudes directly (i.e. the person knows their attitude is being studied). The most widely used is the Likert Scale.
Likert (1932) developed the principle of measuring attitudes by asking people to respond to a series of statements about a topic, in terms of the extent to which they agree with them, and so tapping into the cognitive and affective components of attitudes.
Likert-type or frequency scales use fixed choice response formats and are designed to measure attitudes or opinions (Bowling, 1997; Burns, & Grove, 1997). These ordinal scales measure levels of agreement/disagreement.
A Likert-type scale assumes that the strength/intensity of experience is linear, i.e. on a continuum from strongly agree to strongly disagree, and makes the assumption that attitudes can be measured. Respondents may be offered a choice of five to seven or even nine pre-coded responses with the neutral point being neither agree nor disagree.
In its final form, the Likert Scale is a five (or seven) point scale which is used to allow the individual to express how much they agree or disagree with a particular statement.
I believe that ecological questions are the most important issues facing human beings today.
Strongly agree / agree / don’t know / disagree / strongly disagree
Each of the five (or seven) responses would have a numerical value which would be used to measure the attitude under investigation.
Likert Scale Examples
- Strongly Agree
- Strongly Disagree
- Very Frequently
- Very Important
- Moderately Important
- Of Little Importance
- Almost Always True
- Usually True
- Occasionally True
- Usually Not True
- Almost Never True
How can you analyze data from a Likert Scale?
(i) Summarize using a median or a mode (not a mean); the mode is probably the most suitable for easy interpretation.
(ii) Display the distribution of observations in a bar chart (it can’t be a histogram, because the data is not continuous).
Likert Scales have the advantage that they do not expect a simple yes / no answer from the respondent, but rather allow for degrees of opinion, and even no opinion at all. Therefore quantitative data is obtained, which means that the data can be analyzed with relative ease.
However, like all surveys, the validity of Likert Scale attitude measurement can be compromised due social desirability. This means that individuals may lie to put themselves in a positive light. For example, if a likert scale was measuring discrimination, who would admit to being racist?
Offering anonymity on self-administered questionnaires should further reduce social pressure, and thus may likewise reduce social desirability bias.
Paulhus (1984) found that more desirable personality characteristics were reported when people were asked to write their names, addresses and telephone numbers on their questionnaire than when they told not to put identifying information on the questionnaire.
SEMANTIC DIFFERENTIAL SCALE
The Semantic Differential Scale is a seven-point rating scale used to derive the respondent’s attitude towards the given object or event by asking him to select an appropriate position on a scale between two bipolar adjectives (such as “warm” or “cold”, “powerful” or “weak”, etc.)
For example, the respondent might be asked to rate the following five attributes of shoppers stop by choosing a position on a scale between the adjectives that best describe what really the shoppers stop means to him.
The respondent will place a mark anywhere between the two extreme adjectives, representing his attitude towards the object. Such as, in the above example, the shoppers stop is evaluated as organized, cold, modern, reliable and simple.
Sometimes the negative adjectives are placed on the right and sometimes on the left side of a scale. This is done to control the tendency of the respondents, especially those with either very positive or negative attitudes, to mark the right or left-hand sides of a scale without reading the labels.
The items on a semantic differential scale can be scored on either a numerical range of -3 to +3 or 1 to 7. The data obtained are analyzed through profile analysis. In profile analysis, the means and medians of the scale values are found out and then are compared by plotting or statistical analysis. Through this method, it is possible to compare the overall similarities and differences among the objects.
The versatility of the semantic differential scale increases its application in the marketing research. It is widely used in comparing the brand, company image, and product. It also helps in developing an advertising campaign and promotional strategies in new product development studies.