Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Statistics project
ACKNOWLEDGEMENT
Firstly I would like to thank almighty Allah who gave me abilities, caliber and incentives to conduct study on Inflation and GDP. I would like to thank Dr. Shahid Kamal who had been helping me throughout course of statistics and without his help it was not possible to accomplish target.
TABLE OF CONTENTS:
Introduction Literature review Objectives Methodology Analyzing results Conclusion References Data on two selected variables
INTRODUCTION
My stats project starts with two variables from World Development Indicators 2005 (WDI2005) which provides data of over 600 economic variables. The time frame of my statistical analysis is of 41 years i.e. from 1960 to 2001. Because of economic background of topic there is a dire need to understand the concept of Macroeconomics behind topic. Inflation rate and GDP growth rate are major issues in Macroeconomics, so I will be focusing on this issue. Percentage increase per annum in the average price of goods and services is the annual inflation rate. Due to collective or persistent increases in the supply of money, in money incomes or in prices tends inflation to occur whereas, average annual rate of growth of real output in a country is measured by GDP growth. GDP is Gross domestic product measures the output produced by factors of production within geographical boundaries of a country in one year. GDP consists of two types: i) GDP at market prices: GDP at market prices measures output inclusive of indirect taxes on goods and services. ii) GDP at basic prices: GDP at basic prices measures domestic output exclusive of indirect taxes on goods and services. The GDP at market prices exceeds GDP at basic prices by the amount of revenue raised in indirect taxes. Several studies have estimated that there is negative relationship between inflation and GDP whereas, some opposed too. Fischer reports that inflation reduces economic growth by reducing investment and productivity growth.
LITERATURE REVIEW
Yasir Malik has written article on inflation and growth in June 2005. This study estimates the threshold level of inflation rate in Pakistan using annual dataset from 1973 to 2000. The study focuses on condition of two variables in Pakistan and according to this study that there is an inverse relationship between the two variables. It mentions that in late 1970s growth rate fell below 5% whereas, inflation rate doubled at that time. This trend repeated again in 1990s which can be justified on bases of business cycle. Rising inflation is acting as a major challenge in establishing a sustainable growth rate in the economy and inflation can be raised from two sides one is demand pull inflation and the other is from supply side. As far as demand pull inflation is concerned it can be increased due to increase in demand of goods and services as a result prices in the economy goes up and output in the economy increases too so this type of inflation will increase the GDP growth rate. Supply side inflation is another type and arises due to increase in prices of raw materials which mostly includes the increase in prices of oil in the world market. When prices increase and raw material become expensive and automatically output goes down, thus reducing the GDP growth rate in the economy.
OBJECTIVES
The objective behind this project is to analyze the relationship between two variables that are annual inflation rate and GDP growth rate and to determine relationship between them, whether it is direct or inverse. This project also contains critical analysis of the variables by performing different operations like calculating mean, median, mode, hypothesis testing. Afterwards, a conclusion about the relationship between them from the analysis performed on them is provided.
METHODOLOGY
The test statistics that I would be using are the following: Mean= x/n Median= ([n/2]+1) Q1 Q2 = ([n/4]+1) = ([3n/4]+1) =([X-] /n)
The above-mentioned test statistics are for the basic analysis and the now I will give out the linear regression model formula that describes the relationship between X and Y. where the X and Y take the form: Y= + + Or Y= (y.x) + Where i s are random errors. The random error is are assumed to be independent of Xi and normally distributed with E( i) = 0 and Var(i) = 2y.x, a constant for all X. These assumptions imply that Yi also have common variance 2y.x as the only random element in the model is i. The regression line E(Yi) = y.x = + Xi is estimated from the sample data by = a + bX, where b = n XY XY , a = Y bX and is the nX2 (X)2 Sample estimate of the population mean y.x. I have taken Pakistans Current accounts balance as my dependent variable that is Yi, which is dependent on Exported goods ( Xi).
Analysis of Variables
ONE VARIABLE SUMMARY Data variable: INFLATION % Selection variable: YEAR 41 values ranging from -0.516462 to 26.663 Summary Statistics for INFLATION % Count = 41 Average = 7.91834 Variance = 31.2299 Standard deviation = 5.58837 Minimum = -0.516462 Maximum = 26.663 Stnd. skewness = 4.13476 Stnd. kurtosis = 4.35756 Sum = 324.652 This table shows summary statistics for INFLATION %. It includes measures of central tendency, measures of variability, and measures of shape. Of particular interest here are the standardized skewness and standardized kurtosis, which can be used to determine whether the sample comes from a normal distribution. Values of these statistics outside the range of -2 to +2 indicate significant departures from normality, which would tend to invalidate any statistical test regarding the standard deviation. In this case, the standardized skew ness value is not within the range expected for data from a normal distribution. The standardized kurtosis value is not within the range expected for data from a normal distribution.
Confidence Intervals for INFLATION % 95.0% confidence interval for mean: 7.91834 +/- 1.76391 [6.15443,9.68225] 95.0% confidence interval for standard deviation: [4.58812,7.15033] This pane displays 95.0% confidence intervals for the mean and standard deviation of INFLATION %. The classical interpretation of these intervals is that, in repeated sampling, these intervals will contain the true mean or standard deviation of the population from which the data come 95.0% of the time. In practical terms, we can state with 95.0% confidence that the true mean INFLATION % is somewhere between 6.15443 and 9.68225, while the true standard deviation is somewhere between 4.58812 and 7.15033. Both intervals assume that the population from which the sample comes can be represented by a normal distribution. While the confidence interval for the mean is quite robust and not very sensitive to violations of this assumption, the confidence interval for the standard deviation is quite sensitive. If the data do not come from a normal distribution, the interval for the standard deviation may be incorrect. To check whether the data come from a normal distribution, select Summary Statistics from the list of Tabular Options, or choose Normal Probability Plot from the list of Graphical Options.
Related Graphs:
SCATTER PLOT:
S c a tte r p lo t f o r I N F L A T I O N %
-1
14
19
24
29
IN F L A T IO N %
BOX PLOT:
B o x - a n d - W h is k e r P lo t
-1
14
19
24
29
IN F L A T IO N %
HISTOGRAM:
H isto g ra m fo r IN F L A T IO N %
24 20 16
frequency
12 8 4 0 -2 8 18 28 38
Count = 41 Average = 5.48354 Variance = 6.27757 Standard deviation = 2.50551 Minimum = 0.468373 Maximum = 11.3535 Stnd. skewness = 0.42072 Stnd. kurtosis = 0.0627172 Sum = 224.825 This table shows summary statistics for GDP %. It includes measures of central tendency, measures of variability, and measures of shape. Of particular interest here are the standardized skewness and standardized kurtosis, which can be used to determine whether the sample comes from a normal distribution. Values of these statistics outside the range of -2 to +2 indicate significant departures from normality, which would tend to invalidate any statistical test regarding the standard deviation. In this case, the standardized skewness value is within the range expected for data from a normal distribution. The standardized kurtosis value is within the range expected for data from a normal distribution. Summary Statistics for GDP %
95.0% confidence interval for mean: 5.48354 +/- 0.790837 [4.69271,6.27438] 95.0% confidence interval for standard deviation: [2.05705,3.2058] This shows that 95.0% confidence intervals for the mean and standard deviation of GDP %. The classical interpretation of these intervals is that, in repeated sampling, these intervals will contain the true mean or standard deviation of the population from which the data come 95.0% of the time. In practical terms, we can state with 95.0% confidence that the true mean GDP % is somewhere between 4.69271 and 6.27438, while the true standard deviation is somewhere between 2.05705 and 3.2058. Both intervals assume that the population from which the sample comes can be represented by a normal distribution. While the confidence interval for the mean is quite robust and not very sensitive to violations of this assumption, the confidence interval for the standard deviation is quite sensitive. If the data do not come from a normal distribution, the interval for the standard deviation may be incorrect
This displays the results of three tests concerning the center of the population from which the sample of GDP % comes. The t-test of the null hypothesis that the mean GDP % equals 0.0 versus the alternative hypothesis that the mean GDP % is not equal to 0.0. Since the P-value for this test is less than 0.05, we can reject the null hypothesis at the 95.0% confidence level. Somewhat less powerful than the ttest if the data all come from a single normal distribution.
RELATED GRAPHS:
BOX PLOT:
B o x - a n d - W h is k e r P lo t
10
12
SCATTER PLOT:
G D P %
S c a tt e r p l o t f o r G D P %
10
12
G D P %
HISTOGRAM:
H isto g ra m fo r G D P %
16 12
frequency
8 4 0 -1 2 5 8 11 14
GDP %
GDP % Count Average Variance Standard devtion Minimum Maximum Stnd. skewness Stnd. kurtosis Sum 41 5.48354 6.27757 2.50551 0.468373 11.3535 0.42072 0.0627172 224.825
ANALYSIS:
This table shows summary statistics for each of the selected data variables. It includes measures of central tendency, measures of variability, and measures of shape. Of particular interest here are the standardized skewness and standardized kurtosis, which can be used to determine whether the sample comes from a normal distribution. Values of these statistics outside the range of -2 to +2 indicate significant departures from normality, which would tend to invalidate many of the statistical procedures normally applied to this data. In this case, the following variables show standardized skewness values outside the expected range: INFLATION %. The following variables show standardized kurtosis values outside the expected range: INFLATION %.
Confidence Intervals:
95.0 percent confidence intervals Mean GDP % INFLATION % 5.48354 7.91834 Stnd. error 0.391294 0.872756 Lower limit 4.69271 6.15443 Upper limit 6.27438 9.68225
Analysis:
This table shows 95.0% confidence intervals for the means of each of the variables. These intervals bound the sampling error in the estimates of the means of the populations from which the data come. They can be used to help judge how precisely the population means have been estimated.
RELATED GRAPHS:
Scatter plot:
G P% D
IN A FL TION %
REGRESSION
Regression Analysis - Linear model: Y = a + b*X Dependent variable: INFLATION % Independent variable: GDP % Standard Parameter Intercept Slope Estimate 9.17773 -0.229667 Error 2.13727 0.355257 T Statistic 4.29414 -0.646483 P-Value 0.0001 0.5218
Analysis of Variance Source Model Residual Total (Corr.) Sum of Squares 13.2449 1235.95 1249.19 40 Df 1 39 Mean Square 13.2449 31.691 F-Ratio 0.42 P-Value 0.5218
Correlation Coefficient = -0.10297 R-squared = 1.06028 percent Standard Error of Est. = 5.62948
ANALYSIS
The output shows the results of fitting a linear model to describe the relationship between INFLATION % and GDP %. The equation of the fitted model is INFLATION % = 9.17773 - 0.229667*GDP % Since the P-value in the ANOVA table is greater or equal to 0.10, there is not a statistically significant relationship between INFLATION % and GDP % at the 90% or higher confidence level. The R-Squared statistic indicates that the model as fitted explains 1.06028% of the variability in INFLATION %. The correlation coefficient equals -0.10297, indicating a relatively weak relationship between the variables. The standard error of the estimate shows the standard deviation of the residuals to be 5.62948. This value can be used to construct prediction limits for new observations by selecting the Forecasts option from the text menu.
CONCLUSION
The analysis that we performed on both the variables shows that there does exist a relationship between the two variables i.e. inflation rate and GDP annual % in Pakistan. According to the equation in regression, when check the value of r-squared, it shows that 1.06028 percent changes in Y are being caused by X. showing that this is an equation for social sciences and not a mathematical equation. This also shows that the rest of the changes in the variable Y is being caused by unknown items which we call ebsolon . Hence 1.06028% shows the strength of relationship and from here I reach to conclusion that there are many other factors also which causes change in GDP.
REFERENCES
BOOKS: Chaudhry Sher Muhammad and Dr. Shahid Kamal, An introduction to Statistical Theory Part II. Walpole R.E Introduction to Statistics, 3rd Edition, Macmillian Publishing CO.
WEBSITES:
www.wds.worldbank.org/.../IW3P/IB/2000/ www.cbm.edu.pk/Inflation%20and%20Growth-Estmation%20of%20Threshold%20Point%20of %20Inflation%20for%20Pakis http://www.cbm.edu.pk/Inflation%20and%20Growth-Estmation%20of%20Threshold%20Point%20of %20Inflation%20for%20Pakis
Country Name Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan Pakistan
Year 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001
Inflation, consumer GDP growth prices (annual %)-(annual %)-1.640429323 -0.516461652 1.456481607 4.179579905 5.568639573 7.227623925 6.811398597 0.170624916 3.18698558 5.349850769 4.730691205 5.183217545 23.07013267 26.66302483 20.9044832 7.158314475 10.13297926 6.13867931 8.267074011 11.93822438 11.87990821 5.903516645 6.362060228 6.087154025 5.614849719 3.506413547 4.681198666 8.837953307 7.84425188 9.052147467 11.79125311 9.509043755 9.973673846 12.36818655 12.34358263 10.3738 11.37552571 6.227964995 4.142653007 4.366627915 3.148305368 5.987345 4.48286 8.688827 7.569758 10.41937 5.789952 5.400613 7.233221 5.5079 11.35346 0.468373 0.813406 7.064264 3.540192 4.211416 5.15619 3.947698 8.048534 3.758436 10.2157 7.920764 6.537487 6.778378 5.065206 7.592115 5.501654 6.452343 7.625279 4.959769 4.458587 5.061568 7.705898 1.757748 3.713969 4.986338 4.846581 1.014396 2.550234 3.660133 4.242755 2.736555