Following my articles 398 and 399 on Epidemiology research, this article describes errors of research, validity, precision, random, systematic and selection Bias errors.
1) The validity of a study is dependent on the degree of systematic error. Validity is usually separated into two components:
- Internal validity is dependent on the amount of error in measurements, including exposure, disease, and the associations between these variables. Good internal validity implies a lack of error in measurement and suggests that inferences may be drawn at least as they pertain to the subjects under study.
- External validity pertains to the process of generalizing the findings of the study to the population from which the sample was drawn (or even beyond that population to a more universal statement). This requires an understanding of which conditions are relevant (or irrelevant) to the generalization. Internal validity is clearly a prerequisite for external validity.
2) Random error is the result of fluctuations around a true value because of sampling variability. Random error is just that: random. It can occur during data collection, coding, transfer, or analysis. Examples of random error include: poorly worded questions, a misunderstanding in interpreting an individual answer from a particular respondent, or a typographical error during coding. Random error affects measurement in a transient, inconsistent manner and it is impossible to correct for random error. It may be found in all sampling procedures. This is called sampling error. There are two basic ways to reduce random error in an epidemiological study. The first is to increase the sample size of the study. In other words, add more subjects to your study. The second is to reduce the variability in measurement in the study. This might be accomplished by using a more precise measuring device or by increasing the number of measurements. Note, that if sample size or number of measurements are increased, or a more precise measuring tool is purchased, the costs of the study are usually increased. There is usually an uneasy balance between the need for adequate precision and the practical issue of study cost.
3) A systematic error or bias occurs when there is a difference between the true value (in the population) and the observed value (in the study) from any cause other than sampling variability. An example of systematic error is if, unbeknown to you, the pulse oximeter you are using is set incorrectly and adds two points to the true value each time a measurement is taken. The measuring device could be precise but not accurate. Because the error happens in every instance, it is systematic. Conclusions you draw based on that data will still be incorrect. But the error can be reproduced in the future (eg, by using the same mis-set instrument). A mistake may occur in coding which affects all responses for that particular question is another example of a systematic error.
Selection bias is one of three types of bias that threatens the validity of a study. Selection bias is an inaccurate measure of effect which results from a systematic difference in the relation between exposure and disease between those who are in the study and those who should be in the study. If one or more of the sampled groups does not accurately represent the population they are intended to represent, then the results of that comparison may be misleading. Selection bias can produce either an overestimation or underestimation of the effect measure. It can also produce an effect when none actually exists. An example of selection bias is volunteer bias. Volunteers may not be representative of the true population. They may exhibit exposures or outcomes which may differ from nonvolunteers (eg volunteers tend to be healthier or they may seek out the study because they already have a problem with the disease being studied and want free treatment). Another type of selection bias is caused by non-respondents. For example, women who have been subjected to politically motivated sexual assault may be more fearful of participating in a survey measuring incidents of mass rape than non-victims, leading researchers to underestimate the number of rapes. To reduce selection bias, you should develop explicit (objective) definitions of exposure and/or disease. You should strive for high participation rates. Have a large sample size and randomly select the respondents so that you have a better chance of truly representing the population. (743 words) www.askdryahya.com