Good Chi-Square Test Of Independence Research Paper Example

Abstract

The purpose of this paper is to discuss the effects of type D personality on the development of cardiovascular diseases. This paper discusses how the study was conducted and it compares the results obtained with statistics on the possession of type D personality by heart diseases patients and how it affects their morbidity and mortality rates. The chi square test of independence is used to test if there is a significant difference between the variables gender and type D personality. The tests for type D personality, Negative affectivity and social inhibition are all insignificant at 0.05 significance level. The fact that the tests are insignificant implies that the sample can be considered to be as a result of random sampling from a population whose categories are not statistically different. The percentages for type D personality, Negative affectivity and social inhibition for the different categories of gender are also included. The recommendations and conclusions discuss the options that could be taken to reduce the mortality rate of type D personality patients who have heart disease. The recommendations indicate that type D personality can be used as an early indicator of coronary heart disease.

Introduction

The chi-square test is a non-parametric test that is used to test the goodness of fit of a model. Alternatively it can be used to test for the independence of two categorical variables. The goodness of fit of a model relies on the comparison of expected frequencies and the observed frequency have changed. The chi-square distribution is a family of curves whose distribution varies with the degrees of freedom. When the number of degrees of freedom increases, then the shape of the distribution becomes symmetrical to the standard normal distribution. For the goodness of fit, the number of degrees of freedom are k-1 thatis if the variable consisted of k equal number of categories. Essentially, the chi-square test is a measure of the difference between the expected frequencies and the observed frequencies. This means that an increase in the difference between the expected frequencies and the observed frequencies translates to a larger value of the computed chi-square value. The decision rule is reached if the calculated chi-squared value falls within the critical region for rejection that is the calculated chi-square value is greater than the critical chi-square value. In this case the null hypothesis is rejected in favor of the alternative hypothesis. The rejection region of the chi-square test is in most cases on the right hand of the chi-square distribution, this is because the computation of the calculated chi-square value relies on the difference between the observed frequencies and the expected frequencies.
The chi-square test for independence on the other hand involves a contingency table which indicates the dependence between two categorical variables which are considered mutually exclusive. When constructing the contingency table it is such that an entry to a cell excludes the possibility of the same entry being made on another cell. The chi-square test is evaluating the null hypothesis that there is no dependence between the two categorical variables. That is, the frequencies observed can be attributed to the fact that the random sample was collected from a population in which the proportions are equal. The decision to reject the null hypothesis is reached if the probability value is below the significance level being used. In the event that the null hypothesis is rejected it implies that the difference between the two categories is not significant. The chi-square test involves two categorical variables, and complication is encountered in the computation of the expected frequencies for each cell. In the event that the population proportions are unknown, then the expected frequencies can either be equally distributed or proportionally distributed. The computation of the expected frequencies rely on the ration in the marginal totals. An appropriate method to calculate the expected frequency of a particular cell is to multiply the row frequency by the corresponding column frequency and then dividing the result by the total frequency. The degree of freedom for a two-by-two contingency table is one, and for a two-by-three contingency table is two degrees of freedom. The chi-square test can be applied to any number of contingency tables, the degree of freedom is obtained by multiplying the number of rows less one by the number of columns less one. The null hypothesis is rejected if the computed chi-square value is greater than the critical chi-square value.
The purpose of this analysis is to evaluate whether Type D personality has an effect on the health related behavioral patterns like physical inactivity, and poor treatment adherence which are factors that promote the development of Coronary Artery Disease.

Literature review

Type D personality is considered to be the tendency to undergo negative emotions and the inclination to suppress the portrayal of these emotions in social interactions. This condition is associated with a number of several negative effects on coronary heart disease patients and these include; decreased health status, increased cardiac symptoms, fatigue, and increased possibility of future depression. These patients are usually involved in negative healthy behavior that are characterized by irregular medical checkups and poor eating habits. A preview of previous analysis done on the effect of type D on the development of coronary heart disease indicate that there has been limited research especially on certain races particularly the Indian population. The main purpose of the study is to explore the contribution of type D on the development of coronary heart disease. Specifically, the study is interested in determining if there are differences in the presence of type D in the different categories of gender. Moreover, the study will explore how the individual factors of type D, that is, Negative Affectivity (NA) and Social Inhibition (SI) differ across the categories of gender.

Methodology

The target population is respondents who have been diagnosed with coronary heart disease within the age bracket of (36-77) years of age. The study was conducted in the Advanced Cardiac Centre (ACC) in the Post Graduate Institute of Medical Education and Research (PGIMER) an it involved 100 respondents out of whom 50 were Female and 50 were male. The mixed research approach technique was employed which involves a combination of qualitative and quantitative techniques in the data collection and research process. This involved the use of in-depth interview in order to capture the age, type of coronary heart disease, and the disease symptoms of the respondents. Other information that are of interest for the study that was captured include social support and socio-economic status. Psychological factors that contribute to coronary heart disease was also captured and this was mainly through type D personality. Type D personality is composed of negative affectivity and social inhibition each with seven items respectively, these items were captured through the use of five-point Likert scale responses which consisted of 0(false), 1(rather false), 2(neutral), 3(rather true) and 4(true). In order to capture the type D personality a predefined cut-off point was established for both the negative affectivity ad social inhibition and it was set at >10.
Cronbach's alpha is used to test the reliability of the items in the questionnaire to correctly capture the variable of interest. Cronbach's alpha was obtained to be 0.88 for negative affectivity and 0.86 for social inhibition. These values indicate that the items of questionnaire which was used to capture the effect of type D personality in the development of coronary heart disease were highly reliable. A Cronbach's alpha of 0.8 and above is usually and indication of reliably structured questions to capture the variable of interest.

Results

the socioeconomic class of most respondents was middle class with 46% of both the female and the male respondents being classified as middle class. There were no significant differences in the socio-economic status, origin and age of respondents across the categories of gender as indicated by the Pearson chi square test.
There were no significant difference in the type D personality of the respondents across the different categories of gender. The percentage of females who had type D personality was 68% which was slightly higher than that of the males which was 64%. Differences in the sub classes of type D personality negative affectivity and social inhibition, however, did not indicate any statistical significance. Approximately 83% of the coronary artery disease patients had high and very high negative affectivity. The percentage of the response 'very high' was higher in the females 62% than in the males 42%. an observation of the social inhibition indicate that for both categories of gender the percentages were evenly spread across the responses. 52% of the responses were above average and 48% were below average.

The results are presented in the table below

Type D personality across the categories of gender.
Negative affectivity across the categories of gender.
Social inhibition across the categories of gender.
Discussion
According to Haupt (2010), approximately half of the patients being treated with heart complications are type D. this is comparable with the results of the study which indicate that 66% of the subjects who were undergoing treatment if cardiovascular issues were type D. Denollet has researched extensively on type D personality and results from the approximately 49 studies he has conducted on more than 6000 subjects indicate that type D personality individuals with cardiovascular complications are more likely to die than non-D's.in a previous study which was conducted by Denollet, an observation which involved 300 patients indicated that approximately 27% of those classified to be type D personality died in a span of eight years mostly because of strokes and heart failures. These numbers are worrying when compared to non-D's patients who had a 7% death rate in the same span. Outstanding characteristics of type D personality is they supress their emotions and as such they do not have avenues of venting their stress. As a consequence, stress is a leading causing factor of increased cortisol levels and this causes high blood pressure, and inflammation of the artery among other complications. Of particular concern is the fact that type D personality patients are less likely to follow treatment programs and they are also less likely to exercise. Apart from avoiding the discussion of possible health complications with their doctors, type D personality are also less likely to stop smoking (Haupt, 2010).
Type D personality is a trait that is characterized by both negative affectivity and social inhibition. Research indicates that suppression of emotions is a leading factor in the development of increased cardiovascular reactivity (Sher, 2005). The significance level is 0.05 and it is preferred because it is in most cases considered a moderate criterion in the decision to reject or accept any hypothesis. Most importantly it strikes a balance between not committing both type one and type two errors. Type one error is the possibility of rejecting a true null hypothesis and type two error is the probability of accepting a false alternative hypothesis. Differences for the possession of type D personality was not significant at 0.05 level of significance because the p-value was computed to be 0.673. The test is therefore insignificant and we fail to reject the null hypothesis that there is no difference in the possession of type D personality across the categories of gender. Even at 0.1 significance level, the test is still insignificant, this shows that it is not by chance that we have obtained this result. Therefore, it can be concluded that the frequencies observed in the categories of gender are as a result of random sampling from a population whose proportions of gender are equal.
An observation of the difference in the negative affectivity of the respondents indicate that the test is insignificant at 0.05 level of significance. Therefore, we fail to reject the null hypothesis as there is not sufficient evidence for its rejection. It is concluded that there is no statistically significant difference in the categories of gender for Negative Affectivity. The possession of the sub-trait by the subject can therefore be considered to be as a result of random sampling in from a population whose categories are not statistically different. The p-value is 0.316 which is greater than 0.05 thus we fail to reject the null hypothesis.
The sub-trait social inhibition is not statistically significant, the p-value obtained is 0.663 which is greater than 0.05 and as such we fail to reject the null hypothesis. It is concluded that there is no significant difference in the possession of social inhibition across the categories of gender. The possession of the sub trait is as a result of random sampling from a population whose categories of gender are significantly similar. The chi-square test has been used in this study to test for the independence between the variables gender and type D personality. For the different analysis conducted which are; the possession of type D personality, Negative Affectivity and Social Inhibition all the chi-square tests are statistically insignificant which indicate that the variable gender and type D personality are independent.

Recommendations

Individuals with type D personality with a special focus on those who are at risk of cardiovascular complications should undergo counseling so that they can acquire healthy habits that incorporate physical activity and active and proper use prescribed medication. Stress reduction mechanisms may be employed for coronary heart disease patients who have type D personality. This will include; psychotherapy, emotional assistance and relaxation techniques among others. The identification of possible cardiovascular patients could be aided through observation of the type D personality individuals. Further studies could be conducted to establish if there is a correlation between type D personality and coronary heart disease and possible if there is a correlation between type D personality and mortality rate.

Conclusions

Type D personality is a health risk factor especially given that it is a causing factor to stress and depression and as a result it increases the chances of developing coronary heart disease. In addition, it is best to eliminate risks to health and for that matter it is also recommended that individuals be educated about the type D personality and its impact on the health of individuals.Individuals with cardiovascular complications have increased morbidity, mortality and as a result close observation is recommended so as to reduce these factors. It is also appropriate to have a personality approach for those patients who are at risk of coronary heart diseases (Sher, 2005).

References

Dornelas, E. A. (2012). Stress proof the heart: Behavioral interventions for cardiac patients. New York: Springer.
Haupt, A. (2010). Type D personality: How distress affects your health. U.S News and Health Report.
Kothari, C. R. (2005). Research methodology: Methods & techniques. New Delhi: New Age International (P) Ltd.
Molinari, E., Compare, A., &Parati, G. (2006). Clinical psychology and heart disease. Milan: Springer.
Sher, L. (2005) Type D personality: the heart, stress, and cortisol. Medicine and Health. 98 (5).
Vlodaver, Z., Wilson, R. F., & Garry, D. J. (2012). Coronary heart disease: Clinical, pathological, imaging, and molecular profiles. New York: Springer.