top of page

(Vol)TurorCom Group

Public·10 members
Andrew Jackson
Andrew Jackson

Introduction To Econometrics Stock 3rd Zip ~REPACK~


Datasets (and in some cases replication scripts) are available forseveral popular econometrics textbooks, as shown in the table below.Please note that the .exe files are self-installers, for use onMS Windows only; the .tar.gz and .zip files arecompressed archives that are usable on any operating system. Notes oninstalling the files can be found beneath the table.




introduction to econometrics stock 3rd zip



Investments in stocks earn a substantially higher return than investment in safer assets in the long run, even after adjusting for risks in the stock market. However, not all households own stocks (Mankiw and Zeldes, 1991), and the share of U.S. households that invest in stocks has been much lower than the standard theory predicts--a phenomenon often referred to as the "participation puzzle." For example, according to the latest Survey of Consumer Finances, fewer than 15 percent of U.S. households own stocks directly, and only about 50 percent of households own stocks either directly or indirectly through mutual funds or retirement accounts (Bricker et al 2014).


Numerous theories, such as participation costs, incomplete information, and behavioral biases, have been offered to account for the lack of stock market participation. Notably, motivated by the notion that the social capital of a society may influence its financial developments, Guido, Sapienza, and Zingales (GSZ, 2008) argue that some people choose not to invest in stocks because of their lack of trust to the system and the market. They show that the individuals who trust others have a likelihood of investing in stocks that is 50 percent higher than the average participation rate, and among stock investors, those who trust others have a share invested in stocks that is 15 percent higher than the mean stock allocation.


Following Dokko, Li, and Hayes (2015), we take on this challenge and revisit the relationship between trust and stock market participation using the average level of credit scores within a community as an indicator of trusting attitude of people living in that community. The premise of using a community's average credit score to approximate its residents' trusting attitude is twofold. First, credit scores reflect people's previous experiences with credit markets and personal finance at large. The neighborhoods with lower average credit scores tend to be economically downtrodden or hit particularly hard during financially hard times. Arguably, residents in such community can feel more distrustful towards financial markets in general, including the stock market. Second, credit scores, to a certain extent, may reveal an individual's underlying trustworthiness, in addition to the likelihood of defaulting on financial obligations. Thus, other factors held constant, an individual who lives in a community where residents have higher credit scores tends to interact with more trustworthy people and thus be more trusting.


Our analysis confirms the findings of GSZ. People who live in areas with higher credit scores are more likely to own stocks and the share of stock investment in the entire portfolio is also higher for participating investors living in such areas, a result that holds even after controlling for a wide range of socioeconomic and demographic characteristics and the level of stock ownership of the community. In our baseline analysis, a one standard deviation increase in the mean credit score of a census tract (41 credit score points) boosts its residents' likelihood of owning stocks by 4 percentage points (20 percent of the mean stock market participation rate) and share of stocks in financial investment portfolio by 7 percentage points (35 percent of the mean stock allocation).


People's perceptions and attitudes may be determined in their childhood. They can also be influenced and changed throughout one's life by certain experiences and events. For example, Malmendier and Nagel (2011) present evidence that investors who experienced prolonged periods of low stock returns are less likely to later invest in stocks. Presumably, people who encountered negative credit events before, thereby having low credit scores, limited access to credit markets, and faring poorly on their personal finance, may be more distrustful towards the financial markets in general. Moreover, an individual who finds most of the people in the community he interacts to be trustworthy, thereby encountering less fraud and cheating, may have higher trust in others when dealing with personal investment and financial affairs.


We augment an econometric model that has been used extensively in stock market participation research with an array of community characteristics, including average credit scores. In our baseline analysis, a community is defined as a census tract, which has an average population of about 4,000. Specifically, we estimate the following logit model.


Our analysis uses a number of distinct data sources. For stock market participation status, share of stocks in financial portfolio, and household demographic and socioeconomic characteristics, we use the Survey of Consumer Finances (SCF), which is conducted by the Federal Reserve Board every three years and is widely regarded as the gold standard for data concerning U.S. household balance sheets. The SCF individual characteristics we use include race, the inverse hyperbolic sine transformation of household income and wealth, and bins of age, educational attainment, and risk aversions.3 For community demographic characteristics, we use 2000 U.S. Census statistics that include median income, share of college graduates, racial composition, and share of unemployed population. For local economic conditions, we use the Bureau of Labor Statistics QCEW data of employment and wage growth and the Corelogic data of house price growth, all at the county level.4


The model is estimated with standard errors clustered at the census tract level, and the results are reported in column 1 of table 1. As shown in the odds ratio estimates presented in brackets, a one standard deviation increase in the average credit score (41 credit score points) of the census tract an investor resides is associated with a 27.5 percent increase in the likelihood of investing directly in stocks, an estimate that is highly significant. The estimated effects of the control variables (not shown) are all consistent with findings in previous studies of stock ownership--investors who are more educated, less risk averse, white, and have higher income and wealth are more likely to own stocks. Interestingly, while the median income and racial and educational attainment composition of a tract are highly correlated with the average credit score of that tract, such community characteristics do not appear to have an effect on stock market participation decision. Regarding local economic conditions, our estimates indicate that better labor market conditions boost stock investments but higher house price growth reduces stock market participation, with the latter perhaps representing a substitution effect between investment in stocks and in real estate properties.


Although the SCF interviewer-provided assessment of the investors' trusting attitude is correlated with tract average credit scores, adding it as an additional control does not qualitatively change the baseline result (column 2). On its own right, consistent with the notion that more trusting investors are more likely to invest in the stock market, the estimated odds ratio for the SCF measure of trust indicates that the respondents who appeared to be more trusting of the survey are on average 15 percent more likely to invest in stocks, a margin that is also statistically significant.


Instead of the effects of trust on stock investment, the estimated β coefficient may reveal the fact that high credit score communities tend to have high stock ownership, which leads to more efficient information sharing that in turn induces a higher probability of individual residents investing in stocks. To further isolate the trust effect from this potential information channel, we add, as an additional control, the local share of stock ownership, which we estimate at the ZIP code level from the Statistics of Income (SOI) data released by the Internal Revenue Service.5 As shown in column 3, families living in a ZIP code that has a one standard deviation higher stock ownership have a 25 percent higher likelihood of owning stocks directly themselves. In this specification, the estimated β coefficient is appreciably smaller but significant statistically and sizeable economically. The reason why controlling for local stock ownership reduces the magnitude of β is that an area's average credit score tends to be highly correlated with its average stock ownership. While the cross-sectional analysis we implement in this note cannot fully address this endogeneity, we suspect that the true effect of trust on stock market participation should be somewhere between the estimates of column 1 and 3.


Finally, we study the effect of trust on the share of stock investment in household financial asset portfolios by estimating a tobit model with the same controls as in column 1. The results, reported in column (5) imply that a one standard deviation increase in tract mean credit score is associated with a 5 percentage point increase in stock investment share (20 percent of the mean stock investment share). The results presented in table 1 hold qualitatively when stock investment is defined as owning stock directly or through mutual funds or retirement accounts. These results also hold for an analysis at the county, instead of the census tract, level.


The long-run return to stock investment is higher than the return on investment in safer assets, which makes the low rate of participation in equity markets puzzling. Recent work underscores the importance of trust in explaining this puzzle (GSZ, 2008). This strand of literature typically uses self-reported and subjective measures of trust. Following Dokko, Li, and Hayes (2015), we use average credit scores in a community to approximate the trust level in the community. Using detailed information in the Survey of Consumer Finances and proprietary data from a major credit reporting agency, we find that investors who live in areas with higher levels of trusting attitudes have a higher likelihood of stock market participation and a greater share of stock investment, conditional on a wide variety of economic characteristics of the family and of the community. This finding is robust to the inclusion of an external assessment of the trusting attitude of the investor.


About

Welcome to the group! You can connect with other members, ge...

Members

bottom of page