Question

Discuss the strengths and weaknesses of correlational and regression studies; discuss concepts such as positive and negative correlations, correlation coefficients, confounding, and causality.

Answer 1

Positive correlation: If the increse or decrease in one variable effects the increase or decrease in other variable, we say that two variables are positively correlated.

Negative correlation: If the increse or decrease in one variable effects the decrease or increase in other variable, we say that two variables are negatively correlated.

Correlation coefficient: It studies about the degree of the relationship between the two variables. Or it studies about the strength of the two variables.

The advantages and disadvantages of correlational studies:

Advantages: It gives the idea about the linear relationship between two variables, whether they are correlated.

Disadvantage: Correlation does not mean that one variable "caused" the other variable to change. If the change in one variable effects the change in the other variable, then we say that two variables are correlated.

Types of Correlational Designs:
There are many methods for correlational studies with their own strengths and weaknesses. Onetrendy method is called naturalistic observation, which necessitates a researcher to observe andrecord the natural environment without interference. One benefit of naturalistic observation isthat the researcher is observing variables in a natural state. Some limitations are that it can bedifficult to control the variables or to avoid outside influences from faking the results.Another type of correlational research is called the survey method. Surveys are easy on the pocket and swift, and can be used to gather information from very large sample size. However, poorly written survey questions can distort results. Another hitch is that survey results are alsodependent on survey respondents, who are not always trustworthy.A third method for correlational design is archival research, which analyzes historical records.An improvement in this method is that it’s a workable way to analyze large amounts of datawithout expending a lot of money. A lapse of this particular research method is that theresearcher has no way of knowing if the original data collection methods were reliable.Correlational studies are a helpful tool for conducting research. However, it must be kept in mindthat no study method is perfect. Researchers must take into consideration the limitations of boththeir preferred research method and correlational studies as a general rule.Correlational designs may be cross-sectional, in which all observations are made at the same point with context to time, or they may be longitudinal, in which calculations are made at two or more different time points

Correlation is not causation. For example, a vast majority of serial killers eat bread, but it would be absurd to say that eating bread causes you to kill people. You have to be very specific with what you are testing and make sure it is not something so vague that it applies to everything. A bad example of negitive correlation is that I ahve this rock that repels tigers because there are no tigers around. Does the rock really repel tigers? No. Correlation is best used in medical science, but it has to be tested against a placebo, or a control set, in multiple experiments to help show the new drugs effectiveness.

Regression analysis involves identifying the relationship between a dependent variable and one or more independent variables. A model of the relationship is hypothesized, and estimates of the parameter values are used to develop an estimated regression equation. Various tests are then employed to determine if the model is satisfactory. If the model is deemed satisfactory, the estimated regression equation can be used to predict the value of the dependent variable given values for the independent variables.

Regression model: In simple linear regression, the model used to describe the relationship between a single dependent variable y and a single independent variable x is y = a0 + a1x + k. a0and a1 are referred to as the model parameters, and is a probabilistic error term that accounts for the variability in y that cannot be explained by the linear relationship with x. If the error term were not present, the model would be deterministic; in that case, knowledge of the value of x would be sufficient to determine the value of y.