How can you improve validity

The chosen methodology needs to be appropriate for the research questions being investigated and this will then impact on your choice of research methods. The design of the instruments used for data collection is critical in ensuring a high level of validity. For example it is important to be aware of the potential for researcher bias to impact on the design of the instruments.

It is necessary to consider how effective the instruments will be in collecting data which answers the research questions and is representative of the sample. The method including the analysis may contain some assumptions that need to be satisfied, e. The experimental method must ensure that all the assumptions are satisfied, otherwise, you will end up using a method or analysis that is inappropriate, and the result will be invalid.

You may be able to identify invalid measurements and discard them from the analysis. If your experiment is invalid, then the result is meaningless because either the equipment, method or analysis were not appropriate for addressing the aim. Reliability is about how close repeated measurements are to each other.

You can consider the reliability of a measurement, or of the entire experiment. A measurement is reliable if you repeat it and get the same or a similar answer over and over again, and an experiment is reliable if it gives the same result when you repeat the entire experiment.

You can test reliability through repetition. The more similar repeated measurements are, the more reliable the results. Improving reliability is a different matter to testing it. The reliability of single measurements is not improved through repetition , but through the design of the experiment.

Implementing a method that reduces random errors will improve reliability. Valid samples with a representative cross-section of your target group are based on random selection. If you allow survey respondents to decide whether to answer a survey, you can't be sure the respondents represent a random sample.

You have to pick survey respondents at random and classify those who don't answer the questions as "did not respond. You may have to change how you conduct the survey to get enough samples from a random selection. Often a random sampling technique introduces responses from people who are not members of your target group. You can include screening questions that block those respondents from participating, or you can collect all responses and discard those from people who don't meet your selection criteria.

For example, if you are surveying frequent customers, a question asking how often someone has purchased from you in the past month allows you to screen respondents. If you are surveying pensioners, an age cut-off lets you block or screen younger respondents. Validity is harder to assess, but it can be estimated by comparing the results to other relevant data or theory.

Methods of estimating reliability and validity are usually split up into different types. Several aspects of the experiment can contribute to validity: the equipment, the experimental method, and the analysis of the results.

Although it may seem obvious, the appropriate equipment needs to be used. The equipment must be suitable for carrying out the experiment and taking the necessary measurements. When you design your questions carefully and ensure your samples are representative, you can improve the validity of your research methods. Questionnaires are said to often lack validity for a number of reasons.

Participants may lie; give answers that are desired and so on. It is argued that qualitative data is more valid than quantitative data.

This type of internal validity could be assessed by comparing questionnaire responses with objective measures of the states or events to which they refer; for example comparing the self-reported amount of cigarette smoking with some objective measure such as cotinine levels in breath. Reliability can be thought of as repeatability — the extent to which, if you repeated the research, you would get the same results.