Quantitative Methods in Political Science - Term Paper Example

 «Quantitative Methods in Political Science» Introduction With terror and violence predominantly existing and arising in various parts of the world, there is a grave necessity to study the causes of such war and violence. The data obtained on Civil Disputes and War around the globe contains several categorical variables at more than 2 levels. Hence to compare these variables, statistical tests related to categorical and nominal variables have to be used. The cross-tabulation method is one such tool used to study the relationship between categorical variables. It uses the Pearson Chi-Square test to obtain a conclusion about the relationship variables under study. Hence the topic of study in my report is Cross-tabulation. Pearson's chi-square (χ2) belongs to the chi-square family of distributions that are used for significance testing. Prof. Karl Pearson first investigated its properties. When it is a matter of studying the relationship between the variables, which are categorical in nature, the cross-tabulation method is used. A contingency table based on the joint frequency distribution of the variables is obtained. The Pearson’s chi-square is then used to analyze the table. That is the variables are analyzed for association. The Pearson’s chi-square statistic is used to test the null hypothesis of no association of the various levels of the variables arranged as columns and rows in tabular form. It can be used even with nominal data. The chi square is used commonly to test the relationship between the variables and to test the significance of the discrepancy between theory and experiment. When the chi-square probability is obtained as 0.05 or less, it is commonly interpreted to reject the null hypothesis that the row variable is unrelated to the column variable by social scientists. Given below is an output of a cross-tabulation analysis made in SPSS. The Pearson’s chi-square value is obtained as 3.33. The insignificant p-value (0.68) explains that there is no association between the categorical variables, Party and Sex. Articles related to the topic: Given below is the list of articles that use the cross-tabulation method of analysis to draw a conclusion on the relationship between the categorical variables under study. 1) Article by Tetlock, Herrmann and Visser (1999): ‘Mass Public Decisions to go to War: A Cognitive-Interactionist Framework’, The American Political Science Association. The article studies the effect of the Americans’ decision to go to war. The various factors involved in the occurrence of a war were analyzed with the decisiveness of waging a war. Five different experiments were conducted on the Americans and their decisions of waging a war were analyzed. The chi-square tests were used to study the association between the various variables involved in the study. The study proved that Americans did not want to run away to protect themselves even when faced by an adversary with nuclear weapons. They were undeterred even when reminded about potentially catastrophic casualties. 2) Licklider, Roy (1995): ‘The Consequences of Negotiated Settlements in Civil Wars, 1945-1993’, American Political Science Review, 89, 3, 681-690. This article tries to study the impact of negotiations on settlements of civil wars. As several nations were involved in the study and the various causes that lead to the end of a war along with the duration were analyzed in a categorical format, chi-square analysis was used to obtain the results. It was found that military victories and negotiated settlements had the same after-effect on political-economic conflicts. However, in identity wars, military victories proved to have a stronger stand than negotiated settlements that broke into war sooner. Study on recent research: Salehyan’s article summary This paper will present a short summary of the article by Salehyan, Idean and Kristian Skrede Gleditsch (2006): ‘Refugees and the Spread of Civil War’, International Organization along with methodologies and results. The increase in political conflicts and violence leading to wars has forced us to analyse and examine every possible aspect disturbing the peace process of one country and its neighbouring countries. The one factor that has been paid least attention is the refugee flow. Though these people do not contribute to violence in vivid manner, they cannot be dispelled from the purpose even. The flow of refugees from insecure camps also leads to spread of epidemic diseases. The security of the host country is also adversely affected. A statistical analysis of the link between refugees and civil conflict since mid-twentieth century has shown that the presence of refugees from neighbouring countries is a crucial reason for conflict diffusion. The data under study is from the Uppsala/PRIO Conflict Data Set. The main dependent variable was conflict onset, coded 1 for the first year of conflict and 0 for no conflict. A chi-square/cross-tabulation between conflict onset and refugee flow from neighbouring states shows that the relationship between conflict and refugees in not a deterministic one. This may be due to the security measures taken by the host countries through various organisations. Further there are several other factors that also contribute to the risk of civil war. Hence these factors (conflicts in neighbouring countries, transborder ethnic groups, effect of income measured by GDP, impact of democracy based on Polity 4, ethnic relations and total population) are considered as control measures and suitable models are developed. Similarly models are developed by adding significant variables and the corresponding p-values are analyzed. From all the models, we find that there is sufficient evidence to support the null hypothesis that refugees significantly contribute to the occurrence of conflicts and civil wars. Though it is also shown that refugees do not involve in violence, the occurrence can be prevented by political intervention of the individual government and the United Nations. Short Assignment In this paper, three statistical analyses are performed on the 1999 Bercovitch Dataset (International Conflict Management 1945-1999). The tests of Cross-tabulation, Spearman’s rank correlation and binary logistic regression analysis are described in Part I, Part II and Part III respectively. For the “Study on the hostility level and reciprocity of the disputes” through correlation and regression analysis, the dispute data is taken from 1999 Bercovitch Dataset. The description of the variables taken is given below: 1. Hostility Level (D8): The level of hostility (enmity) of the dispute. The various levels are coded as: 1 'no militarized threat' 2'threat to use force' 3'display of force' 4'use of force' 5'war' 2. 'UN Involvment' (D25): The level of involvement of the UN in the disputes. The two levels are coded as: 1 'for UN involved' 2 'no UN' 3. Geographic Region (D12): The regions involved in the disputes. The various regions are coded as: 1 'Nth America' 2 'Central & S Amer' 3 'Africa' 4 'SW Asia' 5 'E Asia & Pacific' 6 'Middle East' 7 'Europe' 4. Reciprocity (D9): The level of reciprocation to the dispute. The two levels are coded as: 0 'no' 1 'yes' 5. Fatalities (raw) (D5a): The actual number of fatalities (victims) of the disputes. Part I: Cross-tabulation Let us consider the two variables, Hostility Level (D8) and 'UN Involvment' (D25). As they are categorical variables with two levels each, let us use the cross-tabulation method to analyse the relationship between the variables. Hence the hypotheses are framed as follows: H0 : There is no association between the two variables. H1 : There is association between the two variables. On conducting the cross-tabulation, we obtain a Pearson chi-square value of 59.427 (Table 1). The p-value is found to be 0.000. As this value is less than the 0.05 level of significance, we reject the null hypothesis and conclude that there is association between the hostility level and the UN involvement in the disputes. That is the involvement of the UN affects the hostility level of the disputes among the nations. Part II: Spearman’s Rank Correlation Analysis Spearman's Rank Correlation is a technique used to test the direction and strength of the relationship between two categorical variables. The statistic falls between -1 and +1. To calculate Spearman’s rho, let us consider the two variables, Hostility Level (D8) and Geographic Region (D12). Using SPSS, the following correlation matrix (Table 2) is obtained. Table 2: Correlation matrix Hostility Level Geographic Region Spearman's rho Hostility Level Correlation Coefficient 1.000 -.047(**) Sig. (2-tailed) . .008 N 3207 3207 Geographic Region Correlation Coefficient -.047(**) 1.000 Sig. (2-tailed) .008 . N 3207 3207 ** Correlation is significant at the 0.01 level (2-tailed). We find that a negative correlation coefficient (-0.047) is obtained. That is there is a weak negative correlation between the two variables. The p-value equal to 0.008 indicates that correlation is significant at the 0.01 significance level. This means that when the level of one variable increases, the level of the other variable tends to decrease. This can be further described as: The hostility level may be higher or highest in North America leading to war, while the hostility level may be the least in Europe having no militarized threat. Part III: Binary Logistic Regression A binary logistic regression is used to perform logistic regression on a binary response variable. A binary variable only has two possible values, such as presence or absence of a particular disease. Let us consider the following variables for the process: 1. Reciprocity (D9) - This is the categorical response (dependent) variable with two levels 2. Fatalities (raw) (D5a) - This is an independent quantitative variable 3. Geographic Region (D12) - This is an independent categorical variable. Because the response (Reciprocity) is categorized as yes and no, a binary logistic regression analysis is appropriate to investigate the effects of fatalities and geographic region on reciprocity. The null and alternate hypothesis can be written as: Ho: There is no difference between the observed and predicted values of the dependent. H1: There is difference between the observed and predicted values of the dependent. The model's estimates do not fit the data at an acceptable level. From the logistic regression table (Table 3a), we find that the odds ratio of fatalities is equal to 1. This means that Reciprocity is unaffected by one unit increase in fatalities. Further the G value (229.458) with p-value < 0.000, shows that one of the coefficients of the variables under study is not equal to 0. The Hosmer-Lemeshow Goodness of fit test (Table 3b) provides a highly insignificant p-value (0.960). We fail to reject the null hypothesis that there is no difference, implying that the model's estimates fit the data at an acceptable level. Table of Observed and Expected Frequencies (Table 3c) allows us to see how well the model fits the data by comparing the observed and expected frequencies. There is insufficient evidence that the model does not fit the data well, as the observed and expected frequencies are similar. This supports the conclusions made by the Goodness of Fit Test. Conclusion From a chi-square analysis on the association between the hostility level and UN involvement, it was found that only 26.03% (19 out of 2172) of the nations did not reciprocate to the disputes with UN involvement, while 68.7% (2153 out of 2172) reciprocated to the disputes despite UN involvement. This means that the UN involvement in bringing about harmony among nations has to be scrutinized thoroughly. The negative rank correlation between hostility level and geographic region shows that the danger of a civil war is more in the American continent rather than the European continent. Hence considerable steps by way of politics should be taken to control the tense situations in those countries. The binary logistic regression model obtained from this analysis can be used to predict the level of reciprocity to the disputes in the various geographical regions around the world along with considering the number of fatalities (casualties) incurred in the outcome of the severe hostile levels. Analysis on the involvement of refugees for the arise of civil wars had been studied and it had been found to be positive. That is the shifting of considerable population from one nation to another as refugees with varied thoughts and principles had affected the peace and culture of the native population thereby creating communal riots. This had lead to civil wars among the nations which gradually spread to the neighbouring nations. From the analysis it is found that the Governments around the world should take steps to induce peace among their own territories as the involvement of the UN in the peace-keeping process has not produced significant results. That is the countries reciprocate to disputes in a severe manner despite the UN’s negotiations. Hence stringent measures of implementing peace among the nations have to be adopted to reduce the number of fatalities caused during war times. Although alarming results are obtained from this analysis, there are several possibilities of misinterpreting the variables due to lack of considerable theoretical description of the data. References: Doane D.P. & Seward L.E. (2007). Applied Statistics in Business and Economics. McGraw-Hill/Irwin: New York Elliot A. C. & Wayne A. W. (2007) Statistical Analysis Quick Reference Guidebook: with SPSS examples. London: Sage Salehyan, Idean and Kristian Skrede Gleditsch (2006): ‘Refugees and the Spread of Civil War’, International Organization, 60, 335-366, Tetlock, Herrmann and Visser (1999): ‘Mass Public Decisions to go to War: A Cognitive-Interactionist Framework’, The American Political Science Association. Licklider, Roy (1995): ‘The Consequences of Negotiated Settlements in Civil Wars, 1945-1993’, American Political Science Review, 89, 3, 681-690. Rumsey D. (2003). Statistics for Dummies. Hoboken, NJ: Wiley Publishing Griffith A. (2007). SPSS for Dummies. Hoboken, NJ: Wiley Publishing http://www.indiana.edu/~educy520/sec5982/week_12/chi_sq_summary011020.pdf http://faculty.chass.ncsu.edu/garson/PA765/chisq.htm Appendix: Table Table 1: Cross-tabulation Tabulated statistics: Reciprocity, Involvement 1 Rows: Reciprocity Columns: Involvement 1 UN no UN involved All no 54 19 73 73.97 26.03 100.00 yes 981 2153 3134 31.30 68.70 100.00 All 1035 2172 3207 32.27 67.73 100.00 Cell Contents: Count % of Row Pearson Chi-Square = 59.427, DF = 1, P-Value = 0.000 Likelihood Ratio Chi-Square = 54.601, DF = 1, P-Value = 0.000 Table 3: Binary Logistic Regression: Reciprocity versus Fatalities, Geographic region Link Function: Logit Response Information Variable Value Count Reciprocity yes 3134 (Event) no 73 Total 3207 Factor Information Factor Levels Values Geographic region 6 Africa, Central & S Amer, E Asia & Pacific, Europe, Middle East, SW Asia Table 3a: Logistic Regression Table Odds 95% CI Predictor Coef SE Coef Z P Ratio Lower Upper Constant 2.81655 0.368149 7.65 0.000 Fatalities 0.0012216 0.0002956 4.13 0.000 1.00 1.00 1.00 Geographic region Central & S Amer -0.117999 0.554822 -0.21 0.832 0.89 0.30 2.64 E Asia & Pacific -1.20536 0.451890 -2.67 0.008 0.30 0.12 0.73 Europe 1.22611 1.06992 1.15 0.252 3.41 0.42 27.75 Middle East -1.25829 0.400459 -3.14 0.002 0.28 0.13 0.62 SW Asia 0.267319 0.807148 0.33 0.741 1.31 0.27 6.36 Log-Likelihood = -233.566 Test that all slopes are zero: G = 229.458, DF = 6, P-Value = 0.000 Table 3b: Goodness-of-Fit Tests Method Chi-Square DF P Hosmer-Lemeshow 2.545 8 0.960 Table 3c: Table of Observed and Expected Frequencies: (See Hosmer-Lemeshow Test for the Pearson Chi-Square Statistic) Group Value 1 2 3 4 5 6 7 8 9 10 yes Obs 282 308 421 340 330 372 352 328 325 76 Exp 282.2 304.8 424.0 340.0 330.0 372.0 352.0 328.0 325.0 76.0 no Obs 51 14 8 0 0 0 0 0 0 0 Exp 50.8 17.2 5.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 Total 333 322 429 340 330 372 352 328 325 76 Value Total yes Obs 3134 Exp no Obs 73 Exp Total 3207 Read More