Earnings management and ipos: differences between industries
Profit management as methods of adjusting financial information to increase the attractiveness of the company to investors. General characteristics of the basic principles of accounting. Acquaintance with key features and problems of profit management.
| Рубрика | Менеджмент и трудовые отношения |
| Вид | дипломная работа |
| Язык | английский |
| Дата добавления | 07.12.2019 |
| Размер файла | 1,2 M |
Отправить свою хорошую работу в базу знаний просто. Используйте форму, расположенную ниже
Студенты, аспиранты, молодые ученые, использующие базу знаний в своей учебе и работе, будут вам очень благодарны.
Table 1. Descriptive statistics of the variables
|
Variable |
Obs |
Mean |
Std. Dev. |
Min |
Max |
|
|
AR |
188 |
166350.3 |
479149.9 |
1.799 |
2478996 |
|
|
GrossPPE |
188 |
161361.4 |
412250 |
19120 |
2023447 |
|
|
TotalAssets |
188 |
544759.4 |
1365262 |
155.206 |
7259652 |
|
|
Revenue |
188 |
563404.9 |
1607594 |
28.251 |
8827252 |
|
|
NetIncome |
188 |
68542.44 |
206564.4 |
-196671 |
889758 |
|
|
CFO |
188 |
97876.67 |
316806.6 |
-8249 |
1807099 |
|
|
LagTA |
188 |
443701.2 |
1067052 |
128.313 |
5819008 |
|
|
LagAR |
188 |
133180.1 |
378568.6 |
7.117 |
2065024 |
|
|
LagRevenue |
188 |
440107.3 |
1219570 |
28.251 |
7143866 |
|
|
AccrualsLa~A |
188 |
-.0498315 |
.1393094 |
-.5208012 |
.3850516 |
|
|
1/LagTA |
188 |
.0005216 |
.0015437 |
1.72e-07 |
.0077934 |
|
|
ChgCashRev~A |
188 |
.3779316 |
1.657498 |
-1.353787 |
11.87024 |
|
|
PPELagTA |
188 |
.6994765 |
1.38829 |
.0003194 |
6.883786 |
This is only a descriptive statistic, showing the overall situation with the variables. However, there is a need to check the variables on the normality of their distribution.
Further, I will elaborate and explain regressions I received and tests that were performed in order to evaluate the reliability of the regression. The first regression I built is the modified Jones model on the example of IPO telecommunication companies. I will describe the first regression and its test in more details to show how analysis works. This will allow to understand the concept of the analysis and steps that were performed to conduct the analysis with each sample.
The very first thing to do is to show the linear correlation between dependent and independent variables. The correlation matrix is the following:
Table 2. Correlation matrix
|
(obs=54) |
Accrua~A |
1/LagTA |
ChgCas~A |
PPELagTA |
|
|
AccrualsLa~A |
1.0000 |
||||
|
1/LagTA |
0.5875 |
1.0000 |
|||
|
ChgCashRev~A |
-0.3177 |
0.4768 |
1.0000 |
||
|
PPELagTA |
-0.6129 |
0.8043 |
0.5820 |
1.0000 |
As it could be observed, there is a linear dependence of the variables, therefore we can analyze the sample by the regression analysis in order to estimate the intense of this dependence. Moreover, according to the modified Jones model I use multiple linear regression; therefore, the assumption is that the variables distributed normally. However, there is no need for multiple linear regression normality, there is only need of normal distribution of the residuals,
After calculating total accruals, which is basically the dependent variable, the independent variables were calculated as well, and the regression is the following is presented in Table [3].
Table 3. Multiple linear regression
|
Source |
SS |
df |
MS |
Number of obs =54 |
|||
|
F( 3, 50) =11.28 |
|||||||
|
Model |
.46995892 |
3 |
.156652973 |
Prob > F = 0.0000 |
|||
|
Residual |
.694574049 |
50 |
.013891481 |
R-squared = 0.4036 |
|||
|
Adj R-squared = 0.3678 |
|||||||
|
Total |
1.16453297 |
53 |
.02197232 |
Root MSE = .11786 |
|||
|
Coef. |
Std. Err. |
t |
P > | t | |
[95% Conf. Interval] |
|||
|
AccrualsLagTA |
|||||||
|
1/LagTA |
-485.8246 |
331.5207 |
-1.47 |
0.149 |
-151.704 |
180.0543 |
|
|
ChgCashRevLagTA |
.0053706 |
.0115324 |
0.47 |
0.643 |
-0177928 |
.028534 |
|
|
PPELagTA |
-.0526523 |
.0241878 |
-2.18 |
0.034 |
-.101235 |
-0040696 |
|
|
_cons |
-.0024569 |
.0181816 |
-0.14 |
0.893 |
-0389758 |
.034062 |
This multiple linear regression estimates the connection between accruals of the company and the reciprocal of total assets, property, plant and equipment and the difference between sales and accounts receivables. This is a basic modified Jones model. For further estimation of discretionary accruals there is a need to diagnose the linear regression on whether it meets the basic OLS assumptions in order to be reliable model. The first assumption of the data is that it is homoscedastic. It means that the variance of the residuals is constant. Therefore, in order the model to be well-fitted there should not be increasing of variance of residuals with increased value of the dependent variable. Therefore, there is a need to test whether it is so. To check this, it was used two tests on heteroskedasticity: White's test and Breusch-Pagan's test. However, the first thing is needed to be shown is the plot of residuals distribution. The Figure [1] here is kernel density estimate, which shows us the distribution of residuals and the normal distribution line. As it can be observed, the residuals are somehow have the normal distribution and the deviation is not critical. Therefore, I can claim is that the data is appropriate for the analysis.
Figure 1. Kernel density estimation of the residuals
Basically, kernel estimation is a smoothed histogram, which shows the estimation of density of distribution of any random value.
It could be seen from the Figure [2] that residuals are dense with several outliers, and it seems that there is a homoskedasticity. However, the test should be provided in order to prove this. Moreover, the distribution of the residuals is not perfectly normal as it could be observer on the kernel density plot above.
Figure 2. Residuals distribution
The situation could be due to the not normal distribution of the data. For the test it was chosen the White's test on homogeneity of variance of the residuals. The test is presented in Table [4].
Table 4. White's homogeneity test
|
Source |
chi2 |
df |
p |
|
|
Heteroskedasticity |
27.00 |
9 |
0.0014 |
|
|
Skewness |
1.11 |
3 |
0.7756 |
|
|
Kurtosis |
2.41 |
1 |
0.1208 |
|
|
Total |
30.51 |
13 |
0.0040 |
This is the White's test which has a null hypothesis that residuals have constant variance. As it can be seen from the table, the p-value is 0.0014 which is below the significant level (e.g. p-values < 0.05), hence we reject the null hypothesis and assume that there is heteroskedasticity. There is a problem of inconstant variance of residuals, which could influence on the regression estimation. There are several ways to cope with heteroskedasticity: transform and reconsider the model, variables, samples etc., obtain robust standard errors or clustered standard errors. To solve this problem, I used robust standard errors and the regression now is the following:
Table 5. Multiple linear regression for telecom IPOs
|
Linear regression* |
Number of obs =54 |
||||||
|
|
|
|
|
|
F( 3, 50) =64.53 |
||
|
|
|
|
|
|
Prob > F = 0.0000 |
||
|
|
|
|
|
|
R-squared = 0.4036 |
||
|
|
|
|
|
|
Root MSE = .11786 |
||
|
AccrualsLagTA |
Coef. |
Robust Std. |
t |
P > | t | |
[95% Conf. Interval] |
||
|
1/LagTA |
-485.8246 |
282.0385 |
-1.72 |
0.091 |
-1052.316 |
80.66638 |
|
|
ChgCashRevLagTA |
.0053706 |
.0095535 |
0.56 |
0.577 |
-.0138182 |
.0245594 |
|
|
PPELagTA |
-.0526523 |
.0165419 |
-3.18 |
0.003 |
-.0858777 |
-.0194269 |
|
|
_cons |
-.0024569 |
.0179174 |
-0.14 |
0.891 |
-.038445 |
.0335312 |
As it could be seen from the table, overall situation has not changed, now we just have a little bit more significant coefficients, but there is only one which is significant on the 5% confidence level - PP&E coefficient with the p-value 0.003, which is really significant. Other factors seem to influence insignificantly on the 5% significance level on the dependent variable, which could be the flaw of the model or the data.
The next test we need to perform is multicollinearity. The situation with multicollinearity is that independent variables actually could have linear dependence between each other, therefore the estimations of the model will not be correct, and the variables do not explain anything. For checking multicollinearity, I use the variance inflator factor which basically estimates the degree of dependence of variables between each other:
Table 6. Variance inflation factor
|
Variable |
VIF |
1/VIF |
|
|
PPELagTA |
3.31 |
0.302049 |
|
|
1/LagTA |
2.83 |
0.352914 |
|
|
ChgCashRev~A |
1.51 |
0.661077 |
|
|
Mean VIF |
2.55 |
The rule of thumb for this estimation states that if the value of vif coefficient is more than 10, it indicates the multicollinearity. As it could be observed, there is no any multicollinearity among independent variables.
The last test concerns endogenity problem, one of the most common problem of cross-sectional data estimations. Endogenity implies any correlation of regressors, independent variables with the residuals. This situation breaks all the estimations and the model becomes unreliable. In order to check endogenity, I will use the Ramsey test in Stata, which checks the parameters of the equation and the null hypothesis is that there are no any omitted variables in the model:
The test indicates that the p-value is more than 0.05, therefore the null hypothesis is not rejected and there are no omitted variables. It suggests that the model is correct.
Thus, there are four main tests were provided in order to check the assumptions of OLS model of multiple linear regression. All the tests were successful except homoskedasticity, which was fixed by robust standard errors. R - squared in this regression is quite high, 0.4, which means that 40% of variance of dependent variable is explained by independent variables and the model in general. This value of R - squared is appropriate, because I rely on the benchmark and similar studies which have conducted the same analyses using modified Jones model and I can state that even R - squared 0.1 is appropriate and the researches use these models.
In the part presented above was shown the detailed analysis of one sample and the tests which were conducted in order to ensure that the model meets the assumptions of ordinary least squares estimations of multiple linear regression. The very same analysis was conducted on other samples in order to receive the beta coefficients. For example, the IPO automobile firms have the regression estimations which is presented in Table [7]:
Table 7. Multiple linear regression for automobile IPOs
|
Linear regression* |
Number of obs = 40 |
||||||
|
|
|
|
|
|
F( 3, 36) = 1.26 |
||
|
|
|
|
|
|
Prob > F = 0.0301 |
||
|
|
|
|
|
|
R-squared = 0.3110 |
||
|
|
|
|
|
|
Root MSE = .08308 |
||
|
AccrualsLagTA |
Coef. |
Robust Std. |
t |
P >| t | |
[95% Conf. Interval] |
||
|
1/LagTA |
-2.72901 |
2.196163 |
-1.24 |
0.222 |
-7.183035 |
1.725015 |
|
|
ChgCashRevLagTA |
.0745699 |
.0488079 |
1.53 |
0.135 |
-.0244171 |
.1735569 |
|
|
PPELagTA |
-.060423 |
.0435581 |
-1.39 |
0.017 |
-.148763 |
.027917 |
|
|
_cons |
.0061937 |
.0393354 |
0.16 |
0.876 |
-.0735821 |
.0859696 |
As the regressions were conducted, the same analyses on the reliability of the model were carried out. In all models I used robust standard errors, and all were checked on the endogenity and multicollinearity. As an example, the kernel density graph of residuals distribution is presented on the Figure [3]:
Figure 3. Kernel density plot of the residuals
It could be observed that in this set, the residuals are more normally distributed, and the deviations are not very significant.
The next very important step is to estimate discretionary accruals using the regressions' coefficients. For example, in the first regression we have the estimations of all s and we just need to put them into equation to get the values. Due to the fact that we know the values of net operating accruals, which basically total accruals, therefore, the residuals will indicate on the discretionary part of accruals. For each firm in the sample, I use the same coefficients, but the values of the independent variables differ, hence I will obtain the set of discretionary accruals per each firm. This will be the dependent variable of the second regression, which will be built with dummy variables. The regression was described in the methodology part. Hence, according to the model, if I get the 1 positive, then the IPO companies engage more earnings management than non-IPO, if I get 2 more than 0, then telecommunication companies engage more earnings management in general, and, finally, if I get 3 > 0, then the IPO companies in telecommunication industry engage more earnings management. This regression also should have some control variables, which could influence the discretionary accruals. However, one of the possible parameters is the size of the company. In this case, there is no need to include such variable, because I have already scaled all the variables by total assets, which helped to get the weighted value, so the size of the company did not influence the estimations. Moreover, the age of the company could influence, but I have not considered continual process, therefore, the age is not relevant in this case. Hence, I do not include any of the control variables in the second regression.
The table above is the main output of the research. It gives the information about the second regression, which aims to build the model of earnings management's usage among IPO and non-IPO companies across telecommunication and automobile industry. The coefficients, as it was mentioned earlier, show the engagement in earnings management. The result is that both hypotheses are confirmed by the analysis.
As the purpose of the study is to reveal how earnings management is used in IPO and already listed companies and to compare these results across two different industries, the results show the research's output. Therefore, I can state that companies which want to go to the initial public offering adjust their earnings more than non-IPO companies. Moreover, the second hypothesis claims that IPO companies in the industry with higher revenue growth expectation engage more earnings management was proved as well. Thus, according to my analysis held by the means of the modified Jones model results in significant observations. Both hypotheses were proved, and the model was diagnosed on its reliability by econometric analysis. Therefore, I can claim that the research is done appropriately according to the standards. Moreover, I should mention that the results could not be interpret in another way. There are some limitations within the presented model, however this is the best and well-fitted model to the research on such topic.
Conclusion
The following part is the conclusion of accomplished work. This part will include brief description of the paper in general, its research design, theoretical base, methodology and conducted analysis, then there will be presented critical evaluation of the results and their contribution into management science. After that, I will consider limitations of the research and possible ways to overcome these difficulties. Moreover, I will elaborate more on different methods which could be used in such paper and whether the results of these methods would be different. The last thing I would consider is the significance and the relevance of the study and its future discussion.
The first thing I want to consider is the concept of the presented research. Overall, it concerns the fact that some companies could adjust their earnings in financial statements and do it according to international standards, which means legally. In this paper I wanted to consider such manipulations around initial public offerings and across two industries. In other words, the purpose was to compare engagement of the companies which go public within two different industries. After conducted prior literature review, there was found a gap of such research, therefore I consider this study as relevant and significant. Moreover, theoretical background allowed to get the comprehensive overview of the topic and concentrate on several specific things, such as methods. After critical analysis of prior literature, I chose the best and the most appropriate analysis, which implies accrual-based model - modified Jones model. Two main hypotheses were stated during the work. The first hypothesis is the following: IPO companies engage earnings management techniques more than non-IPO companies. This hypothesis has already been confirmed, however I needed to check it one more time on the presented sample. The second hypothesis is based on the investors' expectations and could be formulated as following: IPO firms in the industry with higher revenue growth expectation engage more earnings management that do companies in industry with less revenue growth expectations. According to the analytical format research design and literature analyzed, I chose the best option which allows to make the most precise analysis. The data for the analysis was gathered from IPO prospectuses and Thomson Reuters Eikon data base. Observations are literally financial indicators from three main financial statements: cash flow, income statements and balance sheet. The sample consists of four sub-samples which are divided according to the industry and IPO involvement. The industries for analysis were chosen according to the revenue growth expectations indicator. The first industry is with the highest value and the second is with the moderate level of the indicator. After that, the analysis, which is a multiple regression model was conducted and the econometric diagnostic was applied in order to check the reliability of the model. The model occurred to be appropriate and, thus, I can conclude that the results are significant. The results show that in fact, IPO companies indeed adjust their earnings more than non-IPO companies, which is the confirmation of the first hypothesis. The second hypothesis was confirmed as well, hence IPO companies in telecommunication industry engage more earnings management than in automobile industry.
The results of this study are relevant to the evaluation of the firms. I consider such results to be useful for the retail investors in order to evaluate the company before the IPO. Results give another indicator for evaluation of the company. Undoubtedly, the usage of only this method will not result in correct company's evaluation. Only with other methods, it could give the comprehensive picture. For example, it could be a question to the company which want to go public, why the shares are so unreasonably expensive, especially when the earnings are manipulated. Therefore, the contribution of these results is significant for the investors. Moreover, investors could pay attention to the industry, which I analyzed. For instance, the hypothesis of the earnings management among industries with different revenue growth expectation was confirmed. I checked and compared only two industries, nevertheless, it could be the analysis of other industries. However, the investors should pay attention to the revenue growth expectations in the industry. Overall, the main contribution of the research concerns companies' evaluations, especially before initial public offerings.
The next crucial thing I want to elaborate is limitations. Almost in each part of the research there are some limitations, which influence the outcome of the work. However, I suggest that the most significant ones are in methodology part. The specific analysis chosen from the literature provided with the gathered data. The first limitation is the model itself. This situation is present because of the complicated measuring concept of earnings management. In other words, this concept is not so obvious to measure, especially by any model, because it is not obvious and there are a lot of other influencing factors. Many researches claim that the modified Jones model is the most accurate one, but it is not perfect and has its own drawbacks. To the drawbacks of the model could be related the omitted significant variables which could eventually influence the discretionary accruals estimation. Despite the fact that I checked the endogenity, there could occur such situations with different samples and etc.
The second limitation is data sample, I claim that the number of observations is limited by the time due to the manual character of the gathering and absence of prepared data sets. However, I should mention that if any other methodology or analysis takes place, there could be other outcomes. I assume that outcomes would be inaccurate, and the results would be unreliable due to ambiguous concept of earnings management. Therefore, the presented analysis is considered as the most appropriate. The last important point to discuss is future implication.
The presented study strongly implies further discussion and future development.
I state this, because I analyzed only two industries, while there is way more of them, and in all of them initial public offerings take place. Hence, the study should be extended in terms of industry broadening. Moreover, the similar type of analysis could be applied not only within IPO deals. IPO process used here only for the reason of data availability.
Thus, the research is done appropriately and the opportunity of the additional analysis for retail investors appeared. I conclude that earnings management is widely distributed around IPO deals and in the industry with higher revenue growth expectation.
Reference list
1.Aharony, J., Lin, C., & Loeb, M. (1993). Initial Public Offerings, Accounting Choices, and Earnings Management. Contemporary Accounting Research, 10(1), 61-81.
2.Ball, R., & Shivakumar, L. (2008). Earnings quality at initial public offerings. Journal of Accounting and Economics, 45(2), 324-349.
3.Burgstahler, David C., Hail, Luzi, & Leuz, Christian. (2006). The importance of reporting incentives: Earnings management in European private and public firms. Accounting Review, 81(5), 983-1016.
4.Damodaran, A. (2019, January 5). Historical (Compounded Annual) Growth Rates by Sector. Retrieved from http://pages.stern.nyu.edu/~adamodar/.
5.Burgstahler, D. C. and M. J. Eames. (1998). “Management of Earnings and Analyst Forecasts.” Working Paper, University of Washington and Santa Clara University.
6.Dechow, P., Sloan, R., & Sweeney, A. (1995). Detecting Earnings Management. The Accounting Review, 70(2), 193-225.
7.Dechow, P., Hutton, A., Kim, J., & Sloan, R. (2012). Detecting Earnings Management: A New Approach. Journal of Accounting Research, 50(2), 275-334.
8.Degeorge, F., Patel, J., & Zeckhauser, R. (1999). Earnings Management to Exceed Thresholds. The Journal of Business, 72(1), 1-33.
9.Healy, P., & Wahlen, J. M. (1999). A review of the earnings management literature and its implications for standard setting. Accounting Horizons, 13(4), 365-383.
10.International Accounting Standards Board. (2017). International financial reporting standards (IFRS's): Including international accounting standards (IAS's) and interpretations as at. London: International Accounting Standards Board.
11.Kothari, Leone, & Wasley. (2005). Performance matched discretionary accrual measures. Journal of Accounting and Economics, 39(1), 163-197.
12.Liu, J., Uchida, K., & Gao, R. (2014). Earnings management of initial public offering firms: Evidence from regulation changes in China. Accounting & Finance, 54(2), 505-537.
13.Mulford, W., & Comiskey, E. (2005). The Financial numbers game: Detecting creative accounting practices. Hoboken, NJ: John Wiley & Sons, Inc.
14.McNichols, M., Wilson, G., & DeAngelo, L. (1988). Evidence of Earnings Management from the Provision for Bad Debts. Journal of Accounting Research, 26(2), 1.
15.Plummer, E., & Mest, D. (2001). Evidence on the Management of Earnings Components. Journal of Accounting, Auditing & Finance, 16(4), 301-323.
16.Roychowdhury, S. (2006). Earnings management through real activities manipulation. Journal of Accounting and Economics, 42(3), 335-370.
17.Schipper, K. (1989). Earnings Management. Accounting Horizons, 3(4), 91-102.
18.Schrand, & Zechman. (2012). Executive overconfidence and the slippery slope to financial misreporting. Journal of Accounting and Economics, 53(1-2), 311-329.
Appendix 1
Stata do-file for regression models
import excel "/Users/ Disk C ", sheet("Telecom_pre_IPO") firstrow
drop in 73/80
summarize, detail
summarize AR GrossPPE TotalAssets NetIncome CFO
drop U V SUMMARYOUTPUT X Y Z AA AB AC AD AE
summarize AR GrossPPE TotalAssets NetIncome CFO
summarize AR GrossPPE TotalAssets NetIncome CFO
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, noconstant vce(hc3)
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
xttest3
ssc install xtest3
ssc describe x
findit xtest3
ssc install xttest3
xttest3
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
xttest3
xtreg
ssc install xtreg
xtger AccrualsLagTA M ChgCashRevLagTA PPELagTA
xttest3 AccrualsLagTA M ChgCashRevLagTA PPELagTA
AccrualsLagTA. xttest3
xttest3.
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
hausman AccrualsLagTA .
ac help
help
corrgram AccrualsLagTA
ac AccrualsLagTA
tsset AccrualsLagTA
drop aintercept bchgCashRev cPPE NormalAccurals DiscretionaryAcruals
drop in 73/80
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
tsset YEAR
predict AccrualsLagTA, xb
predict s1, residual
gen s1s = s1^2
scatter s1 AccrualsLagTA
regress s1s M ChgCashRevLagTA PPELagTA
gen AccrualsLagTA2 = AccrualsLagTA^2
regress s1s AccrualsLagTA AccrualsLagTA2
ovtest
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
help esttab
eststo: regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
ssc install eststo
findit eststo
findit eststo
scatter AccrualsLagTA ChgCashRevLagTA
scatter AccrualsLagTA PPELagTA
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
vif
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
predict r, resid
kdensity r, normal
swilk r
corr AccrualsLagTA M ChgCashRevLagTA PPELagTA, means
predict r, resid
kdensity r, normal
xttest3
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
xttest3
swilk r
estat imtest
estat hettest
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA
estat imtest
estat hettest
hettest
estat imtest, white
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
ovtest
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA
predict s2, residuals
gen s12s = s2^2
scatter s2 AccrualsLagTA
scatter s2s AccrualsLagTA
scatter s12s AccrualsLagTA
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA
sktest s2
var
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA
var
sktest s2
sktest AccrualsLagTA
correlate AccrualsLagTA M ChgCashRevLagTA PPELagTA
scatter AccrualsLagTA
scatter AccrualsLagTA PPELagTA
qnorm, r
qnorm r
graph save Graph "/Users/nikitarybin/Desktop/qnorm_residuals.gph"
qnorm r
pnrom r
pnorm r
scatter PPELagTA r
scatter r ChgCashRevLagTA
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
ovtest
import excel "/Users/nikitarybin/Desktop/DATA_Cases.xlsx", sheet("Auto_pre_IPO") firstrow clear
drop in 41/132
reg AccrualsLagTA L ChgCashRevLagTA PPELagTA, robust
predict r, residuals
ovtest
scatter PPELagTA r
scatter AccrualsLagTA r
predict r, resid
kdensity r, normal
pnorm r
qnorm r
kdensity r, normal
import excel "/Users/nikitarybin/Desktop/DATA_Cases.xlsx", sheet("Sheet1") firstrow clear
drop in 96
reg DiscretionaryAcruals Dummy_IPO Dummy_Telecom IPOxTELE
reg DiscretionaryAcruals Dummy_IPO Dummy_Telecom IPOxTELE, robust
import excel "/Users/ /Desktop/DATA_Cases.xlsx", sheet("Sheet1") firstrow clear
import excel "/Users/ /Desktop/DATA_Cases.xlsx", sheet("Sheet1") firstrow clear
regress DiscretionaryAcruals IPO Telecom IPOxTELE
regress DiscretionaryAcruals IPO Telecom IPOxTELE, robust
predict r, residuals
scatter DiscretionaryAcruals r
kdensity r, normal
summarize AR GrossPPE TotalAssets Revenue NetIncome CFO AccrualsLagTA, detail
tabulate TotalAssets Revenue
summarize
sktest AccrualsLagTA
sktest AccrualsLagTA M ChgCashRevLagTA PPELagTA
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
eststo regressiya1:regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
net from /Users/nikitarybin/Desktop/estout
net install estout, replace
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
import excel "/Users/nikitarybin/Desktop/DATA_Cases.xlsx", sheet("Telecom_non_IPO") firstrow clear
eststo regressiya1:regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
esttab regressiya1 using "regressiya1.rtf", replace l ///
rtf b se nodep ///
aic bic ///
scalars("r2 R-squared" "r2_a adjusted R-squared" "F F-stat" "") ///
unstack sfmt(%8.2f) nogaps ///
starlevels(+ 0.10 * 0.05 ** 0.01 *** 0.001) title("???????? ??????? 1")
esttab regressiya1 using "regressiya1.rtf", replace l ///
esttab regressiya1 using "regressiya1.rtf", replace l
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
eststo regressiya1:regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
esttab regressiya1 using "regressiya1.rtf", replace l
rtf b se nodep
aic bic
scalars("r2 R-squared" "r2_a adjusted R-squared" "F F-stat" "")
unstack sfmt(%8.2f) nogaps
starlevels(+ 0.10 * 0.05 ** 0.01 *** 0.001) title("???????? ??????? 1")
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
outreg2 using regression_results, replace word dec(3)
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
outreg2 using regression_results, replace word dec(3)
regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, robust
outreg2 using results, replace word dec(3)
ssc install asdoc
asdoc regress AccrualsLagTA M ChgCashRevLagTA PPELagTA, replace
asdoc sum, append
Размещено на Allbest.ru
...Подобные документы
The concept and features of bankruptcy. Methods prevent bankruptcy of Russian small businesses. General characteristics of crisis management. Calculating the probability of bankruptcy discriminant function in the example of "Kirov Plant "Mayak".
курсовая работа [74,5 K], добавлен 18.05.2015About cross-cultural management. Differences in cross-cultural management. Differences in methods of doing business. The globalization of the world economy and the role of cross-cultural relations. Cross-cultural issues in International Management.
контрольная работа [156,7 K], добавлен 14.04.2014Analysis of the peculiarities of the mobile applications market. The specifics of the process of mobile application development. Systematization of the main project management methodologies. Decision of the problems of use of the classical methodologies.
контрольная работа [1,4 M], добавлен 14.02.2016Definition of management. The aim of all managers. Their levels: executives, mid-managers and supervisors. The content and value of basic components of management: planning, organizing, coordinating, staffing, directing, controlling and evaluating.
презентация [414,2 K], добавлен 16.12.2014The primary goals and principles of asset management companies. The return of bank loans. Funds that are used as a working capital. Management perfection by material resources. Planning of purchases of necessary materials. Uses of modern warehouses.
реферат [14,4 K], добавлен 13.05.2013Types of the software for project management. The reasonability for usage of outsourcing in the implementation of information systems. The efficiency of outsourcing during the process of creating basic project plan of information system implementation.
реферат [566,4 K], добавлен 14.02.2016Organizational legal form. Full-time workers and out of staff workers. SWOT analyze of the company. Ways of motivation of employees. The planned market share. Discount and advertizing. Potential buyers. Name and logo of the company, the Mission.
курсовая работа [1,7 M], добавлен 15.06.2013Company’s representative of small business. Development a project management system in the small business, considering its specifics and promoting its development. Specifics of project management. Problems and structure of the enterprises of business.
реферат [120,6 K], добавлен 14.02.2016Milestones and direction of historical development in Germany, its current status and value in the world. The main rules and principles of business negotiations. Etiquette in management of German companies. The approaches to the formation of management.
презентация [7,8 M], добавлен 26.05.2015The impact of management and leadership styles on strategic decisions. Creating a leadership strategy that supports organizational direction. Appropriate methods to review current leadership requirements. Plan for the development of future situations.
курсовая работа [36,2 K], добавлен 20.05.2015Organizational structure of the company. Analysis of the external and internal environment. Assessment of the company's competitive strength. Company strategy proposal. Structure of implementation and creation of organizational structure of management.
дипломная работа [2,7 M], добавлен 19.01.2023Сущность понятия healthcare management, опыт его использования в зарубежных компаниях. Применяемые в данной системе методы и приемы, условия и возможности их использования в отечественных реалиях. Разработка и внедрение программы управления здоровьем.
контрольная работа [32,5 K], добавлен 26.01.2016Improving the business processes of customer relationship management through automation. Solutions the problem of the absence of automation of customer related business processes. Develop templates to support ongoing processes of customer relationships.
реферат [173,6 K], добавлен 14.02.2016Leaders are those who can make others perform tasks without being coerced through force or formal authority. Conflict Management Styles. Teambuilding is essential in the workplace and highly desirable skills to possess when seeking a new job, promotion.
реферат [23,7 K], добавлен 04.01.2016Составление проекта по методологии Oracle (комплекс методологий "Oracle Method") и по стандарту PMBOK (Project Management Body of Knowledge). Сравнение проектов, выявление их достоинств и недостатков, преимущественные сферы использования каждого.
контрольная работа [2,8 M], добавлен 28.05.2014Сущность CRM-систем - Customer Relationship Management. Преимущества клиенториентированного подхода к бизнесу. Формы функционирования и классификация CRM-систем. Основные инструменты, которые включает в себя технология управления отношениями с клиентами.
реферат [30,9 K], добавлен 12.01.2011Рассмотрение концепции Customer Relationship Management по управлению взаимоотношениями с клиентами. Возможности CRM-систем, их влияние на эффективность бизнеса. Разработка, реализация и стоимость проекта внедрения CRM-системы для ЗАО "Сибтехнология".
дипломная работа [5,5 M], добавлен 15.09.2012Logistics as a part of the supply chain process and storage of goods, services. Logistics software from enterprise resource planning. Physical distribution of transportation management systems. Real-time system with leading-edge proprietary technology.
контрольная работа [15,1 K], добавлен 18.07.2009The concept of transnational companies. Finding ways to improve production efficiency. International money and capital markets. The difference between Eurodollar deposits and ordinary deposit in the United States. The budget in multinational companies.
курсовая работа [34,2 K], добавлен 13.04.2013The audience understand the necessity of activity planning and the benefits acquired through budgeting. The role of the economic planning department. The main characteristics of the existing system of planning. The master budget, the budgeting process.
презентация [1,3 M], добавлен 12.01.2012
