- Statistics Tutorial
- Adjusted R-Squared
- Analysis of Variance
- Arithmetic Mean
- Arithmetic Median
- Arithmetic Mode
- Arithmetic Range
- Bar Graph
- Best Point Estimation
- Beta Distribution
- Binomial Distribution
- Black-Scholes model
- Central limit theorem
- Chebyshev's Theorem
- Chi-squared Distribution
- Chi Squared table
- Circular Permutation
- Cluster sampling
- Cohen's kappa coefficient
- Combination with replacement
- Comparing plots
- Continuous Uniform Distribution
- Continuous Series Arithmetic Mean
- Continuous Series Arithmetic Median
- Continuous Series Arithmetic Mode
- Cumulative Frequency
- Co-efficient of Variation
- Correlation Co-efficient
- Cumulative plots
- Cumulative Poisson Distribution
- Data collection
- Data collection - Questionaire Designing
- Data collection - Observation
- Data collection - Case Study Method
- Data Patterns
- Deciles Statistics
- Discrete Series Arithmetic Mean
- Discrete Series Arithmetic Median
- Discrete Series Arithmetic Mode
- Dot Plot
- Exponential distribution
- F distribution
- F Test Table
- Frequency Distribution
- Gamma Distribution
- Geometric Mean
- Geometric Probability Distribution
- Goodness of Fit
- Grand Mean
- Gumbel Distribution
- Harmonic Mean
- Harmonic Number
- Harmonic Resonance Frequency
- Hypergeometric Distribution
- Hypothesis testing
- Individual Series Arithmetic Mean
- Individual Series Arithmetic Median
- Individual Series Arithmetic Mode
- Interval Estimation
- Inverse Gamma Distribution
- Kolmogorov Smirnov Test
- Laplace Distribution
- Linear regression
- Log Gamma Distribution
- Logistic Regression
- Mcnemar Test
- Mean Deviation
- Means Difference
- Multinomial Distribution
- Negative Binomial Distribution
- Normal Distribution
- Odd and Even Permutation
- One Proportion Z Test
- Outlier Function
- Permutation with Replacement
- Pie Chart
- Poisson Distribution
- Pooled Variance (r)
- Power Calculator
- Probability Additive Theorem
- Probability Multiplecative Theorem
- Probability Bayes Theorem
- Probability Density Function
- Process Capability (Cp) & Process Performance (Pp)
- Process Sigma
- Quadratic Regression Equation
- Qualitative Data Vs Quantitative Data
- Quartile Deviation
- Range Rule of Thumb
- Rayleigh Distribution
- Regression Intercept Confidence Interval
- Relative Standard Deviation
- Reliability Coefficient
- Required Sample Size
- Residual analysis
- Residual sum of squares
- Root Mean Square
- Sample planning
- Sampling methods
- Shannon Wiener Diversity Index
- Signal to Noise Ratio
- Simple random sampling
- Standard Deviation
- Standard Error ( SE )
- Standard normal table
- Statistical Significance
- Statistics Formulas
- Statistics Notation
- Stem and Leaf Plot
- Stratified sampling
- Student T Test
- Sum of Square
- T-Distribution Table
- Ti 83 Exponential Regression
- Trimmed Mean
- Type I & II Error
- Venn Diagram
- Weak Law of Large Numbers
- Z table
- Statistics Useful Resources
- Statistics - Discussion
- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who
Statistics - Data Collection
The data required for a research can be primary or secondary in nature. Primary data, by definition is the date that has been collected first hand by the researcher specially for addressing the population at hand. A survey research can be objectivist or subjectivist in nature. An objectivist approach is a more rigid and scientific approach. In this the hypothesis is tested using publicly standard procedure. There is little or no latitude available to deviate from the stated procedures or questions. A subjectivist approach, requires a hypothesis test, but is not that rigid in following the procedures. The researcher is allowed to use unstructured methods, at his discretion, to record data. The research data can be classified as follows:
A form of communication approach to collecting data from respondent's interview is to oral or verbal questioning. Bingham and Moore have described interview as 'conversation with a purpose.' Lindsey Gardner, has defined interview as a 'two-person conversation, initiated by the interviewer for the specific purpose of obtaining research-relevant information and focused by him on the content specified by the research objectives of description and explanation.
It is thus clear that interview is a verbal conversation between two people with the objective of collecting research relevant information from the respondent. Interview can be classified into various types' viz., personal interview, telephone interview, focus group interview, depth interview and projective techniques also called as indirect interviewing.
Type of Interview
The interview techniques can be grouped in the following categories:
A Personal interview is a face to face way communication between the interviewer and the respondent. Generally the personal interview is carried out in a planned manner and is referred to as 'structured interview'. The personal interviews can be conducted in many forms e.g. door to door interviewing where the respondents are interviewed in their home, or as planned formal executive meeting, most commonly used to interview officials and business persons, or as a mall intercept survey where respondents are interviewed at select places where the chances of finding respondents is maximum.
Method of Conducting an Interview
A personal interview involves a lot of preparation. Generally an interview should go through the following stages.
Rapport Building - The first reaction of a respondent on being asked to give interview is to say 'No'. Hence in the initial stage the interviewer should increase the receptiveness of the respondent by making him believe that his opinions are very useful to the research, and the interview is going to be a pleasure rather than an ordeal. It is important that the interviewer should convey his confidence to the respondent and satisfy his mental reservations if any. Wherever possible an appointment should be sought.
Introduction - An introduction involves the interviewer identifying himself by giving him his name, purpose and sponsorship if any. An introductory letter goes a long way in conveying the study's legitimacy. If the respondent is unavailable, then the interviewer should ensure that he seeks a reappoint.
Probing - In this stage the interviewer collects data by asking questions from an interview schedule which contains questions in prearranged sequence. Generally the questions should be asked the way they are worded in order to avoid bias, but if they are not understood or heard properly they may be repealed. An advantage of interview is that it allows for probing. Probing is the technique of encouraging the respondents to answer freely, completely and relevantly. Some of the frequently used probing styles are use of comments like "I understand", "Uh-huh", repeating the respondents reply to incite him to rethink his reply, give an expectant out pause to convey interest etc. However probing should be used carefully and should not bias the respondent's reply.
Recording - The last stage in an interview, is recording responses. The interviewer 'can either write the response at the time of interview or after the interview. Normally, the recording should take place side by side. The interviewer can use short hand and abbreviate responses. Recording response later on has the disadvantage that one way forgets what had been said earlier. In certain cases, where the respondent allows for it, audio or visual aids can be used to record answers.
Closing - After the interview is over, the interviewer should thank the respondent and once again assure him about the worth of his answers and the confidentiality of the same.
In telephone interviewing the information is collected from the respondent by asking the questions on phone. The marriage of telephone and computer has made this method even more popular. Traditional telephone interviews call for phoning a sample of respondents, asking them questions written on a paper and recording them with a pencil. In case of Computer Assisted Telephone Interviewing (CATI) uses a computerized questionnaire is used which prompts the interviewer with introductory statements, and qualifying questions to be asked to the respondents.
The computer replaces the paper and pen. The computer randomly dials a number from the sample; upon contact the interviewer reads the questions and diret1y into the computer's memory bank. Another variant is 'Computer Administered Telephone Surveys (CATS) where the interviewer is replaced by computer. The questions are voice synthesized and the respondent's answer and computer timing decide whether to continue or disconnect. The chief disadvantage of this method is that the rejection of this mode of data collection affects the refusal rate (and thus non-response bias) because people hang up more easily on a computer than on a human Telephone interview has the following advantages over personal interview:
Faster collection of data
Reduces biases (caused by personal presence of interviewer)
Focus group interview
A kind of unstructured interview. It involves a moderator leading discussion between small groups of respondents on a specified topic. A focus group interview involves 8 to 12 respondents having homogeneous characteristics, seated in a comfortable relaxed informal atmosphere. The interview generally continues for 1 to 3 hour during which the respondents develop a rapport and share their views. The proceedings are recorded on an audio or visual device. The moderator keeps the discussion going and probes the respondents whenever necessary to elicit insightful responses. These responses are better analyzed to derive conclusive results. Focus group interview results in advantages summed up as following 10 "S"
Synergism - When group of people produce better insight into a problem than individual.
Snowballing - One person's response initiates a chain of responses.
Stimulation - As the interview progress respondents are more and more encouraged to give responses.
Security - Since an individual generally finds somebody in the group who might endorse his opinion, he feels secure in answering.
Spontaneity - Since there are no pre designed questions being asked, responses are spontaneous.
Serendipity - Often new ideas are generated.
Specialization - Since response is being sought from large numberof respondents, the interviewer or moderator is a highly trained person.
Scientific Scrutiny - Since the proceedings are being recorded, they can be analyzed in a great detail scientifically.
Structure - It allows for topic to be discussed flexibly and in great depth.
Speed - Since a large number of respondents are being interviewed simultaneously, data is collected quickly.
However, like the two sides of a coin, focus group interview suffers from certain disadvantages like; the results can be wrongly interpreted since the response is not to any specific question. Focus group interviews make coding and analysis of data also very difficult. Most importantly, it is difficult to find a moderator who can conduct these interviews successfully.
Like the focus group interview in an unstructured type of interview used to collect qualitative data. However it is involves a one to one interaction between the interviewer and respondent. The depth interview can be 'non directive in nature where the respondent is given freedom to answer within the boundaries of topic of interest.' The other form of depth interview is 'semistructrured' in nature where the interviewer covers a specific list of topics although the linking, the sequence and the wording of each question is left to the interviewer's discretion.
In depth interviews, the interviewer asks the initial question and thereafter it is the response of the respondents from which further questions may be generated. The interviewer using probing techniques looks for more elaboration.
The interviewer only follows a rough outline of questions. The depth interviews have the advantage of uncovering much uncovering much deeper feelings and insights than focus group interviews, since they are dealing with just one respondent. However it suffers from the drawback of being expensive, time consuming and demands skilled interviewer.
The techniques involve highly unstructured and indirect form of questioning. The central feature of all projective techniques that is the presentation of an ambiguous, unstructured object, activity or person that to respondent is asked to interpret and explain. These techniques are best suited in situation where the respondent is not sure of his feelings and hence cannot express his answers directly. The projective techniques can be classified as construction techniques, association techniques and completion techniques.
In projective techniques, the respondents are asked to interpret the behavior of others and this way they indirectly reveal their own behavior in the same situation. Some of these techniques are discussed below.
Thematic Apperception Test (TAT) - The respondent is shown a set of pictures and then asked what he perceives of these pictures. e.g. he might be shown a picture of students holding protest banners and his perception of what he interprets from the picture is sought.
Item Substitution Test. This test involves creating two groups of respondents, the test group and the control group. The stimulus, presented as a list of items, is given to both the groups which is similar in all respect except for the substitution of items relevant to the study e.g. a shopping list is given to both the groups with one list having Maggie noodles which gets substituted by 'Top Ramen' noodles and the shopper's characteristics can be judged.
Word Association Test - Respondents are presented with a list of words one at a time and they are asked to respond immediately with the first things that come to their mind e. g. in a study on TV viewing habits the respondents can be presented with words like 'discovery', 'soap', 'idiot', 'star' etc. This method allows respondents to reveal their inner feelings on the topic.
Rorschach Test - It consists of ten cards that have print of ink blots that are although symmetrical but defy all meaning. The respondents are asked to interpret these cards/inkblots and their responses are interpreted on the basis of some predetermined framework.
Cloud Picture Test - This shows two or more characters conversing with each other and cloud of one character is left empty as a response to be filled by the respondent according to his interpretation of what the other characters are saying. It could even be a single character with an empty cloud overhead indicating his would be response to a particular situation.
Sentence Completition Test - It is similar to a word association test where instead of a word, a sentence is left incomplete and the respondent is asked to fill it with the first thought that comes to his mind e. g.
People who enter politics are...................................................................
A person who gives money to a charity is.................................................
Analysis of the response helps a researcher in concluding about the attitudes of people to various objects or subjects.
Story Completion Study - A step further to sentence completion is the story completion study: Under this a story is created by the researcher which defines the topic of research and the respondents are asked to complete the story.