1. Errors:
In sampling and research design
Chetna, PhD (First year) 2022
R.no. 722403
Adm. No. PH000104
Department of Food Science and Technology
Course: BAS 751
3. Errors in research?!
● Beginning of research - broad to specific
● Setting in objectives
● Planning a research design
● Sampling methods & selection
● Data collection-Data entry-Data analysis
● Result interpretation
● Report writing
4. Sampling Error
● Errors occur due to sampling methods and selection of sample size- when
taking sample from a population
● Leads to statistical error
● Sources of error
○ Wrong estimation of population parameter
○ Randomness
○ Less number of samples from the whole population
○ Choosing inaccurate sampling methods or techniques
○ Biases in choosing samples
5. Continued..
● Same sample size but different sampling method- affects magnitude of
sampling error
● For instance, Random sampling method has higher chances of error than
stratified random sampling(if population is heterogeneous in nature)
● Measurement of Sampling error
○ Usually called precision of sampling plan (↑Sample size ↑Precision)
○ By sampling design and size
6. Continued..
● How to limit Sampling errors (not possible to control 100% error)
○ True representation of population
○ Population specification
○ Sampling design
○ Sample accuracy- Homogeneity
○ Sampling method
○ Sample selection
○ Increase sample size
7. ● Larger the sample— higher the
accuracy in research
● Increases the sample size,
decreases the sampling error
❖ Limitations in increasing sample size
➢ Cost ↑ & Time ↑
➢ Systematic bias ↑
➢ Wastage of sample
Figure 1: Graphical representation of relationship
between sample size and sample design
Continued..
8. Non- Sampling Error
● Errors occurring due to other sources than sampling.
● Error arises at any stage of conducting a research such as planning, collecting
data, data entry, data coding, tabulation, data analysis, also during report
writing.
● Sources of non-sampling error
○ Not attentive towards work
○ Lack of knowledge
○ Bias in data analysis
9. ● When can non-sampling error occur?
○ Lack of proper specification of the domain of study and scope of the
investigation,
○ Incomplete coverage of the population or sample,
○ Faulty definitions and objective setting,
○ Inappropriate sampling frame,
○ defective methods of data collection,
○ Error in instrument- Measurement error,
○ Data processing- collection, entering, coding, tabulation, analysis etc.
Continued..
10. ● How to limit non-sampling error?
○ Specification of area of research and defined objectives
○ Appropriate research design
○ Appropriate sampling frame
○ Complete data collection
○ Minimizing errors in instruments
○ Use of suitable data collection methods
○ Avoid short timing for data collection
○ Cautious to data processing
○ Pre-testing or Pilot study Continued..
11. Types of non-sampling error
● Respondent error
○ Inability or unwillingness of respondent creates error.
○ Also named as, non-response error
○ To reduce errors associated with respondents: Rechecking, Re-contact,
willingness, to know the ability of respondent, etc.
● Measurement Errors
○ Errors in instruments, e.g., Spectrophotometer, Weighing scale, Computer
reading to wrong entry etc.
○ Take measurements or reading consciously and observe the data before analysis
12. ● Tabulation errors
○ At tabulation stage, when data is entered before analysing
○ Reasons: Insufficient data, errors in data processing, errors in graphical
representation etc.
○ To minimize the errors, data accuracy and data sufficiency is crucial.
● Specification errors: Errors at planning stage, due to inadequate and inconsistent
specification of data, w.r.t. Objectives of research, faults in data tool handling, etc.
○ To reduce this error: set specific objectives, Adequacy and consistency in data,
selection of appropriate data collection tool, etc.
13. ● Ascertainment errors: errors may occur at field stage, when researchers goes for data
collection, either in community or in laboratory.
○ Not trained or experienced investigations, recall errors, lack of adequate
inspection and lack of supervision of primary staff etc.
○ Further divided into 2 sub-categories:
■ Coverage errors: from duplication or omissions of data or non-response
■ Content errors : wrong entries by researcher
○ To limit errors at this stage:
■ Trained and experienced investigators is required
■ Avoid data manipulation
■ Monitoring and evaluation can reduce ascertainment error
14. Difference between
Sampling error Non-sampling error
What
Why
Where
With
sample
size
Occurs due to the sample selected does
not perfectly represents the population
of interest.
Due to the sources other than sampling.
Deviation between sample mean and
population mean
Scarcity of data and miscalculated or
misinterpreted analysis
Only during sample selection From the beginning to the end
Increase in sample size No relation with sample size
15. ¿¿….Questions….??
Q1. _____ occurs when the sample used in the study is not representative of the
whole population.
a.Sampling error b.Margin of error
c.Population specification d. Non-sampling error
Q2. Which of these is NOT a technique to minimize sampling error?
a. Increase the sample size
b. Divide the population into groups
c. Know your population
d. Train your team Technique to reduce non-sampling error
16. Q3. Name non-sampling error and its control.
Q4. Name the non-sampling errors:
a. When respondent is fail to response-
b. Colorimeter may show-
c. Insufficiency of data may create-
d. Using wrong verbs, punctuation marks, etc-
Q5. Is sampling error the same as standard error?
Non-response error
Measurement error
Tabulation error
Grammatical error
17. References
● Kothari, C. R., & Garg, G. (2008, December 11). Research Methodology : Methods And Techniques (Multi Colour
Edition) (4th ed.). New Age International Publishers.
● https://www.youtube.com/watch?v=AJdt2_qxulo
● https://www.youtube.com/watch?v=v61kKi_gwMA
● http://home.iitk.ac.in/~shalab/sampling/chapter13-sampling-non-sampling-errors.pdf
● https://egyankosh.ac.in/bitstream/123456789/12260/1/Unit-4.pdf
● Khadka, J. (2019, January). Sampling Error in Survey Research. International Journal of Science and Research (IJSR),
8(1). https://doi.org/10.21275/SUB157990